Vincent Lejeune
2012-Oct-24 21:26 UTC
[LLVMdev] RegisterCoalescing Pass seems to ignore part of CFG.
Hi,
I don't know if my llvm ir code is faulty, or if I spot a bug in the
RegisterCoalescing Pass, so I'm posting my issue on the ML. Shader and
print-before-all dump are given below.
The interessing part is the vreg6/vreg48 reduction : before RegCoalescing, the
machine code is :
// BEFORE LOOP
... Some COPYs....
400B%vreg47<def> = COPY %vreg2<kill>; R600_Reg32:%vreg47,%vreg2
416B%vreg48<def> = COPY %vreg3<kill>; R600_Reg128:%vreg48,%vreg3
432B%vreg49<def> = COPY %vreg13<kill>; R600_Reg32:%vreg49,%vreg13
Successors according to CFG: BB#1
// LOOP CONDITION
464B%vreg5<def> = COPY %vreg47<kill>; R600_Reg32:%vreg5,%vreg47
480B%vreg6<def> = COPY %vreg48<kill>; R600_Reg128:%vreg6,%vreg48
496B%vreg7<def> = COPY %vreg49<kill>; R600_Reg32:%vreg7,%vreg49
512B%vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0,
0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7
528B%vreg30<def> = COPY %vreg29<kill>; R600_Reg32:%vreg30,%vreg29
544B%PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16;
R600_Reg32:%vreg30
560BJUMP <BB#3>, pred:%PREDICATE_BIT
576BJUMP <BB#2>, pred:%noreg
// LOOP BODY
896B%vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31
R600_Reg128:%vreg6
912B%vreg32:sel_x<def,read-undef> = COPY %vreg31<kill>;
R600_Reg128:%vreg32 R600_Reg32:%vreg31
928B%vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34
R600_Reg128:%vreg6
944B%vreg35<def> = COPY %vreg32<kill>; R600_Reg128:%vreg35,%vreg32
960B%vreg35:sel_y<def> = COPY %vreg34<kill>; R600_Reg128:%vreg35
R600_Reg32:%vreg34
976B%vreg36<def> = COPY %vreg35<kill>; R600_Reg128:%vreg36,%vreg35
992B%vreg36:sel_z<def> = COPY %vreg5<kill>; R600_Reg128:%vreg36
R600_Reg32:%vreg5
1008B%vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37
R600_Reg128:%vreg6
1024B%vreg10<def> = COPY %vreg36<kill>; R600_Reg128:%vreg10,%vreg36
1040B%vreg10:sel_w<def> = COPY %vreg37<kill>; R600_Reg128:%vreg10
R600_Reg32:%vreg37
1056B%vreg9<def> = COPY %vreg6:sel_z<kill>; R600_Reg32:%vreg9
R600_Reg128:%vreg6
1072B%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38
1088B%vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7<kill>, 0, 0, 0,
%vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0;
R600_Reg32:%vreg11,%vreg7,%vreg38
1104B%vreg47<def> = COPY %vreg9<kill>; R600_Reg32:%vreg47,%vreg9
1120B%vreg48<def> = COPY %vreg10<kill>; R600_Reg128:%vreg48,%vreg10
1136B%vreg49<def> = COPY %vreg11<kill>; R600_Reg32:%vreg49,%vreg11
1152BJUMP <BB#1>, pred:%noreg
// EXPORTED VALUES
608B%vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39
R600_Reg128:%vreg6
624B%T2_X<def> = COPY %vreg39<kill>; R600_Reg32:%vreg39
640B%vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40
R600_Reg128:%vreg6
656B%T2_Y<def> = COPY %vreg40<kill>; R600_Reg32:%vreg40
672B%vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41
R600_Reg128:%vreg6
688B%T2_Z<def> = COPY %vreg41<kill>; R600_Reg32:%vreg41
704B%vreg42<def> = COPY %vreg6:sel_w<kill>; R600_Reg32:%vreg42
R600_Reg128:%vreg6
720B%T2_W<def> = COPY %vreg42<kill>; R600_Reg32:%vreg42
And after the pass :
//Before Loop
...Some COPYs...
128B%vreg27:sel_x<def,read-undef> = COPY %C1_X; R600_Reg128:%vreg27
192B%vreg27:sel_y<def> = COPY %C1_Y; R600_Reg128:%vreg27
272B%vreg27:sel_z<def> = COPY %C1_Z; R600_Reg128:%vreg27
320B%vreg27:sel_w<def> = COPY %C1_W; R600_Reg128:%vreg27
//LOOP CONDITION
512B%vreg30<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %vreg49, 0,
0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg30,%vreg49
544B%PREDICATE_BIT<def> = PRED_X %vreg30, 152, 16; R600_Reg32:%vreg30
560BJUMP <BB#3>, pred:%PREDICATE_BIT
576BJUMP <BB#2>, pred:%noreg
//LOOP BODY
1072B%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38
1088B%vreg49<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg49, 0, 0, 0,
%vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0;
R600_Reg32:%vreg49,%vreg38
1152BJUMP <BB#1>, pred:%noreg
// EXPORTED VALUES
624B%T2_X<def> = COPY %vreg27:sel_x; R600_Reg128:%vreg27
656B%T2_Y<def> = COPY %vreg27:sel_y; R600_Reg128:%vreg27
688B%T2_Z<def> = COPY %vreg27:sel_z; R600_Reg128:%vreg27
720B%T2_W<def> = COPY %vreg27:sel_w; R600_Reg128:%vreg27
Apparently, the pass assumed that it's still in SSA mode, and join vreg6
with vreg27, thus ignoring the body block that can modify vreg48 value, and thus
vreg6 value.
I don't know if I should manually tell the pass that it's not in SSA
mode (I assume that previous pass like 2 address simplification pass does it),
if I miss something in my LLVM IR,
or if it's a bug.
Regards,
Vincent
The LLVM IR is the following :
____________________________________________________
; ModuleID = 'glsl-to-llvm'
define void @main() {
call void @llvm.AMDGPU.reserve.reg(i32 0)
call void @llvm.AMDGPU.reserve.reg(i32 1)
call void @llvm.AMDGPU.reserve.reg(i32 2)
call void @llvm.AMDGPU.reserve.reg(i32 3)
%1 = call float @llvm.AMDGPU.load.const(i32 0)
%2 = bitcast float %1 to i32
%3 = call float @llvm.AMDGPU.load.const(i32 4)
%4 = insertelement <4 x float> undef, float %3, i32 0
%5 = call float @llvm.AMDGPU.load.const(i32 5)
%6 = insertelement <4 x float> %4, float %5, i32 1
%7 = call float @llvm.AMDGPU.load.const(i32 6)
%8 = insertelement <4 x float> %6, float %7, i32 2
%9 = call float @llvm.AMDGPU.load.const(i32 7)
%10 = insertelement <4 x float> %8, float %9, i32 3
%11 = call float @llvm.R600.load.input(i32 4)
%12 = insertelement <4 x float> undef, float %11, i32 0
%13 = call float @llvm.R600.load.input(i32 5)
%14 = insertelement <4 x float> %12, float %13, i32 1
%15 = call float @llvm.R600.load.input(i32 6)
%16 = insertelement <4 x float> %14, float %15, i32 2
%17 = call float @llvm.R600.load.input(i32 7)
%18 = insertelement <4 x float> %16, float %17, i32 3
%19 = shufflevector <4 x float> %10, <4 x float> %10, <1 x
i32> <i32 1>
%20 = extractelement <1 x float> %19, i32 0
%21 = insertelement <1 x float> undef, float %20, i32 0
%22 = shufflevector <1 x float> undef, <1 x float> %21, <1 x
i32> <i32 1>
%23 = extractelement <1 x float> %22, i32 0
%24 = shufflevector <4 x float> undef, <4 x float> %10, <4 x
i32> <i32 4, i32 5, i32 6, i32 7>
br label %25
; <label>:25 ; preds = %41, %0
%26 = phi float [ %45, %41 ], [ undef, %0 ]
%27 = phi float [ %50, %41 ], [ %23, %0 ]
%28 = phi <4 x float> [ %53, %41 ], [ %24, %0 ]
%29 = phi i32 [ %58, %41 ], [ 0, %0 ]
%30 = icmp sge i32 %29, %2
br i1 %30, label %31, label %41
; <label>:31 ; preds = %25
%32 = shufflevector <4 x float> undef, <4 x float> %18, <4 x
i32> <i32 4, i32 5, i32 6, i32 7>
%33 = extractelement <4 x float> %28, i32 0
call void @llvm.AMDGPU.store.output(float %33, i32 8)
%34 = extractelement <4 x float> %28, i32 1
call void @llvm.AMDGPU.store.output(float %34, i32 9)
%35 = extractelement <4 x float> %28, i32 2
call void @llvm.AMDGPU.store.output(float %35, i32 10)
%36 = extractelement <4 x float> %28, i32 3
call void @llvm.AMDGPU.store.output(float %36, i32 11)
%37 = extractelement <4 x float> %32, i32 0
call void @llvm.AMDGPU.store.output(float %37, i32 4)
%38 = extractelement <4 x float> %32, i32 1
call void @llvm.AMDGPU.store.output(float %38, i32 5)
%39 = extractelement <4 x float> %32, i32 2
call void @llvm.AMDGPU.store.output(float %39, i32 6)
%40 = extractelement <4 x float> %32, i32 3
call void @llvm.AMDGPU.store.output(float %40, i32 7)
ret void
; <label>:41 ; preds = %25
%42 = insertelement <1 x float> undef, float %27, i32 0
%43 = insertelement <1 x float> undef, float %26, i32 0
%44 = shufflevector <1 x float> %43, <1 x float> %42, <1 x
i32> <i32 1>
%45 = extractelement <1 x float> %44, i32 0
%46 = shufflevector <4 x float> %28, <4 x float> %28, <1 x
i32> <i32 2>
%47 = extractelement <1 x float> %46, i32 0
%48 = insertelement <1 x float> undef, float %47, i32 0
%49 = shufflevector <1 x float> %42, <1 x float> %48, <1 x
i32> <i32 1>
%50 = extractelement <1 x float> %49, i32 0
%51 = insertelement <1 x float> undef, float %45, i32 0
%52 = shufflevector <1 x float> %51, <1 x float> %51, <4 x
i32> <i32 0, i32 undef, i32 undef, i32 undef>
%53 = shufflevector <4 x float> %28, <4 x float> %52, <4 x
i32> <i32 0, i32 1, i32 4, i32 3>
%54 = add i32 %29, 1
%55 = insertelement <1 x i32> undef, i32 %54, i32 0
%56 = insertelement <1 x i32> undef, i32 %29, i32 0
%57 = shufflevector <1 x i32> %56, <1 x i32> %55, <1 x i32>
<i32 1>
%58 = extractelement <1 x i32> %57, i32 0
br label %25
}
declare float @llvm.AMDGPU.load.const(i32) readnone
declare float @llvm.R600.load.input(i32) readnone
declare void @llvm.AMDGPU.store.output(float, i32)
declare void @llvm.AMDGPU.reserve.reg(i32)
declare float @llvm.R600.load.input.perspective(i32) readnone
declare float @llvm.R600.load.input.constant(i32) readnone
declare float @llvm.R600.load.input.linear(i32) readnone
_________________________________________________________________
The print before all dump is :
*** IR Dump Before Preliminary module verification ***
define void @main() {
call void @llvm.AMDGPU.reserve.reg(i32 0)
call void @llvm.AMDGPU.reserve.reg(i32 1)
call void @llvm.AMDGPU.reserve.reg(i32 2)
call void @llvm.AMDGPU.reserve.reg(i32 3)
%1 = call float @llvm.AMDGPU.load.const(i32 0)
%2 = bitcast float %1 to i32
%3 = call float @llvm.AMDGPU.load.const(i32 4)
%4 = insertelement <4 x float> undef, float %3, i32 0
%5 = call float @llvm.AMDGPU.load.const(i32 5)
%6 = insertelement <4 x float> %4, float %5, i32 1
%7 = call float @llvm.AMDGPU.load.const(i32 6)
%8 = insertelement <4 x float> %6, float %7, i32 2
%9 = call float @llvm.AMDGPU.load.const(i32 7)
%10 = insertelement <4 x float> %8, float %9, i32 3
%11 = call float @llvm.R600.load.input(i32 4)
%12 = insertelement <4 x float> undef, float %11, i32 0
%13 = call float @llvm.R600.load.input(i32 5)
%14 = insertelement <4 x float> %12, float %13, i32 1
%15 = call float @llvm.R600.load.input(i32 6)
%16 = insertelement <4 x float> %14, float %15, i32 2
%17 = call float @llvm.R600.load.input(i32 7)
%18 = insertelement <4 x float> %16, float %17, i32 3
%19 = shufflevector <4 x float> %10, <4 x float> %10, <1 x
i32> <i32 1>
%20 = extractelement <1 x float> %19, i32 0
%21 = insertelement <1 x float> undef, float %20, i32 0
%22 = shufflevector <1 x float> undef, <1 x float> %21, <1 x
i32> <i32 1>
%23 = extractelement <1 x float> %22, i32 0
%24 = shufflevector <4 x float> undef, <4 x float> %10, <4 x
i32> <i32 4, i32 5, i32 6, i32 7>
br label %25
; <label>:25 ; preds = %41, %0
%26 = phi float [ %45, %41 ], [ undef, %0 ]
%27 = phi float [ %50, %41 ], [ %23, %0 ]
%28 = phi <4 x float> [ %53, %41 ], [ %24, %0 ]
%29 = phi i32 [ %58, %41 ], [ 0, %0 ]
%30 = icmp sge i32 %29, %2
br i1 %30, label %31, label %41
; <label>:31 ; preds = %25
%32 = shufflevector <4 x float> undef, <4 x float> %18, <4 x
i32> <i32 4, i32 5, i32 6, i32 7>
%33 = extractelement <4 x float> %28, i32 0
call void @llvm.AMDGPU.store.output(float %33, i32 8)
%34 = extractelement <4 x float> %28, i32 1
call void @llvm.AMDGPU.store.output(float %34, i32 9)
%35 = extractelement <4 x float> %28, i32 2
call void @llvm.AMDGPU.store.output(float %35, i32 10)
%36 = extractelement <4 x float> %28, i32 3
call void @llvm.AMDGPU.store.output(float %36, i32 11)
%37 = extractelement <4 x float> %32, i32 0
call void @llvm.AMDGPU.store.output(float %37, i32 4)
%38 = extractelement <4 x float> %32, i32 1
call void @llvm.AMDGPU.store.output(float %38, i32 5)
%39 = extractelement <4 x float> %32, i32 2
call void @llvm.AMDGPU.store.output(float %39, i32 6)
%40 = extractelement <4 x float> %32, i32 3
call void @llvm.AMDGPU.store.output(float %40, i32 7)
ret void
; <label>:41 ; preds = %25
%42 = insertelement <1 x float> undef, float %27, i32 0
%43 = insertelement <1 x float> undef, float %26, i32 0
%44 = shufflevector <1 x float> %43, <1 x float> %42, <1 x
i32> <i32 1>
%45 = extractelement <1 x float> %44, i32 0
%46 = shufflevector <4 x float> %28, <4 x float> %28, <1 x
i32> <i32 2>
%47 = extractelement <1 x float> %46, i32 0
%48 = insertelement <1 x float> undef, float %47, i32 0
%49 = shufflevector <1 x float> %42, <1 x float> %48, <1 x
i32> <i32 1>
%50 = extractelement <1 x float> %49, i32 0
%51 = insertelement <1 x float> undef, float %45, i32 0
%52 = shufflevector <1 x float> %51, <1 x float> %51, <4 x
i32> <i32 0, i32 undef, i32 undef, i32 undef>
%53 = shufflevector <4 x float> %28, <4 x float> %52, <4 x
i32> <i32 0, i32 1, i32 4, i32 3>
%54 = add i32 %29, 1
%55 = insertelement <1 x i32> undef, i32 %54, i32 0
%56 = insertelement <1 x i32> undef, i32 %29, i32 0
%57 = shufflevector <1 x i32> %56, <1 x i32> %55, <1 x i32>
<i32 1>
%58 = extractelement <1 x i32> %57, i32 0
br label %25
}
*** IR Dump Before Module Verifier ***
define void @main() {
call void @llvm.AMDGPU.reserve.reg(i32 0)
call void @llvm.AMDGPU.reserve.reg(i32 1)
call void @llvm.AMDGPU.reserve.reg(i32 2)
call void @llvm.AMDGPU.reserve.reg(i32 3)
%1 = call float @llvm.AMDGPU.load.const(i32 0)
%2 = bitcast float %1 to i32
%3 = call float @llvm.AMDGPU.load.const(i32 4)
%4 = insertelement <4 x float> undef, float %3, i32 0
%5 = call float @llvm.AMDGPU.load.const(i32 5)
%6 = insertelement <4 x float> %4, float %5, i32 1
%7 = call float @llvm.AMDGPU.load.const(i32 6)
%8 = insertelement <4 x float> %6, float %7, i32 2
%9 = call float @llvm.AMDGPU.load.const(i32 7)
%10 = insertelement <4 x float> %8, float %9, i32 3
%11 = call float @llvm.R600.load.input(i32 4)
%12 = insertelement <4 x float> undef, float %11, i32 0
%13 = call float @llvm.R600.load.input(i32 5)
%14 = insertelement <4 x float> %12, float %13, i32 1
%15 = call float @llvm.R600.load.input(i32 6)
%16 = insertelement <4 x float> %14, float %15, i32 2
%17 = call float @llvm.R600.load.input(i32 7)
%18 = insertelement <4 x float> %16, float %17, i32 3
%19 = shufflevector <4 x float> %10, <4 x float> %10, <1 x
i32> <i32 1>
%20 = extractelement <1 x float> %19, i32 0
%21 = insertelement <1 x float> undef, float %20, i32 0
%22 = shufflevector <1 x float> undef, <1 x float> %21, <1 x
i32> <i32 1>
%23 = extractelement <1 x float> %22, i32 0
%24 = shufflevector <4 x float> undef, <4 x float> %10, <4 x
i32> <i32 4, i32 5, i32 6, i32 7>
br label %25
; <label>:25 ; preds = %41, %0
%26 = phi float [ %45, %41 ], [ undef, %0 ]
%27 = phi float [ %50, %41 ], [ %23, %0 ]
%28 = phi <4 x float> [ %53, %41 ], [ %24, %0 ]
%29 = phi i32 [ %58, %41 ], [ 0, %0 ]
%30 = icmp sge i32 %29, %2
br i1 %30, label %31, label %41
; <label>:31 ; preds = %25
%32 = shufflevector <4 x float> undef, <4 x float> %18, <4 x
i32> <i32 4, i32 5, i32 6, i32 7>
%33 = extractelement <4 x float> %28, i32 0
call void @llvm.AMDGPU.store.output(float %33, i32 8)
%34 = extractelement <4 x float> %28, i32 1
call void @llvm.AMDGPU.store.output(float %34, i32 9)
%35 = extractelement <4 x float> %28, i32 2
call void @llvm.AMDGPU.store.output(float %35, i32 10)
%36 = extractelement <4 x float> %28, i32 3
call void @llvm.AMDGPU.store.output(float %36, i32 11)
%37 = extractelement <4 x float> %32, i32 0
call void @llvm.AMDGPU.store.output(float %37, i32 4)
%38 = extractelement <4 x float> %32, i32 1
call void @llvm.AMDGPU.store.output(float %38, i32 5)
%39 = extractelement <4 x float> %32, i32 2
call void @llvm.AMDGPU.store.output(float %39, i32 6)
%40 = extractelement <4 x float> %32, i32 3
call void @llvm.AMDGPU.store.output(float %40, i32 7)
ret void
; <label>:41 ; preds = %25
%42 = insertelement <1 x float> undef, float %27, i32 0
%43 = insertelement <1 x float> undef, float %26, i32 0
%44 = shufflevector <1 x float> %43, <1 x float> %42, <1 x
i32> <i32 1>
%45 = extractelement <1 x float> %44, i32 0
%46 = shufflevector <4 x float> %28, <4 x float> %28, <1 x
i32> <i32 2>
%47 = extractelement <1 x float> %46, i32 0
%48 = insertelement <1 x float> undef, float %47, i32 0
%49 = shufflevector <1 x float> %42, <1 x float> %48, <1 x
i32> <i32 1>
%50 = extractelement <1 x float> %49, i32 0
%51 = insertelement <1 x float> undef, float %45, i32 0
%52 = shufflevector <1 x float> %51, <1 x float> %51, <4 x
i32> <i32 0, i32 undef, i32 undef, i32 undef>
%53 = shufflevector <4 x float> %28, <4 x float> %52, <4 x
i32> <i32 0, i32 1, i32 4, i32 3>
%54 = add i32 %29, 1
%55 = insertelement <1 x i32> undef, i32 %54, i32 0
%56 = insertelement <1 x i32> undef, i32 %29, i32 0
%57 = shufflevector <1 x i32> %56, <1 x i32> %55, <1 x i32>
<i32 1>
%58 = extractelement <1 x i32> %57, i32 0
br label %25
}
*** IR Dump Before Canonicalize natural loops ***
; <label>:25 ; preds = %41, %0
%26 = phi float [ %45, %41 ], [ undef, %0 ]
%27 = phi float [ %50, %41 ], [ %23, %0 ]
%28 = phi <4 x float> [ %53, %41 ], [ %24, %0 ]
%29 = phi i32 [ %58, %41 ], [ 0, %0 ]
%30 = icmp sge i32 %29, %2
br i1 %30, label %31, label %41
; <label>:41 ; preds = %25
%42 = insertelement <1 x float> undef, float %27, i32 0
%43 = insertelement <1 x float> undef, float %26, i32 0
%44 = shufflevector <1 x float> %43, <1 x float> %42, <1 x
i32> <i32 1>
%45 = extractelement <1 x float> %44, i32 0
%46 = shufflevector <4 x float> %28, <4 x float> %28, <1 x
i32> <i32 2>
%47 = extractelement <1 x float> %46, i32 0
%48 = insertelement <1 x float> undef, float %47, i32 0
%49 = shufflevector <1 x float> %42, <1 x float> %48, <1 x
i32> <i32 1>
%50 = extractelement <1 x float> %49, i32 0
%51 = insertelement <1 x float> undef, float %45, i32 0
%52 = shufflevector <1 x float> %51, <1 x float> %51, <4 x
i32> <i32 0, i32 undef, i32 undef, i32 undef>
%53 = shufflevector <4 x float> %28, <4 x float> %52, <4 x
i32> <i32 0, i32 1, i32 4, i32 3>
%54 = add i32 %29, 1
%55 = insertelement <1 x i32> undef, i32 %54, i32 0
%56 = insertelement <1 x i32> undef, i32 %29, i32 0
%57 = shufflevector <1 x i32> %56, <1 x i32> %55, <1 x i32>
<i32 1>
%58 = extractelement <1 x i32> %57, i32 0
br label %25
*** IR Dump Before Canonicalize natural loops ***
; <label>:25 ; preds = %41, %0
%26 = phi float [ %45, %41 ], [ undef, %0 ]
%27 = phi float [ %50, %41 ], [ %23, %0 ]
%28 = phi <4 x float> [ %53, %41 ], [ %24, %0 ]
%29 = phi i32 [ %58, %41 ], [ 0, %0 ]
%30 = icmp sge i32 %29, %2
br i1 %30, label %31, label %41
; <label>:41 ; preds = %25
%42 = insertelement <1 x float> undef, float %27, i32 0
%43 = insertelement <1 x float> undef, float %26, i32 0
%44 = shufflevector <1 x float> %43, <1 x float> %42, <1 x
i32> <i32 1>
%45 = extractelement <1 x float> %44, i32 0
%46 = shufflevector <4 x float> %28, <4 x float> %28, <1 x
i32> <i32 2>
%47 = extractelement <1 x float> %46, i32 0
%48 = insertelement <1 x float> undef, float %47, i32 0
%49 = shufflevector <1 x float> %42, <1 x float> %48, <1 x
i32> <i32 1>
%50 = extractelement <1 x float> %49, i32 0
%51 = insertelement <1 x float> undef, float %45, i32 0
%52 = shufflevector <1 x float> %51, <1 x float> %51, <4 x
i32> <i32 0, i32 undef, i32 undef, i32 undef>
%53 = shufflevector <4 x float> %28, <4 x float> %52, <4 x
i32> <i32 0, i32 1, i32 4, i32 3>
%54 = add i32 %29, 1
%55 = insertelement <1 x i32> undef, i32 %54, i32 0
%56 = insertelement <1 x i32> undef, i32 %29, i32 0
%57 = shufflevector <1 x i32> %56, <1 x i32> %55, <1 x i32>
<i32 1>
%58 = extractelement <1 x i32> %57, i32 0
br label %25
*** IR Dump Before Loop Strength Reduction ***
; <label>:25 ; preds = %41, %0
%26 = phi float [ %45, %41 ], [ undef, %0 ]
%27 = phi float [ %50, %41 ], [ %23, %0 ]
%28 = phi <4 x float> [ %53, %41 ], [ %24, %0 ]
%29 = phi i32 [ %58, %41 ], [ 0, %0 ]
%30 = icmp sge i32 %29, %2
br i1 %30, label %31, label %41
; <label>:41 ; preds = %25
%42 = insertelement <1 x float> undef, float %27, i32 0
%43 = insertelement <1 x float> undef, float %26, i32 0
%44 = shufflevector <1 x float> %43, <1 x float> %42, <1 x
i32> <i32 1>
%45 = extractelement <1 x float> %44, i32 0
%46 = shufflevector <4 x float> %28, <4 x float> %28, <1 x
i32> <i32 2>
%47 = extractelement <1 x float> %46, i32 0
%48 = insertelement <1 x float> undef, float %47, i32 0
%49 = shufflevector <1 x float> %42, <1 x float> %48, <1 x
i32> <i32 1>
%50 = extractelement <1 x float> %49, i32 0
%51 = insertelement <1 x float> undef, float %45, i32 0
%52 = shufflevector <1 x float> %51, <1 x float> %51, <4 x
i32> <i32 0, i32 undef, i32 undef, i32 undef>
%53 = shufflevector <4 x float> %28, <4 x float> %52, <4 x
i32> <i32 0, i32 1, i32 4, i32 3>
%54 = add i32 %29, 1
%55 = insertelement <1 x i32> undef, i32 %54, i32 0
%56 = insertelement <1 x i32> undef, i32 %29, i32 0
%57 = shufflevector <1 x i32> %56, <1 x i32> %55, <1 x i32>
<i32 1>
%58 = extractelement <1 x i32> %57, i32 0
br label %25
*** IR Dump Before Lower Garbage Collection Instructions ***
define void @main() {
call void @llvm.AMDGPU.reserve.reg(i32 0)
call void @llvm.AMDGPU.reserve.reg(i32 1)
call void @llvm.AMDGPU.reserve.reg(i32 2)
call void @llvm.AMDGPU.reserve.reg(i32 3)
%1 = call float @llvm.AMDGPU.load.const(i32 0)
%2 = bitcast float %1 to i32
%3 = call float @llvm.AMDGPU.load.const(i32 4)
%4 = insertelement <4 x float> undef, float %3, i32 0
%5 = call float @llvm.AMDGPU.load.const(i32 5)
%6 = insertelement <4 x float> %4, float %5, i32 1
%7 = call float @llvm.AMDGPU.load.const(i32 6)
%8 = insertelement <4 x float> %6, float %7, i32 2
%9 = call float @llvm.AMDGPU.load.const(i32 7)
%10 = insertelement <4 x float> %8, float %9, i32 3
%11 = call float @llvm.R600.load.input(i32 4)
%12 = insertelement <4 x float> undef, float %11, i32 0
%13 = call float @llvm.R600.load.input(i32 5)
%14 = insertelement <4 x float> %12, float %13, i32 1
%15 = call float @llvm.R600.load.input(i32 6)
%16 = insertelement <4 x float> %14, float %15, i32 2
%17 = call float @llvm.R600.load.input(i32 7)
%18 = insertelement <4 x float> %16, float %17, i32 3
%19 = shufflevector <4 x float> %10, <4 x float> %10, <1 x
i32> <i32 1>
%20 = extractelement <1 x float> %19, i32 0
%21 = insertelement <1 x float> undef, float %20, i32 0
%22 = shufflevector <1 x float> undef, <1 x float> %21, <1 x
i32> <i32 1>
%23 = extractelement <1 x float> %22, i32 0
%24 = shufflevector <4 x float> undef, <4 x float> %10, <4 x
i32> <i32 4, i32 5, i32 6, i32 7>
br label %25
; <label>:25 ; preds = %41, %0
%26 = phi float [ %45, %41 ], [ undef, %0 ]
%27 = phi float [ %50, %41 ], [ %23, %0 ]
%28 = phi <4 x float> [ %53, %41 ], [ %24, %0 ]
%29 = phi i32 [ %58, %41 ], [ 0, %0 ]
%30 = icmp sge i32 %29, %2
br i1 %30, label %31, label %41
; <label>:31 ; preds = %25
%32 = shufflevector <4 x float> undef, <4 x float> %18, <4 x
i32> <i32 4, i32 5, i32 6, i32 7>
%33 = extractelement <4 x float> %28, i32 0
call void @llvm.AMDGPU.store.output(float %33, i32 8)
%34 = extractelement <4 x float> %28, i32 1
call void @llvm.AMDGPU.store.output(float %34, i32 9)
%35 = extractelement <4 x float> %28, i32 2
call void @llvm.AMDGPU.store.output(float %35, i32 10)
%36 = extractelement <4 x float> %28, i32 3
call void @llvm.AMDGPU.store.output(float %36, i32 11)
%37 = extractelement <4 x float> %32, i32 0
call void @llvm.AMDGPU.store.output(float %37, i32 4)
%38 = extractelement <4 x float> %32, i32 1
call void @llvm.AMDGPU.store.output(float %38, i32 5)
%39 = extractelement <4 x float> %32, i32 2
call void @llvm.AMDGPU.store.output(float %39, i32 6)
%40 = extractelement <4 x float> %32, i32 3
call void @llvm.AMDGPU.store.output(float %40, i32 7)
ret void
; <label>:41 ; preds = %25
%42 = insertelement <1 x float> undef, float %27, i32 0
%43 = insertelement <1 x float> undef, float %26, i32 0
%44 = shufflevector <1 x float> %43, <1 x float> %42, <1 x
i32> <i32 1>
%45 = extractelement <1 x float> %44, i32 0
%46 = shufflevector <4 x float> %28, <4 x float> %28, <1 x
i32> <i32 2>
%47 = extractelement <1 x float> %46, i32 0
%48 = insertelement <1 x float> undef, float %47, i32 0
%49 = shufflevector <1 x float> %42, <1 x float> %48, <1 x
i32> <i32 1>
%50 = extractelement <1 x float> %49, i32 0
%51 = insertelement <1 x float> undef, float %45, i32 0
%52 = shufflevector <1 x float> %51, <1 x float> %51, <4 x
i32> <i32 0, i32 undef, i32 undef, i32 undef>
%53 = shufflevector <4 x float> %28, <4 x float> %52, <4 x
i32> <i32 0, i32 1, i32 4, i32 3>
%54 = add i32 %29, 1
%55 = insertelement <1 x i32> undef, i32 %54, i32 0
%56 = insertelement <1 x i32> undef, i32 %29, i32 0
%57 = shufflevector <1 x i32> %56, <1 x i32> %55, <1 x i32>
<i32 1>
%58 = extractelement <1 x i32> %57, i32 0
br label %25
}
*** IR Dump Before Remove unreachable blocks from the CFG ***
define void @main() {
call void @llvm.AMDGPU.reserve.reg(i32 0)
call void @llvm.AMDGPU.reserve.reg(i32 1)
call void @llvm.AMDGPU.reserve.reg(i32 2)
call void @llvm.AMDGPU.reserve.reg(i32 3)
%1 = call float @llvm.AMDGPU.load.const(i32 0)
%2 = bitcast float %1 to i32
%3 = call float @llvm.AMDGPU.load.const(i32 4)
%4 = insertelement <4 x float> undef, float %3, i32 0
%5 = call float @llvm.AMDGPU.load.const(i32 5)
%6 = insertelement <4 x float> %4, float %5, i32 1
%7 = call float @llvm.AMDGPU.load.const(i32 6)
%8 = insertelement <4 x float> %6, float %7, i32 2
%9 = call float @llvm.AMDGPU.load.const(i32 7)
%10 = insertelement <4 x float> %8, float %9, i32 3
%11 = call float @llvm.R600.load.input(i32 4)
%12 = insertelement <4 x float> undef, float %11, i32 0
%13 = call float @llvm.R600.load.input(i32 5)
%14 = insertelement <4 x float> %12, float %13, i32 1
%15 = call float @llvm.R600.load.input(i32 6)
%16 = insertelement <4 x float> %14, float %15, i32 2
%17 = call float @llvm.R600.load.input(i32 7)
%18 = insertelement <4 x float> %16, float %17, i32 3
%19 = shufflevector <4 x float> %10, <4 x float> %10, <1 x
i32> <i32 1>
%20 = extractelement <1 x float> %19, i32 0
%21 = insertelement <1 x float> undef, float %20, i32 0
%22 = shufflevector <1 x float> undef, <1 x float> %21, <1 x
i32> <i32 1>
%23 = extractelement <1 x float> %22, i32 0
%24 = shufflevector <4 x float> undef, <4 x float> %10, <4 x
i32> <i32 4, i32 5, i32 6, i32 7>
br label %25
; <label>:25 ; preds = %41, %0
%26 = phi float [ %45, %41 ], [ undef, %0 ]
%27 = phi float [ %50, %41 ], [ %23, %0 ]
%28 = phi <4 x float> [ %53, %41 ], [ %24, %0 ]
%29 = phi i32 [ %58, %41 ], [ 0, %0 ]
%30 = icmp sge i32 %29, %2
br i1 %30, label %31, label %41
; <label>:31 ; preds = %25
%32 = shufflevector <4 x float> undef, <4 x float> %18, <4 x
i32> <i32 4, i32 5, i32 6, i32 7>
%33 = extractelement <4 x float> %28, i32 0
call void @llvm.AMDGPU.store.output(float %33, i32 8)
%34 = extractelement <4 x float> %28, i32 1
call void @llvm.AMDGPU.store.output(float %34, i32 9)
%35 = extractelement <4 x float> %28, i32 2
call void @llvm.AMDGPU.store.output(float %35, i32 10)
%36 = extractelement <4 x float> %28, i32 3
call void @llvm.AMDGPU.store.output(float %36, i32 11)
%37 = extractelement <4 x float> %32, i32 0
call void @llvm.AMDGPU.store.output(float %37, i32 4)
%38 = extractelement <4 x float> %32, i32 1
call void @llvm.AMDGPU.store.output(float %38, i32 5)
%39 = extractelement <4 x float> %32, i32 2
call void @llvm.AMDGPU.store.output(float %39, i32 6)
%40 = extractelement <4 x float> %32, i32 3
call void @llvm.AMDGPU.store.output(float %40, i32 7)
ret void
; <label>:41 ; preds = %25
%42 = insertelement <1 x float> undef, float %27, i32 0
%43 = insertelement <1 x float> undef, float %26, i32 0
%44 = shufflevector <1 x float> %43, <1 x float> %42, <1 x
i32> <i32 1>
%45 = extractelement <1 x float> %44, i32 0
%46 = shufflevector <4 x float> %28, <4 x float> %28, <1 x
i32> <i32 2>
%47 = extractelement <1 x float> %46, i32 0
%48 = insertelement <1 x float> undef, float %47, i32 0
%49 = shufflevector <1 x float> %42, <1 x float> %48, <1 x
i32> <i32 1>
%50 = extractelement <1 x float> %49, i32 0
%51 = insertelement <1 x float> undef, float %45, i32 0
%52 = shufflevector <1 x float> %51, <1 x float> %51, <4 x
i32> <i32 0, i32 undef, i32 undef, i32 undef>
%53 = shufflevector <4 x float> %28, <4 x float> %52, <4 x
i32> <i32 0, i32 1, i32 4, i32 3>
%54 = add i32 %29, 1
%55 = insertelement <1 x i32> undef, i32 %54, i32 0
%56 = insertelement <1 x i32> undef, i32 %29, i32 0
%57 = shufflevector <1 x i32> %56, <1 x i32> %55, <1 x i32>
<i32 1>
%58 = extractelement <1 x i32> %57, i32 0
br label %25
}
*** IR Dump Before Lower invoke and unwind, for unwindless code generators ***
define void @main() {
call void @llvm.AMDGPU.reserve.reg(i32 0)
call void @llvm.AMDGPU.reserve.reg(i32 1)
call void @llvm.AMDGPU.reserve.reg(i32 2)
call void @llvm.AMDGPU.reserve.reg(i32 3)
%1 = call float @llvm.AMDGPU.load.const(i32 0)
%2 = bitcast float %1 to i32
%3 = call float @llvm.AMDGPU.load.const(i32 4)
%4 = insertelement <4 x float> undef, float %3, i32 0
%5 = call float @llvm.AMDGPU.load.const(i32 5)
%6 = insertelement <4 x float> %4, float %5, i32 1
%7 = call float @llvm.AMDGPU.load.const(i32 6)
%8 = insertelement <4 x float> %6, float %7, i32 2
%9 = call float @llvm.AMDGPU.load.const(i32 7)
%10 = insertelement <4 x float> %8, float %9, i32 3
%11 = call float @llvm.R600.load.input(i32 4)
%12 = insertelement <4 x float> undef, float %11, i32 0
%13 = call float @llvm.R600.load.input(i32 5)
%14 = insertelement <4 x float> %12, float %13, i32 1
%15 = call float @llvm.R600.load.input(i32 6)
%16 = insertelement <4 x float> %14, float %15, i32 2
%17 = call float @llvm.R600.load.input(i32 7)
%18 = insertelement <4 x float> %16, float %17, i32 3
%19 = shufflevector <4 x float> %10, <4 x float> %10, <1 x
i32> <i32 1>
%20 = extractelement <1 x float> %19, i32 0
%21 = insertelement <1 x float> undef, float %20, i32 0
%22 = shufflevector <1 x float> undef, <1 x float> %21, <1 x
i32> <i32 1>
%23 = extractelement <1 x float> %22, i32 0
%24 = shufflevector <4 x float> undef, <4 x float> %10, <4 x
i32> <i32 4, i32 5, i32 6, i32 7>
br label %25
; <label>:25 ; preds = %41, %0
%26 = phi float [ %45, %41 ], [ undef, %0 ]
%27 = phi float [ %50, %41 ], [ %23, %0 ]
%28 = phi <4 x float> [ %53, %41 ], [ %24, %0 ]
%29 = phi i32 [ %58, %41 ], [ 0, %0 ]
%30 = icmp sge i32 %29, %2
br i1 %30, label %31, label %41
; <label>:31 ; preds = %25
%32 = shufflevector <4 x float> undef, <4 x float> %18, <4 x
i32> <i32 4, i32 5, i32 6, i32 7>
%33 = extractelement <4 x float> %28, i32 0
call void @llvm.AMDGPU.store.output(float %33, i32 8)
%34 = extractelement <4 x float> %28, i32 1
call void @llvm.AMDGPU.store.output(float %34, i32 9)
%35 = extractelement <4 x float> %28, i32 2
call void @llvm.AMDGPU.store.output(float %35, i32 10)
%36 = extractelement <4 x float> %28, i32 3
call void @llvm.AMDGPU.store.output(float %36, i32 11)
%37 = extractelement <4 x float> %32, i32 0
call void @llvm.AMDGPU.store.output(float %37, i32 4)
%38 = extractelement <4 x float> %32, i32 1
call void @llvm.AMDGPU.store.output(float %38, i32 5)
%39 = extractelement <4 x float> %32, i32 2
call void @llvm.AMDGPU.store.output(float %39, i32 6)
%40 = extractelement <4 x float> %32, i32 3
call void @llvm.AMDGPU.store.output(float %40, i32 7)
ret void
; <label>:41 ; preds = %25
%42 = insertelement <1 x float> undef, float %27, i32 0
%43 = insertelement <1 x float> undef, float %26, i32 0
%44 = shufflevector <1 x float> %43, <1 x float> %42, <1 x
i32> <i32 1>
%45 = extractelement <1 x float> %44, i32 0
%46 = shufflevector <4 x float> %28, <4 x float> %28, <1 x
i32> <i32 2>
%47 = extractelement <1 x float> %46, i32 0
%48 = insertelement <1 x float> undef, float %47, i32 0
%49 = shufflevector <1 x float> %42, <1 x float> %48, <1 x
i32> <i32 1>
%50 = extractelement <1 x float> %49, i32 0
%51 = insertelement <1 x float> undef, float %45, i32 0
%52 = shufflevector <1 x float> %51, <1 x float> %51, <4 x
i32> <i32 0, i32 undef, i32 undef, i32 undef>
%53 = shufflevector <4 x float> %28, <4 x float> %52, <4 x
i32> <i32 0, i32 1, i32 4, i32 3>
%54 = add i32 %29, 1
%55 = insertelement <1 x i32> undef, i32 %54, i32 0
%56 = insertelement <1 x i32> undef, i32 %29, i32 0
%57 = shufflevector <1 x i32> %56, <1 x i32> %55, <1 x i32>
<i32 1>
%58 = extractelement <1 x i32> %57, i32 0
br label %25
}
*** IR Dump Before Remove unreachable blocks from the CFG ***
define void @main() {
call void @llvm.AMDGPU.reserve.reg(i32 0)
call void @llvm.AMDGPU.reserve.reg(i32 1)
call void @llvm.AMDGPU.reserve.reg(i32 2)
call void @llvm.AMDGPU.reserve.reg(i32 3)
%1 = call float @llvm.AMDGPU.load.const(i32 0)
%2 = bitcast float %1 to i32
%3 = call float @llvm.AMDGPU.load.const(i32 4)
%4 = insertelement <4 x float> undef, float %3, i32 0
%5 = call float @llvm.AMDGPU.load.const(i32 5)
%6 = insertelement <4 x float> %4, float %5, i32 1
%7 = call float @llvm.AMDGPU.load.const(i32 6)
%8 = insertelement <4 x float> %6, float %7, i32 2
%9 = call float @llvm.AMDGPU.load.const(i32 7)
%10 = insertelement <4 x float> %8, float %9, i32 3
%11 = call float @llvm.R600.load.input(i32 4)
%12 = insertelement <4 x float> undef, float %11, i32 0
%13 = call float @llvm.R600.load.input(i32 5)
%14 = insertelement <4 x float> %12, float %13, i32 1
%15 = call float @llvm.R600.load.input(i32 6)
%16 = insertelement <4 x float> %14, float %15, i32 2
%17 = call float @llvm.R600.load.input(i32 7)
%18 = insertelement <4 x float> %16, float %17, i32 3
%19 = shufflevector <4 x float> %10, <4 x float> %10, <1 x
i32> <i32 1>
%20 = extractelement <1 x float> %19, i32 0
%21 = insertelement <1 x float> undef, float %20, i32 0
%22 = shufflevector <1 x float> undef, <1 x float> %21, <1 x
i32> <i32 1>
%23 = extractelement <1 x float> %22, i32 0
%24 = shufflevector <4 x float> undef, <4 x float> %10, <4 x
i32> <i32 4, i32 5, i32 6, i32 7>
br label %25
; <label>:25 ; preds = %41, %0
%26 = phi float [ %45, %41 ], [ undef, %0 ]
%27 = phi float [ %50, %41 ], [ %23, %0 ]
%28 = phi <4 x float> [ %53, %41 ], [ %24, %0 ]
%29 = phi i32 [ %58, %41 ], [ 0, %0 ]
%30 = icmp sge i32 %29, %2
br i1 %30, label %31, label %41
; <label>:31 ; preds = %25
%32 = shufflevector <4 x float> undef, <4 x float> %18, <4 x
i32> <i32 4, i32 5, i32 6, i32 7>
%33 = extractelement <4 x float> %28, i32 0
call void @llvm.AMDGPU.store.output(float %33, i32 8)
%34 = extractelement <4 x float> %28, i32 1
call void @llvm.AMDGPU.store.output(float %34, i32 9)
%35 = extractelement <4 x float> %28, i32 2
call void @llvm.AMDGPU.store.output(float %35, i32 10)
%36 = extractelement <4 x float> %28, i32 3
call void @llvm.AMDGPU.store.output(float %36, i32 11)
%37 = extractelement <4 x float> %32, i32 0
call void @llvm.AMDGPU.store.output(float %37, i32 4)
%38 = extractelement <4 x float> %32, i32 1
call void @llvm.AMDGPU.store.output(float %38, i32 5)
%39 = extractelement <4 x float> %32, i32 2
call void @llvm.AMDGPU.store.output(float %39, i32 6)
%40 = extractelement <4 x float> %32, i32 3
call void @llvm.AMDGPU.store.output(float %40, i32 7)
ret void
; <label>:41 ; preds = %25
%42 = insertelement <1 x float> undef, float %27, i32 0
%43 = insertelement <1 x float> undef, float %26, i32 0
%44 = shufflevector <1 x float> %43, <1 x float> %42, <1 x
i32> <i32 1>
%45 = extractelement <1 x float> %44, i32 0
%46 = shufflevector <4 x float> %28, <4 x float> %28, <1 x
i32> <i32 2>
%47 = extractelement <1 x float> %46, i32 0
%48 = insertelement <1 x float> undef, float %47, i32 0
%49 = shufflevector <1 x float> %42, <1 x float> %48, <1 x
i32> <i32 1>
%50 = extractelement <1 x float> %49, i32 0
%51 = insertelement <1 x float> undef, float %45, i32 0
%52 = shufflevector <1 x float> %51, <1 x float> %51, <4 x
i32> <i32 0, i32 undef, i32 undef, i32 undef>
%53 = shufflevector <4 x float> %28, <4 x float> %52, <4 x
i32> <i32 0, i32 1, i32 4, i32 3>
%54 = add i32 %29, 1
%55 = insertelement <1 x i32> undef, i32 %54, i32 0
%56 = insertelement <1 x i32> undef, i32 %29, i32 0
%57 = shufflevector <1 x i32> %56, <1 x i32> %55, <1 x i32>
<i32 1>
%58 = extractelement <1 x i32> %57, i32 0
br label %25
}
*** IR Dump Before Optimize for code generation ***
define void @main() {
call void @llvm.AMDGPU.reserve.reg(i32 0)
call void @llvm.AMDGPU.reserve.reg(i32 1)
call void @llvm.AMDGPU.reserve.reg(i32 2)
call void @llvm.AMDGPU.reserve.reg(i32 3)
%1 = call float @llvm.AMDGPU.load.const(i32 0)
%2 = bitcast float %1 to i32
%3 = call float @llvm.AMDGPU.load.const(i32 4)
%4 = insertelement <4 x float> undef, float %3, i32 0
%5 = call float @llvm.AMDGPU.load.const(i32 5)
%6 = insertelement <4 x float> %4, float %5, i32 1
%7 = call float @llvm.AMDGPU.load.const(i32 6)
%8 = insertelement <4 x float> %6, float %7, i32 2
%9 = call float @llvm.AMDGPU.load.const(i32 7)
%10 = insertelement <4 x float> %8, float %9, i32 3
%11 = call float @llvm.R600.load.input(i32 4)
%12 = insertelement <4 x float> undef, float %11, i32 0
%13 = call float @llvm.R600.load.input(i32 5)
%14 = insertelement <4 x float> %12, float %13, i32 1
%15 = call float @llvm.R600.load.input(i32 6)
%16 = insertelement <4 x float> %14, float %15, i32 2
%17 = call float @llvm.R600.load.input(i32 7)
%18 = insertelement <4 x float> %16, float %17, i32 3
%19 = shufflevector <4 x float> %10, <4 x float> %10, <1 x
i32> <i32 1>
%20 = extractelement <1 x float> %19, i32 0
%21 = insertelement <1 x float> undef, float %20, i32 0
%22 = shufflevector <1 x float> undef, <1 x float> %21, <1 x
i32> <i32 1>
%23 = extractelement <1 x float> %22, i32 0
%24 = shufflevector <4 x float> undef, <4 x float> %10, <4 x
i32> <i32 4, i32 5, i32 6, i32 7>
br label %25
; <label>:25 ; preds = %41, %0
%26 = phi float [ %45, %41 ], [ undef, %0 ]
%27 = phi float [ %50, %41 ], [ %23, %0 ]
%28 = phi <4 x float> [ %53, %41 ], [ %24, %0 ]
%29 = phi i32 [ %58, %41 ], [ 0, %0 ]
%30 = icmp sge i32 %29, %2
br i1 %30, label %31, label %41
; <label>:31 ; preds = %25
%32 = shufflevector <4 x float> undef, <4 x float> %18, <4 x
i32> <i32 4, i32 5, i32 6, i32 7>
%33 = extractelement <4 x float> %28, i32 0
call void @llvm.AMDGPU.store.output(float %33, i32 8)
%34 = extractelement <4 x float> %28, i32 1
call void @llvm.AMDGPU.store.output(float %34, i32 9)
%35 = extractelement <4 x float> %28, i32 2
call void @llvm.AMDGPU.store.output(float %35, i32 10)
%36 = extractelement <4 x float> %28, i32 3
call void @llvm.AMDGPU.store.output(float %36, i32 11)
%37 = extractelement <4 x float> %32, i32 0
call void @llvm.AMDGPU.store.output(float %37, i32 4)
%38 = extractelement <4 x float> %32, i32 1
call void @llvm.AMDGPU.store.output(float %38, i32 5)
%39 = extractelement <4 x float> %32, i32 2
call void @llvm.AMDGPU.store.output(float %39, i32 6)
%40 = extractelement <4 x float> %32, i32 3
call void @llvm.AMDGPU.store.output(float %40, i32 7)
ret void
; <label>:41 ; preds = %25
%42 = insertelement <1 x float> undef, float %27, i32 0
%43 = insertelement <1 x float> undef, float %26, i32 0
%44 = shufflevector <1 x float> %43, <1 x float> %42, <1 x
i32> <i32 1>
%45 = extractelement <1 x float> %44, i32 0
%46 = shufflevector <4 x float> %28, <4 x float> %28, <1 x
i32> <i32 2>
%47 = extractelement <1 x float> %46, i32 0
%48 = insertelement <1 x float> undef, float %47, i32 0
%49 = shufflevector <1 x float> %42, <1 x float> %48, <1 x
i32> <i32 1>
%50 = extractelement <1 x float> %49, i32 0
%51 = insertelement <1 x float> undef, float %45, i32 0
%52 = shufflevector <1 x float> %51, <1 x float> %51, <4 x
i32> <i32 0, i32 undef, i32 undef, i32 undef>
%53 = shufflevector <4 x float> %28, <4 x float> %52, <4 x
i32> <i32 0, i32 1, i32 4, i32 3>
%54 = add i32 %29, 1
%55 = insertelement <1 x i32> undef, i32 %54, i32 0
%56 = insertelement <1 x i32> undef, i32 %29, i32 0
%57 = shufflevector <1 x i32> %56, <1 x i32> %55, <1 x i32>
<i32 1>
%58 = extractelement <1 x i32> %57, i32 0
br label %25
}
*** IR Dump Before Insert stack protectors ***
define void @main() {
call void @llvm.AMDGPU.reserve.reg(i32 0)
call void @llvm.AMDGPU.reserve.reg(i32 1)
call void @llvm.AMDGPU.reserve.reg(i32 2)
call void @llvm.AMDGPU.reserve.reg(i32 3)
%1 = call float @llvm.AMDGPU.load.const(i32 0)
%2 = bitcast float %1 to i32
%3 = call float @llvm.AMDGPU.load.const(i32 4)
%4 = insertelement <4 x float> undef, float %3, i32 0
%5 = call float @llvm.AMDGPU.load.const(i32 5)
%6 = insertelement <4 x float> %4, float %5, i32 1
%7 = call float @llvm.AMDGPU.load.const(i32 6)
%8 = insertelement <4 x float> %6, float %7, i32 2
%9 = call float @llvm.AMDGPU.load.const(i32 7)
%10 = insertelement <4 x float> %8, float %9, i32 3
%11 = call float @llvm.R600.load.input(i32 4)
%12 = insertelement <4 x float> undef, float %11, i32 0
%13 = call float @llvm.R600.load.input(i32 5)
%14 = insertelement <4 x float> %12, float %13, i32 1
%15 = call float @llvm.R600.load.input(i32 6)
%16 = insertelement <4 x float> %14, float %15, i32 2
%17 = call float @llvm.R600.load.input(i32 7)
%18 = insertelement <4 x float> %16, float %17, i32 3
%19 = shufflevector <4 x float> %10, <4 x float> %10, <1 x
i32> <i32 1>
%20 = extractelement <1 x float> %19, i32 0
%21 = insertelement <1 x float> undef, float %20, i32 0
%22 = shufflevector <1 x float> undef, <1 x float> %21, <1 x
i32> <i32 1>
%23 = extractelement <1 x float> %22, i32 0
%24 = shufflevector <4 x float> undef, <4 x float> %10, <4 x
i32> <i32 4, i32 5, i32 6, i32 7>
br label %25
; <label>:25 ; preds = %41, %0
%26 = phi float [ %45, %41 ], [ undef, %0 ]
%27 = phi float [ %50, %41 ], [ %23, %0 ]
%28 = phi <4 x float> [ %53, %41 ], [ %24, %0 ]
%29 = phi i32 [ %58, %41 ], [ 0, %0 ]
%30 = icmp sge i32 %29, %2
br i1 %30, label %31, label %41
; <label>:31 ; preds = %25
%32 = shufflevector <4 x float> undef, <4 x float> %18, <4 x
i32> <i32 4, i32 5, i32 6, i32 7>
%33 = extractelement <4 x float> %28, i32 0
call void @llvm.AMDGPU.store.output(float %33, i32 8)
%34 = extractelement <4 x float> %28, i32 1
call void @llvm.AMDGPU.store.output(float %34, i32 9)
%35 = extractelement <4 x float> %28, i32 2
call void @llvm.AMDGPU.store.output(float %35, i32 10)
%36 = extractelement <4 x float> %28, i32 3
call void @llvm.AMDGPU.store.output(float %36, i32 11)
%37 = extractelement <4 x float> %32, i32 0
call void @llvm.AMDGPU.store.output(float %37, i32 4)
%38 = extractelement <4 x float> %32, i32 1
call void @llvm.AMDGPU.store.output(float %38, i32 5)
%39 = extractelement <4 x float> %32, i32 2
call void @llvm.AMDGPU.store.output(float %39, i32 6)
%40 = extractelement <4 x float> %32, i32 3
call void @llvm.AMDGPU.store.output(float %40, i32 7)
ret void
; <label>:41 ; preds = %25
%42 = insertelement <1 x float> undef, float %27, i32 0
%43 = insertelement <1 x float> undef, float %26, i32 0
%44 = shufflevector <1 x float> %43, <1 x float> %42, <1 x
i32> <i32 1>
%45 = extractelement <1 x float> %44, i32 0
%46 = shufflevector <4 x float> %28, <4 x float> %28, <1 x
i32> <i32 2>
%47 = extractelement <1 x float> %46, i32 0
%48 = insertelement <1 x float> undef, float %47, i32 0
%49 = shufflevector <1 x float> %42, <1 x float> %48, <1 x
i32> <i32 1>
%50 = extractelement <1 x float> %49, i32 0
%51 = insertelement <1 x float> undef, float %45, i32 0
%52 = shufflevector <1 x float> %51, <1 x float> %51, <4 x
i32> <i32 0, i32 undef, i32 undef, i32 undef>
%53 = shufflevector <4 x float> %28, <4 x float> %52, <4 x
i32> <i32 0, i32 1, i32 4, i32 3>
%54 = add i32 %29, 1
%55 = insertelement <1 x i32> undef, i32 %54, i32 0
%56 = insertelement <1 x i32> undef, i32 %29, i32 0
%57 = shufflevector <1 x i32> %56, <1 x i32> %55, <1 x i32>
<i32 1>
%58 = extractelement <1 x i32> %57, i32 0
br label %25
}
*** IR Dump Before Preliminary module verification ***
define void @main() {
call void @llvm.AMDGPU.reserve.reg(i32 0)
call void @llvm.AMDGPU.reserve.reg(i32 1)
call void @llvm.AMDGPU.reserve.reg(i32 2)
call void @llvm.AMDGPU.reserve.reg(i32 3)
%1 = call float @llvm.AMDGPU.load.const(i32 0)
%2 = bitcast float %1 to i32
%3 = call float @llvm.AMDGPU.load.const(i32 4)
%4 = insertelement <4 x float> undef, float %3, i32 0
%5 = call float @llvm.AMDGPU.load.const(i32 5)
%6 = insertelement <4 x float> %4, float %5, i32 1
%7 = call float @llvm.AMDGPU.load.const(i32 6)
%8 = insertelement <4 x float> %6, float %7, i32 2
%9 = call float @llvm.AMDGPU.load.const(i32 7)
%10 = insertelement <4 x float> %8, float %9, i32 3
%11 = call float @llvm.R600.load.input(i32 4)
%12 = insertelement <4 x float> undef, float %11, i32 0
%13 = call float @llvm.R600.load.input(i32 5)
%14 = insertelement <4 x float> %12, float %13, i32 1
%15 = call float @llvm.R600.load.input(i32 6)
%16 = insertelement <4 x float> %14, float %15, i32 2
%17 = call float @llvm.R600.load.input(i32 7)
%18 = insertelement <4 x float> %16, float %17, i32 3
%19 = shufflevector <4 x float> %10, <4 x float> %10, <1 x
i32> <i32 1>
%20 = extractelement <1 x float> %19, i32 0
%21 = insertelement <1 x float> undef, float %20, i32 0
%22 = shufflevector <1 x float> undef, <1 x float> %21, <1 x
i32> <i32 1>
%23 = extractelement <1 x float> %22, i32 0
%24 = shufflevector <4 x float> undef, <4 x float> %10, <4 x
i32> <i32 4, i32 5, i32 6, i32 7>
br label %25
; <label>:25 ; preds = %41, %0
%26 = phi float [ %45, %41 ], [ undef, %0 ]
%27 = phi float [ %50, %41 ], [ %23, %0 ]
%28 = phi <4 x float> [ %53, %41 ], [ %24, %0 ]
%29 = phi i32 [ %58, %41 ], [ 0, %0 ]
%30 = icmp sge i32 %29, %2
br i1 %30, label %31, label %41
; <label>:31 ; preds = %25
%32 = shufflevector <4 x float> undef, <4 x float> %18, <4 x
i32> <i32 4, i32 5, i32 6, i32 7>
%33 = extractelement <4 x float> %28, i32 0
call void @llvm.AMDGPU.store.output(float %33, i32 8)
%34 = extractelement <4 x float> %28, i32 1
call void @llvm.AMDGPU.store.output(float %34, i32 9)
%35 = extractelement <4 x float> %28, i32 2
call void @llvm.AMDGPU.store.output(float %35, i32 10)
%36 = extractelement <4 x float> %28, i32 3
call void @llvm.AMDGPU.store.output(float %36, i32 11)
%37 = extractelement <4 x float> %32, i32 0
call void @llvm.AMDGPU.store.output(float %37, i32 4)
%38 = extractelement <4 x float> %32, i32 1
call void @llvm.AMDGPU.store.output(float %38, i32 5)
%39 = extractelement <4 x float> %32, i32 2
call void @llvm.AMDGPU.store.output(float %39, i32 6)
%40 = extractelement <4 x float> %32, i32 3
call void @llvm.AMDGPU.store.output(float %40, i32 7)
ret void
; <label>:41 ; preds = %25
%42 = insertelement <1 x float> undef, float %27, i32 0
%43 = insertelement <1 x float> undef, float %26, i32 0
%44 = shufflevector <1 x float> %43, <1 x float> %42, <1 x
i32> <i32 1>
%45 = extractelement <1 x float> %44, i32 0
%46 = shufflevector <4 x float> %28, <4 x float> %28, <1 x
i32> <i32 2>
%47 = extractelement <1 x float> %46, i32 0
%48 = insertelement <1 x float> undef, float %47, i32 0
%49 = shufflevector <1 x float> %42, <1 x float> %48, <1 x
i32> <i32 1>
%50 = extractelement <1 x float> %49, i32 0
%51 = insertelement <1 x float> undef, float %45, i32 0
%52 = shufflevector <1 x float> %51, <1 x float> %51, <4 x
i32> <i32 0, i32 undef, i32 undef, i32 undef>
%53 = shufflevector <4 x float> %28, <4 x float> %52, <4 x
i32> <i32 0, i32 1, i32 4, i32 3>
%54 = add i32 %29, 1
%55 = insertelement <1 x i32> undef, i32 %54, i32 0
%56 = insertelement <1 x i32> undef, i32 %29, i32 0
%57 = shufflevector <1 x i32> %56, <1 x i32> %55, <1 x i32>
<i32 1>
%58 = extractelement <1 x i32> %57, i32 0
br label %25
}
*** IR Dump Before Module Verifier ***
define void @main() {
call void @llvm.AMDGPU.reserve.reg(i32 0)
call void @llvm.AMDGPU.reserve.reg(i32 1)
call void @llvm.AMDGPU.reserve.reg(i32 2)
call void @llvm.AMDGPU.reserve.reg(i32 3)
%1 = call float @llvm.AMDGPU.load.const(i32 0)
%2 = bitcast float %1 to i32
%3 = call float @llvm.AMDGPU.load.const(i32 4)
%4 = insertelement <4 x float> undef, float %3, i32 0
%5 = call float @llvm.AMDGPU.load.const(i32 5)
%6 = insertelement <4 x float> %4, float %5, i32 1
%7 = call float @llvm.AMDGPU.load.const(i32 6)
%8 = insertelement <4 x float> %6, float %7, i32 2
%9 = call float @llvm.AMDGPU.load.const(i32 7)
%10 = insertelement <4 x float> %8, float %9, i32 3
%11 = call float @llvm.R600.load.input(i32 4)
%12 = insertelement <4 x float> undef, float %11, i32 0
%13 = call float @llvm.R600.load.input(i32 5)
%14 = insertelement <4 x float> %12, float %13, i32 1
%15 = call float @llvm.R600.load.input(i32 6)
%16 = insertelement <4 x float> %14, float %15, i32 2
%17 = call float @llvm.R600.load.input(i32 7)
%18 = insertelement <4 x float> %16, float %17, i32 3
%19 = shufflevector <4 x float> %10, <4 x float> %10, <1 x
i32> <i32 1>
%20 = extractelement <1 x float> %19, i32 0
%21 = insertelement <1 x float> undef, float %20, i32 0
%22 = shufflevector <1 x float> undef, <1 x float> %21, <1 x
i32> <i32 1>
%23 = extractelement <1 x float> %22, i32 0
%24 = shufflevector <4 x float> undef, <4 x float> %10, <4 x
i32> <i32 4, i32 5, i32 6, i32 7>
br label %25
; <label>:25 ; preds = %41, %0
%26 = phi float [ %45, %41 ], [ undef, %0 ]
%27 = phi float [ %50, %41 ], [ %23, %0 ]
%28 = phi <4 x float> [ %53, %41 ], [ %24, %0 ]
%29 = phi i32 [ %58, %41 ], [ 0, %0 ]
%30 = icmp sge i32 %29, %2
br i1 %30, label %31, label %41
; <label>:31 ; preds = %25
%32 = shufflevector <4 x float> undef, <4 x float> %18, <4 x
i32> <i32 4, i32 5, i32 6, i32 7>
%33 = extractelement <4 x float> %28, i32 0
call void @llvm.AMDGPU.store.output(float %33, i32 8)
%34 = extractelement <4 x float> %28, i32 1
call void @llvm.AMDGPU.store.output(float %34, i32 9)
%35 = extractelement <4 x float> %28, i32 2
call void @llvm.AMDGPU.store.output(float %35, i32 10)
%36 = extractelement <4 x float> %28, i32 3
call void @llvm.AMDGPU.store.output(float %36, i32 11)
%37 = extractelement <4 x float> %32, i32 0
call void @llvm.AMDGPU.store.output(float %37, i32 4)
%38 = extractelement <4 x float> %32, i32 1
call void @llvm.AMDGPU.store.output(float %38, i32 5)
%39 = extractelement <4 x float> %32, i32 2
call void @llvm.AMDGPU.store.output(float %39, i32 6)
%40 = extractelement <4 x float> %32, i32 3
call void @llvm.AMDGPU.store.output(float %40, i32 7)
ret void
; <label>:41 ; preds = %25
%42 = insertelement <1 x float> undef, float %27, i32 0
%43 = insertelement <1 x float> undef, float %26, i32 0
%44 = shufflevector <1 x float> %43, <1 x float> %42, <1 x
i32> <i32 1>
%45 = extractelement <1 x float> %44, i32 0
%46 = shufflevector <4 x float> %28, <4 x float> %28, <1 x
i32> <i32 2>
%47 = extractelement <1 x float> %46, i32 0
%48 = insertelement <1 x float> undef, float %47, i32 0
%49 = shufflevector <1 x float> %42, <1 x float> %48, <1 x
i32> <i32 1>
%50 = extractelement <1 x float> %49, i32 0
%51 = insertelement <1 x float> undef, float %45, i32 0
%52 = shufflevector <1 x float> %51, <1 x float> %51, <4 x
i32> <i32 0, i32 undef, i32 undef, i32 undef>
%53 = shufflevector <4 x float> %28, <4 x float> %52, <4 x
i32> <i32 0, i32 1, i32 4, i32 3>
%54 = add i32 %29, 1
%55 = insertelement <1 x i32> undef, i32 %54, i32 0
%56 = insertelement <1 x i32> undef, i32 %29, i32 0
%57 = shufflevector <1 x i32> %56, <1 x i32> %55, <1 x i32>
<i32 1>
%58 = extractelement <1 x i32> %57, i32 0
br label %25
}
# *** IR Dump Before Expand ISel Pseudo-instructions ***:
# Machine code for function main: SSA
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
BB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
%vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17
%vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16
%vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15
%vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14
%vreg18<def> = R600_LOAD_CONST 4; R600_Reg32:%vreg18
%vreg20<def> = IMPLICIT_DEF; R600_Reg128:%vreg20
%vreg19<def,tied1> = INSERT_SUBREG %vreg20<tied0>, %vreg14, sel_x;
R600_Reg128:%vreg19,%vreg20 R600_TReg32:%vreg14
%vreg2<def> = R600_LOAD_CONST 5; R600_Reg32:%vreg2
%vreg22<def> = IMPLICIT_DEF; R600_Reg128:%vreg22
%vreg21<def,tied1> = INSERT_SUBREG %vreg22<tied0>,
%vreg18<kill>, sel_x; R600_Reg128:%vreg21,%vreg22 R600_Reg32:%vreg18
RESERVE_REG 0
%vreg23<def,tied1> = INSERT_SUBREG %vreg19<tied0>, %vreg15, sel_y;
R600_Reg128:%vreg23,%vreg19 R600_TReg32:%vreg15
%vreg24<def,tied1> = INSERT_SUBREG %vreg21<tied0>, %vreg2, sel_y;
R600_Reg128:%vreg24,%vreg21 R600_Reg32:%vreg2
%vreg25<def> = R600_LOAD_CONST 6; R600_Reg32:%vreg25
%vreg26<def,tied1> = INSERT_SUBREG %vreg23<tied0>, %vreg16, sel_z;
R600_Reg128:%vreg26,%vreg23 R600_TReg32:%vreg16
RESERVE_REG 1
%vreg27<def,tied1> = INSERT_SUBREG %vreg24<tied0>,
%vreg25<kill>, sel_z; R600_Reg128:%vreg27,%vreg24 R600_Reg32:%vreg25
%vreg28<def> = R600_LOAD_CONST 7; R600_Reg32:%vreg28
RESERVE_REG 2
%vreg3<def,tied1> = INSERT_SUBREG %vreg27<tied0>,
%vreg28<kill>, sel_w; R600_Reg128:%vreg3,%vreg27 R600_Reg32:%vreg28
%vreg1<def,tied1> = INSERT_SUBREG %vreg26<tied0>, %vreg17, sel_w;
R600_Reg128:%vreg1,%vreg26 R600_TReg32:%vreg17
%vreg13<def> = MOV_IMM_I32 0; R600_Reg32:%vreg13
%vreg0<def> = R600_LOAD_CONST 0; R600_Reg32:%vreg0
%vreg12<def> = IMPLICIT_DEF; R600_Reg32:%vreg12
RESERVE_REG 3
Successors according to CFG: BB#1
BB#1: derived from LLVM BB %25
Predecessors according to CFG: BB#0 BB#3
%vreg4<def> = PHI %vreg12, <BB#0>, %vreg8, <BB#3>;
R600_Reg32:%vreg4,%vreg12,%vreg8
%vreg5<def> = PHI %vreg2, <BB#0>, %vreg9, <BB#3>;
R600_Reg32:%vreg5,%vreg2,%vreg9
%vreg6<def> = PHI %vreg3, <BB#0>, %vreg10, <BB#3>;
R600_Reg128:%vreg6,%vreg3,%vreg10
%vreg7<def> = PHI %vreg13, <BB#0>, %vreg11, <BB#3>;
R600_Reg32:%vreg7,%vreg13,%vreg11
%vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0,
0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7
%vreg30<def> = COPY %vreg29; GPRI32:%vreg30 R600_Reg32:%vreg29
BRANCH_COND_i32 <BB#3>, %vreg30<kill>; GPRI32:%vreg30
BRANCH <BB#2>
Successors according to CFG: BB#2(4) BB#3(124)
BB#2: derived from LLVM BB %31
Predecessors according to CFG: BB#1
%vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6
%T2_X<def> = COPY %vreg39; R600_Reg32:%vreg39
%vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6
%T2_Y<def> = COPY %vreg40; R600_Reg32:%vreg40
%vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6
%T2_Z<def> = COPY %vreg41; R600_Reg32:%vreg41
%vreg42<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg42 R600_Reg128:%vreg6
%T2_W<def> = COPY %vreg42; R600_Reg32:%vreg42
%vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1
%T1_X<def> = COPY %vreg43; R600_Reg32:%vreg43
%vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1
%T1_Y<def> = COPY %vreg44; R600_Reg32:%vreg44
%vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1
%T1_Z<def> = COPY %vreg45; R600_Reg32:%vreg45
%vreg46<def> = COPY %vreg1:sel_w; R600_Reg32:%vreg46 R600_Reg128:%vreg1
%T1_W<def> = COPY %vreg46; R600_Reg32:%vreg46
RETURN
BB#3: derived from LLVM BB %41
Predecessors according to CFG: BB#1
%vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6
%vreg33<def> = IMPLICIT_DEF; R600_Reg128:%vreg33
%vreg32<def,tied1> = INSERT_SUBREG %vreg33<tied0>,
%vreg31<kill>, sel_x; R600_Reg128:%vreg32,%vreg33 R600_Reg32:%vreg31
%vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6
%vreg35<def,tied1> = INSERT_SUBREG %vreg32<tied0>,
%vreg34<kill>, sel_y; R600_Reg128:%vreg35,%vreg32 R600_Reg32:%vreg34
%vreg36<def,tied1> = INSERT_SUBREG %vreg35<tied0>, %vreg5, sel_z;
R600_Reg128:%vreg36,%vreg35 R600_Reg32:%vreg5
%vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6
%vreg10<def,tied1> = INSERT_SUBREG %vreg36<tied0>,
%vreg37<kill>, sel_w; R600_Reg128:%vreg10,%vreg36 R600_Reg32:%vreg37
%vreg9<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg6
%vreg38<def> = MOV_IMM_I32 1; R600_Reg32:%vreg38
%vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7, 0, 0, 0,
%vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0;
R600_Reg32:%vreg11,%vreg7,%vreg38
%vreg8<def> = COPY %vreg5; R600_Reg32:%vreg8,%vreg5
BRANCH <BB#1>
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Tail Duplication ***:
# Machine code for function main: SSA
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
BB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
%vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17
%vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16
%vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15
%vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14
%vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18
%vreg20<def> = IMPLICIT_DEF; R600_Reg128:%vreg20
%vreg19<def,tied1> = INSERT_SUBREG %vreg20<tied0>, %vreg14, sel_x;
R600_Reg128:%vreg19,%vreg20 R600_TReg32:%vreg14
%vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2
%vreg22<def> = IMPLICIT_DEF; R600_Reg128:%vreg22
%vreg21<def,tied1> = INSERT_SUBREG %vreg22<tied0>,
%vreg18<kill>, sel_x; R600_Reg128:%vreg21,%vreg22 R600_Reg32:%vreg18
%vreg23<def,tied1> = INSERT_SUBREG %vreg19<tied0>, %vreg15, sel_y;
R600_Reg128:%vreg23,%vreg19 R600_TReg32:%vreg15
%vreg24<def,tied1> = INSERT_SUBREG %vreg21<tied0>, %vreg2, sel_y;
R600_Reg128:%vreg24,%vreg21 R600_Reg32:%vreg2
%vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25
%vreg26<def,tied1> = INSERT_SUBREG %vreg23<tied0>, %vreg16, sel_z;
R600_Reg128:%vreg26,%vreg23 R600_TReg32:%vreg16
%vreg27<def,tied1> = INSERT_SUBREG %vreg24<tied0>,
%vreg25<kill>, sel_z; R600_Reg128:%vreg27,%vreg24 R600_Reg32:%vreg25
%vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28
%vreg3<def,tied1> = INSERT_SUBREG %vreg27<tied0>,
%vreg28<kill>, sel_w; R600_Reg128:%vreg3,%vreg27 R600_Reg32:%vreg28
%vreg1<def,tied1> = INSERT_SUBREG %vreg26<tied0>, %vreg17, sel_w;
R600_Reg128:%vreg1,%vreg26 R600_TReg32:%vreg17
%vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13
%vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0
%vreg12<def> = IMPLICIT_DEF; R600_Reg32:%vreg12
Successors according to CFG: BB#1
BB#1: derived from LLVM BB %25
Predecessors according to CFG: BB#0 BB#3
%vreg4<def> = PHI %vreg12, <BB#0>, %vreg8, <BB#3>;
R600_Reg32:%vreg4,%vreg12,%vreg8
%vreg5<def> = PHI %vreg2, <BB#0>, %vreg9, <BB#3>;
R600_Reg32:%vreg5,%vreg2,%vreg9
%vreg6<def> = PHI %vreg3, <BB#0>, %vreg10, <BB#3>;
R600_Reg128:%vreg6,%vreg3,%vreg10
%vreg7<def> = PHI %vreg13, <BB#0>, %vreg11, <BB#3>;
R600_Reg32:%vreg7,%vreg13,%vreg11
%vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0,
0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7
%vreg30<def> = COPY %vreg29; GPRI32:%vreg30 R600_Reg32:%vreg29
%PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16; GPRI32:%vreg30
JUMP <BB#3>, pred:%PREDICATE_BIT<kill>
JUMP <BB#2>, pred:%noreg
Successors according to CFG: BB#2(4) BB#3(124)
BB#2: derived from LLVM BB %31
Predecessors according to CFG: BB#1
%vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6
%T2_X<def> = COPY %vreg39; R600_Reg32:%vreg39
%vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6
%T2_Y<def> = COPY %vreg40; R600_Reg32:%vreg40
%vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6
%T2_Z<def> = COPY %vreg41; R600_Reg32:%vreg41
%vreg42<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg42 R600_Reg128:%vreg6
%T2_W<def> = COPY %vreg42; R600_Reg32:%vreg42
%vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1
%T1_X<def> = COPY %vreg43; R600_Reg32:%vreg43
%vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1
%T1_Y<def> = COPY %vreg44; R600_Reg32:%vreg44
%vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1
%T1_Z<def> = COPY %vreg45; R600_Reg32:%vreg45
%vreg46<def> = COPY %vreg1:sel_w; R600_Reg32:%vreg46 R600_Reg128:%vreg1
%T1_W<def> = COPY %vreg46; R600_Reg32:%vreg46
RETURN
BB#3: derived from LLVM BB %41
Predecessors according to CFG: BB#1
%vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6
%vreg33<def> = IMPLICIT_DEF; R600_Reg128:%vreg33
%vreg32<def,tied1> = INSERT_SUBREG %vreg33<tied0>,
%vreg31<kill>, sel_x; R600_Reg128:%vreg32,%vreg33 R600_Reg32:%vreg31
%vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6
%vreg35<def,tied1> = INSERT_SUBREG %vreg32<tied0>,
%vreg34<kill>, sel_y; R600_Reg128:%vreg35,%vreg32 R600_Reg32:%vreg34
%vreg36<def,tied1> = INSERT_SUBREG %vreg35<tied0>, %vreg5, sel_z;
R600_Reg128:%vreg36,%vreg35 R600_Reg32:%vreg5
%vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6
%vreg10<def,tied1> = INSERT_SUBREG %vreg36<tied0>,
%vreg37<kill>, sel_w; R600_Reg128:%vreg10,%vreg36 R600_Reg32:%vreg37
%vreg9<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg6
%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38
%vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7, 0, 0, 0,
%vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0;
R600_Reg32:%vreg11,%vreg7,%vreg38
%vreg8<def> = COPY %vreg5; R600_Reg32:%vreg8,%vreg5
JUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Optimize machine instruction PHIs ***:
# Machine code for function main: SSA
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
BB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
%vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17
%vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16
%vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15
%vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14
%vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18
%vreg20<def> = IMPLICIT_DEF; R600_Reg128:%vreg20
%vreg19<def,tied1> = INSERT_SUBREG %vreg20<tied0>, %vreg14, sel_x;
R600_Reg128:%vreg19,%vreg20 R600_TReg32:%vreg14
%vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2
%vreg22<def> = IMPLICIT_DEF; R600_Reg128:%vreg22
%vreg21<def,tied1> = INSERT_SUBREG %vreg22<tied0>,
%vreg18<kill>, sel_x; R600_Reg128:%vreg21,%vreg22 R600_Reg32:%vreg18
%vreg23<def,tied1> = INSERT_SUBREG %vreg19<tied0>, %vreg15, sel_y;
R600_Reg128:%vreg23,%vreg19 R600_TReg32:%vreg15
%vreg24<def,tied1> = INSERT_SUBREG %vreg21<tied0>, %vreg2, sel_y;
R600_Reg128:%vreg24,%vreg21 R600_Reg32:%vreg2
%vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25
%vreg26<def,tied1> = INSERT_SUBREG %vreg23<tied0>, %vreg16, sel_z;
R600_Reg128:%vreg26,%vreg23 R600_TReg32:%vreg16
%vreg27<def,tied1> = INSERT_SUBREG %vreg24<tied0>,
%vreg25<kill>, sel_z; R600_Reg128:%vreg27,%vreg24 R600_Reg32:%vreg25
%vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28
%vreg3<def,tied1> = INSERT_SUBREG %vreg27<tied0>,
%vreg28<kill>, sel_w; R600_Reg128:%vreg3,%vreg27 R600_Reg32:%vreg28
%vreg1<def,tied1> = INSERT_SUBREG %vreg26<tied0>, %vreg17, sel_w;
R600_Reg128:%vreg1,%vreg26 R600_TReg32:%vreg17
%vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13
%vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0
%vreg12<def> = IMPLICIT_DEF; R600_Reg32:%vreg12
Successors according to CFG: BB#1
BB#1: derived from LLVM BB %25
Predecessors according to CFG: BB#0 BB#3
%vreg4<def> = PHI %vreg12, <BB#0>, %vreg8, <BB#3>;
R600_Reg32:%vreg4,%vreg12,%vreg8
%vreg5<def> = PHI %vreg2, <BB#0>, %vreg9, <BB#3>;
R600_Reg32:%vreg5,%vreg2,%vreg9
%vreg6<def> = PHI %vreg3, <BB#0>, %vreg10, <BB#3>;
R600_Reg128:%vreg6,%vreg3,%vreg10
%vreg7<def> = PHI %vreg13, <BB#0>, %vreg11, <BB#3>;
R600_Reg32:%vreg7,%vreg13,%vreg11
%vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0,
0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7
%vreg30<def> = COPY %vreg29; GPRI32:%vreg30 R600_Reg32:%vreg29
%PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16; GPRI32:%vreg30
JUMP <BB#3>, pred:%PREDICATE_BIT<kill>
JUMP <BB#2>, pred:%noreg
Successors according to CFG: BB#2(4) BB#3(124)
BB#2: derived from LLVM BB %31
Predecessors according to CFG: BB#1
%vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6
%T2_X<def> = COPY %vreg39; R600_Reg32:%vreg39
%vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6
%T2_Y<def> = COPY %vreg40; R600_Reg32:%vreg40
%vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6
%T2_Z<def> = COPY %vreg41; R600_Reg32:%vreg41
%vreg42<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg42 R600_Reg128:%vreg6
%T2_W<def> = COPY %vreg42; R600_Reg32:%vreg42
%vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1
%T1_X<def> = COPY %vreg43; R600_Reg32:%vreg43
%vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1
%T1_Y<def> = COPY %vreg44; R600_Reg32:%vreg44
%vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1
%T1_Z<def> = COPY %vreg45; R600_Reg32:%vreg45
%vreg46<def> = COPY %vreg1:sel_w; R600_Reg32:%vreg46 R600_Reg128:%vreg1
%T1_W<def> = COPY %vreg46; R600_Reg32:%vreg46
RETURN
BB#3: derived from LLVM BB %41
Predecessors according to CFG: BB#1
%vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6
%vreg33<def> = IMPLICIT_DEF; R600_Reg128:%vreg33
%vreg32<def,tied1> = INSERT_SUBREG %vreg33<tied0>,
%vreg31<kill>, sel_x; R600_Reg128:%vreg32,%vreg33 R600_Reg32:%vreg31
%vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6
%vreg35<def,tied1> = INSERT_SUBREG %vreg32<tied0>,
%vreg34<kill>, sel_y; R600_Reg128:%vreg35,%vreg32 R600_Reg32:%vreg34
%vreg36<def,tied1> = INSERT_SUBREG %vreg35<tied0>, %vreg5, sel_z;
R600_Reg128:%vreg36,%vreg35 R600_Reg32:%vreg5
%vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6
%vreg10<def,tied1> = INSERT_SUBREG %vreg36<tied0>,
%vreg37<kill>, sel_w; R600_Reg128:%vreg10,%vreg36 R600_Reg32:%vreg37
%vreg9<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg6
%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38
%vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7, 0, 0, 0,
%vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0;
R600_Reg32:%vreg11,%vreg7,%vreg38
%vreg8<def> = COPY %vreg5; R600_Reg32:%vreg8,%vreg5
JUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Slot index numbering ***:
# Machine code for function main: SSA
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
BB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
%vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17
%vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16
%vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15
%vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14
%vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18
%vreg20<def> = IMPLICIT_DEF; R600_Reg128:%vreg20
%vreg19<def,tied1> = INSERT_SUBREG %vreg20<tied0>, %vreg14, sel_x;
R600_Reg128:%vreg19,%vreg20 R600_TReg32:%vreg14
%vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2
%vreg22<def> = IMPLICIT_DEF; R600_Reg128:%vreg22
%vreg21<def,tied1> = INSERT_SUBREG %vreg22<tied0>,
%vreg18<kill>, sel_x; R600_Reg128:%vreg21,%vreg22 R600_Reg32:%vreg18
%vreg23<def,tied1> = INSERT_SUBREG %vreg19<tied0>, %vreg15, sel_y;
R600_Reg128:%vreg23,%vreg19 R600_TReg32:%vreg15
%vreg24<def,tied1> = INSERT_SUBREG %vreg21<tied0>, %vreg2, sel_y;
R600_Reg128:%vreg24,%vreg21 R600_Reg32:%vreg2
%vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25
%vreg26<def,tied1> = INSERT_SUBREG %vreg23<tied0>, %vreg16, sel_z;
R600_Reg128:%vreg26,%vreg23 R600_TReg32:%vreg16
%vreg27<def,tied1> = INSERT_SUBREG %vreg24<tied0>,
%vreg25<kill>, sel_z; R600_Reg128:%vreg27,%vreg24 R600_Reg32:%vreg25
%vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28
%vreg3<def,tied1> = INSERT_SUBREG %vreg27<tied0>,
%vreg28<kill>, sel_w; R600_Reg128:%vreg3,%vreg27 R600_Reg32:%vreg28
%vreg1<def,tied1> = INSERT_SUBREG %vreg26<tied0>, %vreg17, sel_w;
R600_Reg128:%vreg1,%vreg26 R600_TReg32:%vreg17
%vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13
%vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0
%vreg12<def> = IMPLICIT_DEF; R600_Reg32:%vreg12
Successors according to CFG: BB#1
BB#1: derived from LLVM BB %25
Predecessors according to CFG: BB#0 BB#3
%vreg5<def> = PHI %vreg2, <BB#0>, %vreg9, <BB#3>;
R600_Reg32:%vreg5,%vreg2,%vreg9
%vreg6<def> = PHI %vreg3, <BB#0>, %vreg10, <BB#3>;
R600_Reg128:%vreg6,%vreg3,%vreg10
%vreg7<def> = PHI %vreg13, <BB#0>, %vreg11, <BB#3>;
R600_Reg32:%vreg7,%vreg13,%vreg11
%vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0,
0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7
%vreg30<def> = COPY %vreg29; GPRI32:%vreg30 R600_Reg32:%vreg29
%PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16; GPRI32:%vreg30
JUMP <BB#3>, pred:%PREDICATE_BIT<kill>
JUMP <BB#2>, pred:%noreg
Successors according to CFG: BB#2(4) BB#3(124)
BB#2: derived from LLVM BB %31
Predecessors according to CFG: BB#1
%vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6
%T2_X<def> = COPY %vreg39; R600_Reg32:%vreg39
%vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6
%T2_Y<def> = COPY %vreg40; R600_Reg32:%vreg40
%vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6
%T2_Z<def> = COPY %vreg41; R600_Reg32:%vreg41
%vreg42<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg42 R600_Reg128:%vreg6
%T2_W<def> = COPY %vreg42; R600_Reg32:%vreg42
%vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1
%T1_X<def> = COPY %vreg43; R600_Reg32:%vreg43
%vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1
%T1_Y<def> = COPY %vreg44; R600_Reg32:%vreg44
%vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1
%T1_Z<def> = COPY %vreg45; R600_Reg32:%vreg45
%vreg46<def> = COPY %vreg1:sel_w; R600_Reg32:%vreg46 R600_Reg128:%vreg1
%T1_W<def> = COPY %vreg46; R600_Reg32:%vreg46
RETURN
BB#3: derived from LLVM BB %41
Predecessors according to CFG: BB#1
%vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6
%vreg33<def> = IMPLICIT_DEF; R600_Reg128:%vreg33
%vreg32<def,tied1> = INSERT_SUBREG %vreg33<tied0>,
%vreg31<kill>, sel_x; R600_Reg128:%vreg32,%vreg33 R600_Reg32:%vreg31
%vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6
%vreg35<def,tied1> = INSERT_SUBREG %vreg32<tied0>,
%vreg34<kill>, sel_y; R600_Reg128:%vreg35,%vreg32 R600_Reg32:%vreg34
%vreg36<def,tied1> = INSERT_SUBREG %vreg35<tied0>, %vreg5, sel_z;
R600_Reg128:%vreg36,%vreg35 R600_Reg32:%vreg5
%vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6
%vreg10<def,tied1> = INSERT_SUBREG %vreg36<tied0>,
%vreg37<kill>, sel_w; R600_Reg128:%vreg10,%vreg36 R600_Reg32:%vreg37
%vreg9<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg6
%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38
%vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7, 0, 0, 0,
%vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0;
R600_Reg32:%vreg11,%vreg7,%vreg38
%vreg8<def> = COPY %vreg5; R600_Reg32:%vreg8,%vreg5
JUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Merge disjoint stack slots ***:
# Machine code for function main: SSA
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
0BBB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
16B%vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17
32B%vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16
48B%vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15
64B%vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14
80B%vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18
96B%vreg20<def> = IMPLICIT_DEF; R600_Reg128:%vreg20
112B%vreg19<def,tied1> = INSERT_SUBREG %vreg20<tied0>, %vreg14,
sel_x; R600_Reg128:%vreg19,%vreg20 R600_TReg32:%vreg14
128B%vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2
144B%vreg22<def> = IMPLICIT_DEF; R600_Reg128:%vreg22
160B%vreg21<def,tied1> = INSERT_SUBREG %vreg22<tied0>,
%vreg18<kill>, sel_x; R600_Reg128:%vreg21,%vreg22 R600_Reg32:%vreg18
176B%vreg23<def,tied1> = INSERT_SUBREG %vreg19<tied0>, %vreg15,
sel_y; R600_Reg128:%vreg23,%vreg19 R600_TReg32:%vreg15
192B%vreg24<def,tied1> = INSERT_SUBREG %vreg21<tied0>, %vreg2,
sel_y; R600_Reg128:%vreg24,%vreg21 R600_Reg32:%vreg2
208B%vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25
224B%vreg26<def,tied1> = INSERT_SUBREG %vreg23<tied0>, %vreg16,
sel_z; R600_Reg128:%vreg26,%vreg23 R600_TReg32:%vreg16
240B%vreg27<def,tied1> = INSERT_SUBREG %vreg24<tied0>,
%vreg25<kill>, sel_z; R600_Reg128:%vreg27,%vreg24 R600_Reg32:%vreg25
256B%vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28
272B%vreg3<def,tied1> = INSERT_SUBREG %vreg27<tied0>,
%vreg28<kill>, sel_w; R600_Reg128:%vreg3,%vreg27 R600_Reg32:%vreg28
288B%vreg1<def,tied1> = INSERT_SUBREG %vreg26<tied0>, %vreg17,
sel_w; R600_Reg128:%vreg1,%vreg26 R600_TReg32:%vreg17
304B%vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13
320B%vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0
336B%vreg12<def> = IMPLICIT_DEF; R600_Reg32:%vreg12
Successors according to CFG: BB#1
352BBB#1: derived from LLVM BB %25
Predecessors according to CFG: BB#0 BB#3
368B%vreg5<def> = PHI %vreg2, <BB#0>, %vreg9, <BB#3>;
R600_Reg32:%vreg5,%vreg2,%vreg9
384B%vreg6<def> = PHI %vreg3, <BB#0>, %vreg10, <BB#3>;
R600_Reg128:%vreg6,%vreg3,%vreg10
400B%vreg7<def> = PHI %vreg13, <BB#0>, %vreg11, <BB#3>;
R600_Reg32:%vreg7,%vreg13,%vreg11
416B%vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0,
0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7
432B%vreg30<def> = COPY %vreg29; GPRI32:%vreg30 R600_Reg32:%vreg29
448B%PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16;
GPRI32:%vreg30
464BJUMP <BB#3>, pred:%PREDICATE_BIT<kill>
480BJUMP <BB#2>, pred:%noreg
Successors according to CFG: BB#2(4) BB#3(124)
496BBB#2: derived from LLVM BB %31
Predecessors according to CFG: BB#1
512B%vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39
R600_Reg128:%vreg6
528B%T2_X<def> = COPY %vreg39; R600_Reg32:%vreg39
544B%vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40
R600_Reg128:%vreg6
560B%T2_Y<def> = COPY %vreg40; R600_Reg32:%vreg40
576B%vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41
R600_Reg128:%vreg6
592B%T2_Z<def> = COPY %vreg41; R600_Reg32:%vreg41
608B%vreg42<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg42
R600_Reg128:%vreg6
624B%T2_W<def> = COPY %vreg42; R600_Reg32:%vreg42
640B%vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43
R600_Reg128:%vreg1
656B%T1_X<def> = COPY %vreg43; R600_Reg32:%vreg43
672B%vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44
R600_Reg128:%vreg1
688B%T1_Y<def> = COPY %vreg44; R600_Reg32:%vreg44
704B%vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45
R600_Reg128:%vreg1
720B%T1_Z<def> = COPY %vreg45; R600_Reg32:%vreg45
736B%vreg46<def> = COPY %vreg1:sel_w; R600_Reg32:%vreg46
R600_Reg128:%vreg1
752B%T1_W<def> = COPY %vreg46; R600_Reg32:%vreg46
768BRETURN
784BBB#3: derived from LLVM BB %41
Predecessors according to CFG: BB#1
800B%vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31
R600_Reg128:%vreg6
816B%vreg33<def> = IMPLICIT_DEF; R600_Reg128:%vreg33
832B%vreg32<def,tied1> = INSERT_SUBREG %vreg33<tied0>,
%vreg31<kill>, sel_x; R600_Reg128:%vreg32,%vreg33 R600_Reg32:%vreg31
848B%vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34
R600_Reg128:%vreg6
864B%vreg35<def,tied1> = INSERT_SUBREG %vreg32<tied0>,
%vreg34<kill>, sel_y; R600_Reg128:%vreg35,%vreg32 R600_Reg32:%vreg34
880B%vreg36<def,tied1> = INSERT_SUBREG %vreg35<tied0>, %vreg5,
sel_z; R600_Reg128:%vreg36,%vreg35 R600_Reg32:%vreg5
896B%vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37
R600_Reg128:%vreg6
912B%vreg10<def,tied1> = INSERT_SUBREG %vreg36<tied0>,
%vreg37<kill>, sel_w; R600_Reg128:%vreg10,%vreg36 R600_Reg32:%vreg37
928B%vreg9<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg6
944B%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38
960B%vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7, 0, 0, 0,
%vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0;
R600_Reg32:%vreg11,%vreg7,%vreg38
976B%vreg8<def> = COPY %vreg5; R600_Reg32:%vreg8,%vreg5
992BJUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Local Stack Slot Allocation ***:
# Machine code for function main: SSA
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
BB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
%vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17
%vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16
%vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15
%vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14
%vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18
%vreg20<def> = IMPLICIT_DEF; R600_Reg128:%vreg20
%vreg19<def,tied1> = INSERT_SUBREG %vreg20<tied0>, %vreg14, sel_x;
R600_Reg128:%vreg19,%vreg20 R600_TReg32:%vreg14
%vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2
%vreg22<def> = IMPLICIT_DEF; R600_Reg128:%vreg22
%vreg21<def,tied1> = INSERT_SUBREG %vreg22<tied0>,
%vreg18<kill>, sel_x; R600_Reg128:%vreg21,%vreg22 R600_Reg32:%vreg18
%vreg23<def,tied1> = INSERT_SUBREG %vreg19<tied0>, %vreg15, sel_y;
R600_Reg128:%vreg23,%vreg19 R600_TReg32:%vreg15
%vreg24<def,tied1> = INSERT_SUBREG %vreg21<tied0>, %vreg2, sel_y;
R600_Reg128:%vreg24,%vreg21 R600_Reg32:%vreg2
%vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25
%vreg26<def,tied1> = INSERT_SUBREG %vreg23<tied0>, %vreg16, sel_z;
R600_Reg128:%vreg26,%vreg23 R600_TReg32:%vreg16
%vreg27<def,tied1> = INSERT_SUBREG %vreg24<tied0>,
%vreg25<kill>, sel_z; R600_Reg128:%vreg27,%vreg24 R600_Reg32:%vreg25
%vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28
%vreg3<def,tied1> = INSERT_SUBREG %vreg27<tied0>,
%vreg28<kill>, sel_w; R600_Reg128:%vreg3,%vreg27 R600_Reg32:%vreg28
%vreg1<def,tied1> = INSERT_SUBREG %vreg26<tied0>, %vreg17, sel_w;
R600_Reg128:%vreg1,%vreg26 R600_TReg32:%vreg17
%vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13
%vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0
%vreg12<def> = IMPLICIT_DEF; R600_Reg32:%vreg12
Successors according to CFG: BB#1
BB#1: derived from LLVM BB %25
Predecessors according to CFG: BB#0 BB#3
%vreg5<def> = PHI %vreg2, <BB#0>, %vreg9, <BB#3>;
R600_Reg32:%vreg5,%vreg2,%vreg9
%vreg6<def> = PHI %vreg3, <BB#0>, %vreg10, <BB#3>;
R600_Reg128:%vreg6,%vreg3,%vreg10
%vreg7<def> = PHI %vreg13, <BB#0>, %vreg11, <BB#3>;
R600_Reg32:%vreg7,%vreg13,%vreg11
%vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0,
0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7
%vreg30<def> = COPY %vreg29; GPRI32:%vreg30 R600_Reg32:%vreg29
%PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16; GPRI32:%vreg30
JUMP <BB#3>, pred:%PREDICATE_BIT<kill>
JUMP <BB#2>, pred:%noreg
Successors according to CFG: BB#2(4) BB#3(124)
BB#2: derived from LLVM BB %31
Predecessors according to CFG: BB#1
%vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6
%T2_X<def> = COPY %vreg39; R600_Reg32:%vreg39
%vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6
%T2_Y<def> = COPY %vreg40; R600_Reg32:%vreg40
%vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6
%T2_Z<def> = COPY %vreg41; R600_Reg32:%vreg41
%vreg42<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg42 R600_Reg128:%vreg6
%T2_W<def> = COPY %vreg42; R600_Reg32:%vreg42
%vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1
%T1_X<def> = COPY %vreg43; R600_Reg32:%vreg43
%vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1
%T1_Y<def> = COPY %vreg44; R600_Reg32:%vreg44
%vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1
%T1_Z<def> = COPY %vreg45; R600_Reg32:%vreg45
%vreg46<def> = COPY %vreg1:sel_w; R600_Reg32:%vreg46 R600_Reg128:%vreg1
%T1_W<def> = COPY %vreg46; R600_Reg32:%vreg46
RETURN
BB#3: derived from LLVM BB %41
Predecessors according to CFG: BB#1
%vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6
%vreg33<def> = IMPLICIT_DEF; R600_Reg128:%vreg33
%vreg32<def,tied1> = INSERT_SUBREG %vreg33<tied0>,
%vreg31<kill>, sel_x; R600_Reg128:%vreg32,%vreg33 R600_Reg32:%vreg31
%vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6
%vreg35<def,tied1> = INSERT_SUBREG %vreg32<tied0>,
%vreg34<kill>, sel_y; R600_Reg128:%vreg35,%vreg32 R600_Reg32:%vreg34
%vreg36<def,tied1> = INSERT_SUBREG %vreg35<tied0>, %vreg5, sel_z;
R600_Reg128:%vreg36,%vreg35 R600_Reg32:%vreg5
%vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6
%vreg10<def,tied1> = INSERT_SUBREG %vreg36<tied0>,
%vreg37<kill>, sel_w; R600_Reg128:%vreg10,%vreg36 R600_Reg32:%vreg37
%vreg9<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg6
%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38
%vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7, 0, 0, 0,
%vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0;
R600_Reg32:%vreg11,%vreg7,%vreg38
%vreg8<def> = COPY %vreg5; R600_Reg32:%vreg8,%vreg5
JUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Remove dead machine instructions ***:
# Machine code for function main: SSA
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
BB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
%vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17
%vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16
%vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15
%vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14
%vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18
%vreg20<def> = IMPLICIT_DEF; R600_Reg128:%vreg20
%vreg19<def,tied1> = INSERT_SUBREG %vreg20<tied0>, %vreg14, sel_x;
R600_Reg128:%vreg19,%vreg20 R600_TReg32:%vreg14
%vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2
%vreg22<def> = IMPLICIT_DEF; R600_Reg128:%vreg22
%vreg21<def,tied1> = INSERT_SUBREG %vreg22<tied0>,
%vreg18<kill>, sel_x; R600_Reg128:%vreg21,%vreg22 R600_Reg32:%vreg18
%vreg23<def,tied1> = INSERT_SUBREG %vreg19<tied0>, %vreg15, sel_y;
R600_Reg128:%vreg23,%vreg19 R600_TReg32:%vreg15
%vreg24<def,tied1> = INSERT_SUBREG %vreg21<tied0>, %vreg2, sel_y;
R600_Reg128:%vreg24,%vreg21 R600_Reg32:%vreg2
%vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25
%vreg26<def,tied1> = INSERT_SUBREG %vreg23<tied0>, %vreg16, sel_z;
R600_Reg128:%vreg26,%vreg23 R600_TReg32:%vreg16
%vreg27<def,tied1> = INSERT_SUBREG %vreg24<tied0>,
%vreg25<kill>, sel_z; R600_Reg128:%vreg27,%vreg24 R600_Reg32:%vreg25
%vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28
%vreg3<def,tied1> = INSERT_SUBREG %vreg27<tied0>,
%vreg28<kill>, sel_w; R600_Reg128:%vreg3,%vreg27 R600_Reg32:%vreg28
%vreg1<def,tied1> = INSERT_SUBREG %vreg26<tied0>, %vreg17, sel_w;
R600_Reg128:%vreg1,%vreg26 R600_TReg32:%vreg17
%vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13
%vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0
%vreg12<def> = IMPLICIT_DEF; R600_Reg32:%vreg12
Successors according to CFG: BB#1
BB#1: derived from LLVM BB %25
Predecessors according to CFG: BB#0 BB#3
%vreg5<def> = PHI %vreg2, <BB#0>, %vreg9, <BB#3>;
R600_Reg32:%vreg5,%vreg2,%vreg9
%vreg6<def> = PHI %vreg3, <BB#0>, %vreg10, <BB#3>;
R600_Reg128:%vreg6,%vreg3,%vreg10
%vreg7<def> = PHI %vreg13, <BB#0>, %vreg11, <BB#3>;
R600_Reg32:%vreg7,%vreg13,%vreg11
%vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0,
0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7
%vreg30<def> = COPY %vreg29; GPRI32:%vreg30 R600_Reg32:%vreg29
%PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16; GPRI32:%vreg30
JUMP <BB#3>, pred:%PREDICATE_BIT<kill>
JUMP <BB#2>, pred:%noreg
Successors according to CFG: BB#2(4) BB#3(124)
BB#2: derived from LLVM BB %31
Predecessors according to CFG: BB#1
%vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6
%T2_X<def> = COPY %vreg39; R600_Reg32:%vreg39
%vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6
%T2_Y<def> = COPY %vreg40; R600_Reg32:%vreg40
%vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6
%T2_Z<def> = COPY %vreg41; R600_Reg32:%vreg41
%vreg42<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg42 R600_Reg128:%vreg6
%T2_W<def> = COPY %vreg42; R600_Reg32:%vreg42
%vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1
%T1_X<def> = COPY %vreg43; R600_Reg32:%vreg43
%vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1
%T1_Y<def> = COPY %vreg44; R600_Reg32:%vreg44
%vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1
%T1_Z<def> = COPY %vreg45; R600_Reg32:%vreg45
%vreg46<def> = COPY %vreg1:sel_w; R600_Reg32:%vreg46 R600_Reg128:%vreg1
%T1_W<def> = COPY %vreg46; R600_Reg32:%vreg46
RETURN
BB#3: derived from LLVM BB %41
Predecessors according to CFG: BB#1
%vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6
%vreg33<def> = IMPLICIT_DEF; R600_Reg128:%vreg33
%vreg32<def,tied1> = INSERT_SUBREG %vreg33<tied0>,
%vreg31<kill>, sel_x; R600_Reg128:%vreg32,%vreg33 R600_Reg32:%vreg31
%vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6
%vreg35<def,tied1> = INSERT_SUBREG %vreg32<tied0>,
%vreg34<kill>, sel_y; R600_Reg128:%vreg35,%vreg32 R600_Reg32:%vreg34
%vreg36<def,tied1> = INSERT_SUBREG %vreg35<tied0>, %vreg5, sel_z;
R600_Reg128:%vreg36,%vreg35 R600_Reg32:%vreg5
%vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6
%vreg10<def,tied1> = INSERT_SUBREG %vreg36<tied0>,
%vreg37<kill>, sel_w; R600_Reg128:%vreg10,%vreg36 R600_Reg32:%vreg37
%vreg9<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg6
%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38
%vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7, 0, 0, 0,
%vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0;
R600_Reg32:%vreg11,%vreg7,%vreg38
%vreg8<def> = COPY %vreg5; R600_Reg32:%vreg8,%vreg5
JUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Machine Loop Invariant Code Motion ***:
# Machine code for function main: SSA
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
BB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
%vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17
%vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16
%vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15
%vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14
%vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18
%vreg20<def> = IMPLICIT_DEF; R600_Reg128:%vreg20
%vreg19<def,tied1> = INSERT_SUBREG %vreg20<tied0>, %vreg14, sel_x;
R600_Reg128:%vreg19,%vreg20 R600_TReg32:%vreg14
%vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2
%vreg22<def> = IMPLICIT_DEF; R600_Reg128:%vreg22
%vreg21<def,tied1> = INSERT_SUBREG %vreg22<tied0>,
%vreg18<kill>, sel_x; R600_Reg128:%vreg21,%vreg22 R600_Reg32:%vreg18
%vreg23<def,tied1> = INSERT_SUBREG %vreg19<tied0>, %vreg15, sel_y;
R600_Reg128:%vreg23,%vreg19 R600_TReg32:%vreg15
%vreg24<def,tied1> = INSERT_SUBREG %vreg21<tied0>, %vreg2, sel_y;
R600_Reg128:%vreg24,%vreg21 R600_Reg32:%vreg2
%vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25
%vreg26<def,tied1> = INSERT_SUBREG %vreg23<tied0>, %vreg16, sel_z;
R600_Reg128:%vreg26,%vreg23 R600_TReg32:%vreg16
%vreg27<def,tied1> = INSERT_SUBREG %vreg24<tied0>,
%vreg25<kill>, sel_z; R600_Reg128:%vreg27,%vreg24 R600_Reg32:%vreg25
%vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28
%vreg3<def,tied1> = INSERT_SUBREG %vreg27<tied0>,
%vreg28<kill>, sel_w; R600_Reg128:%vreg3,%vreg27 R600_Reg32:%vreg28
%vreg1<def,tied1> = INSERT_SUBREG %vreg26<tied0>, %vreg17, sel_w;
R600_Reg128:%vreg1,%vreg26 R600_TReg32:%vreg17
%vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13
%vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0
Successors according to CFG: BB#1
BB#1: derived from LLVM BB %25
Predecessors according to CFG: BB#0 BB#3
%vreg5<def> = PHI %vreg2, <BB#0>, %vreg9, <BB#3>;
R600_Reg32:%vreg5,%vreg2,%vreg9
%vreg6<def> = PHI %vreg3, <BB#0>, %vreg10, <BB#3>;
R600_Reg128:%vreg6,%vreg3,%vreg10
%vreg7<def> = PHI %vreg13, <BB#0>, %vreg11, <BB#3>;
R600_Reg32:%vreg7,%vreg13,%vreg11
%vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0,
0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7
%vreg30<def> = COPY %vreg29; GPRI32:%vreg30 R600_Reg32:%vreg29
%PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16; GPRI32:%vreg30
JUMP <BB#3>, pred:%PREDICATE_BIT<kill>
JUMP <BB#2>, pred:%noreg
Successors according to CFG: BB#2(4) BB#3(124)
BB#2: derived from LLVM BB %31
Predecessors according to CFG: BB#1
%vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6
%T2_X<def> = COPY %vreg39; R600_Reg32:%vreg39
%vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6
%T2_Y<def> = COPY %vreg40; R600_Reg32:%vreg40
%vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6
%T2_Z<def> = COPY %vreg41; R600_Reg32:%vreg41
%vreg42<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg42 R600_Reg128:%vreg6
%T2_W<def> = COPY %vreg42; R600_Reg32:%vreg42
%vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1
%T1_X<def> = COPY %vreg43; R600_Reg32:%vreg43
%vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1
%T1_Y<def> = COPY %vreg44; R600_Reg32:%vreg44
%vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1
%T1_Z<def> = COPY %vreg45; R600_Reg32:%vreg45
%vreg46<def> = COPY %vreg1:sel_w; R600_Reg32:%vreg46 R600_Reg128:%vreg1
%T1_W<def> = COPY %vreg46; R600_Reg32:%vreg46
RETURN
BB#3: derived from LLVM BB %41
Predecessors according to CFG: BB#1
%vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6
%vreg33<def> = IMPLICIT_DEF; R600_Reg128:%vreg33
%vreg32<def,tied1> = INSERT_SUBREG %vreg33<tied0>,
%vreg31<kill>, sel_x; R600_Reg128:%vreg32,%vreg33 R600_Reg32:%vreg31
%vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6
%vreg35<def,tied1> = INSERT_SUBREG %vreg32<tied0>,
%vreg34<kill>, sel_y; R600_Reg128:%vreg35,%vreg32 R600_Reg32:%vreg34
%vreg36<def,tied1> = INSERT_SUBREG %vreg35<tied0>, %vreg5, sel_z;
R600_Reg128:%vreg36,%vreg35 R600_Reg32:%vreg5
%vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6
%vreg10<def,tied1> = INSERT_SUBREG %vreg36<tied0>,
%vreg37<kill>, sel_w; R600_Reg128:%vreg10,%vreg36 R600_Reg32:%vreg37
%vreg9<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg6
%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38
%vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7, 0, 0, 0,
%vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0;
R600_Reg32:%vreg11,%vreg7,%vreg38
JUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Machine Common Subexpression Elimination ***:
# Machine code for function main: SSA
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
BB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
%vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17
%vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16
%vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15
%vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14
%vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18
%vreg20<def> = IMPLICIT_DEF; R600_Reg128:%vreg20
%vreg19<def,tied1> = INSERT_SUBREG %vreg20<tied0>, %vreg14, sel_x;
R600_Reg128:%vreg19,%vreg20 R600_TReg32:%vreg14
%vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2
%vreg22<def> = IMPLICIT_DEF; R600_Reg128:%vreg22
%vreg21<def,tied1> = INSERT_SUBREG %vreg22<tied0>,
%vreg18<kill>, sel_x; R600_Reg128:%vreg21,%vreg22 R600_Reg32:%vreg18
%vreg23<def,tied1> = INSERT_SUBREG %vreg19<tied0>, %vreg15, sel_y;
R600_Reg128:%vreg23,%vreg19 R600_TReg32:%vreg15
%vreg24<def,tied1> = INSERT_SUBREG %vreg21<tied0>, %vreg2, sel_y;
R600_Reg128:%vreg24,%vreg21 R600_Reg32:%vreg2
%vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25
%vreg26<def,tied1> = INSERT_SUBREG %vreg23<tied0>, %vreg16, sel_z;
R600_Reg128:%vreg26,%vreg23 R600_TReg32:%vreg16
%vreg27<def,tied1> = INSERT_SUBREG %vreg24<tied0>,
%vreg25<kill>, sel_z; R600_Reg128:%vreg27,%vreg24 R600_Reg32:%vreg25
%vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28
%vreg3<def,tied1> = INSERT_SUBREG %vreg27<tied0>,
%vreg28<kill>, sel_w; R600_Reg128:%vreg3,%vreg27 R600_Reg32:%vreg28
%vreg1<def,tied1> = INSERT_SUBREG %vreg26<tied0>, %vreg17, sel_w;
R600_Reg128:%vreg1,%vreg26 R600_TReg32:%vreg17
%vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13
%vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0
%vreg33<def> = IMPLICIT_DEF; R600_Reg128:%vreg33
Successors according to CFG: BB#1
BB#1: derived from LLVM BB %25
Predecessors according to CFG: BB#0 BB#3
%vreg5<def> = PHI %vreg2, <BB#0>, %vreg9, <BB#3>;
R600_Reg32:%vreg5,%vreg2,%vreg9
%vreg6<def> = PHI %vreg3, <BB#0>, %vreg10, <BB#3>;
R600_Reg128:%vreg6,%vreg3,%vreg10
%vreg7<def> = PHI %vreg13, <BB#0>, %vreg11, <BB#3>;
R600_Reg32:%vreg7,%vreg13,%vreg11
%vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0,
0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7
%vreg30<def> = COPY %vreg29; GPRI32:%vreg30 R600_Reg32:%vreg29
%PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16; GPRI32:%vreg30
JUMP <BB#3>, pred:%PREDICATE_BIT<kill>
JUMP <BB#2>, pred:%noreg
Successors according to CFG: BB#2(4) BB#3(124)
BB#2: derived from LLVM BB %31
Predecessors according to CFG: BB#1
%vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6
%T2_X<def> = COPY %vreg39; R600_Reg32:%vreg39
%vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6
%T2_Y<def> = COPY %vreg40; R600_Reg32:%vreg40
%vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6
%T2_Z<def> = COPY %vreg41; R600_Reg32:%vreg41
%vreg42<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg42 R600_Reg128:%vreg6
%T2_W<def> = COPY %vreg42; R600_Reg32:%vreg42
%vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1
%T1_X<def> = COPY %vreg43; R600_Reg32:%vreg43
%vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1
%T1_Y<def> = COPY %vreg44; R600_Reg32:%vreg44
%vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1
%T1_Z<def> = COPY %vreg45; R600_Reg32:%vreg45
%vreg46<def> = COPY %vreg1:sel_w; R600_Reg32:%vreg46 R600_Reg128:%vreg1
%T1_W<def> = COPY %vreg46; R600_Reg32:%vreg46
RETURN
BB#3: derived from LLVM BB %41
Predecessors according to CFG: BB#1
%vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6
%vreg32<def,tied1> = INSERT_SUBREG %vreg33<tied0>,
%vreg31<kill>, sel_x; R600_Reg128:%vreg32,%vreg33 R600_Reg32:%vreg31
%vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6
%vreg35<def,tied1> = INSERT_SUBREG %vreg32<tied0>,
%vreg34<kill>, sel_y; R600_Reg128:%vreg35,%vreg32 R600_Reg32:%vreg34
%vreg36<def,tied1> = INSERT_SUBREG %vreg35<tied0>, %vreg5, sel_z;
R600_Reg128:%vreg36,%vreg35 R600_Reg32:%vreg5
%vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6
%vreg10<def,tied1> = INSERT_SUBREG %vreg36<tied0>,
%vreg37<kill>, sel_w; R600_Reg128:%vreg10,%vreg36 R600_Reg32:%vreg37
%vreg9<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg6
%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38
%vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7, 0, 0, 0,
%vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0;
R600_Reg32:%vreg11,%vreg7,%vreg38
JUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Machine code sinking ***:
# Machine code for function main: SSA
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
BB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
%vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17
%vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16
%vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15
%vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14
%vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18
%vreg20<def> = IMPLICIT_DEF; R600_Reg128:%vreg20
%vreg19<def,tied1> = INSERT_SUBREG %vreg20<tied0>, %vreg14, sel_x;
R600_Reg128:%vreg19,%vreg20 R600_TReg32:%vreg14
%vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2
%vreg22<def> = IMPLICIT_DEF; R600_Reg128:%vreg22
%vreg21<def,tied1> = INSERT_SUBREG %vreg22<tied0>,
%vreg18<kill>, sel_x; R600_Reg128:%vreg21,%vreg22 R600_Reg32:%vreg18
%vreg23<def,tied1> = INSERT_SUBREG %vreg19<tied0>, %vreg15, sel_y;
R600_Reg128:%vreg23,%vreg19 R600_TReg32:%vreg15
%vreg24<def,tied1> = INSERT_SUBREG %vreg21<tied0>, %vreg2, sel_y;
R600_Reg128:%vreg24,%vreg21 R600_Reg32:%vreg2
%vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25
%vreg26<def,tied1> = INSERT_SUBREG %vreg23<tied0>, %vreg16, sel_z;
R600_Reg128:%vreg26,%vreg23 R600_TReg32:%vreg16
%vreg27<def,tied1> = INSERT_SUBREG %vreg24<tied0>,
%vreg25<kill>, sel_z; R600_Reg128:%vreg27,%vreg24 R600_Reg32:%vreg25
%vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28
%vreg3<def,tied1> = INSERT_SUBREG %vreg27<tied0>,
%vreg28<kill>, sel_w; R600_Reg128:%vreg3,%vreg27 R600_Reg32:%vreg28
%vreg1<def,tied1> = INSERT_SUBREG %vreg26<tied0>, %vreg17, sel_w;
R600_Reg128:%vreg1,%vreg26 R600_TReg32:%vreg17
%vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13
%vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0
%vreg33<def> = IMPLICIT_DEF; R600_Reg128:%vreg33
Successors according to CFG: BB#1
BB#1: derived from LLVM BB %25
Predecessors according to CFG: BB#0 BB#3
%vreg5<def> = PHI %vreg2, <BB#0>, %vreg9, <BB#3>;
R600_Reg32:%vreg5,%vreg2,%vreg9
%vreg6<def> = PHI %vreg3, <BB#0>, %vreg10, <BB#3>;
R600_Reg128:%vreg6,%vreg3,%vreg10
%vreg7<def> = PHI %vreg13, <BB#0>, %vreg11, <BB#3>;
R600_Reg32:%vreg7,%vreg13,%vreg11
%vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0,
0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7
%vreg30<def> = COPY %vreg29; GPRI32:%vreg30 R600_Reg32:%vreg29
%PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16; GPRI32:%vreg30
JUMP <BB#3>, pred:%PREDICATE_BIT<kill>
JUMP <BB#2>, pred:%noreg
Successors according to CFG: BB#2(4) BB#3(124)
BB#2: derived from LLVM BB %31
Predecessors according to CFG: BB#1
%vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6
%T2_X<def> = COPY %vreg39; R600_Reg32:%vreg39
%vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6
%T2_Y<def> = COPY %vreg40; R600_Reg32:%vreg40
%vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6
%T2_Z<def> = COPY %vreg41; R600_Reg32:%vreg41
%vreg42<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg42 R600_Reg128:%vreg6
%T2_W<def> = COPY %vreg42; R600_Reg32:%vreg42
%vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1
%T1_X<def> = COPY %vreg43; R600_Reg32:%vreg43
%vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1
%T1_Y<def> = COPY %vreg44; R600_Reg32:%vreg44
%vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1
%T1_Z<def> = COPY %vreg45; R600_Reg32:%vreg45
%vreg46<def> = COPY %vreg1:sel_w; R600_Reg32:%vreg46 R600_Reg128:%vreg1
%T1_W<def> = COPY %vreg46; R600_Reg32:%vreg46
RETURN
BB#3: derived from LLVM BB %41
Predecessors according to CFG: BB#1
%vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6
%vreg32<def,tied1> = INSERT_SUBREG %vreg33<tied0>,
%vreg31<kill>, sel_x; R600_Reg128:%vreg32,%vreg33 R600_Reg32:%vreg31
%vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6
%vreg35<def,tied1> = INSERT_SUBREG %vreg32<tied0>,
%vreg34<kill>, sel_y; R600_Reg128:%vreg35,%vreg32 R600_Reg32:%vreg34
%vreg36<def,tied1> = INSERT_SUBREG %vreg35<tied0>, %vreg5, sel_z;
R600_Reg128:%vreg36,%vreg35 R600_Reg32:%vreg5
%vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6
%vreg10<def,tied1> = INSERT_SUBREG %vreg36<tied0>,
%vreg37<kill>, sel_w; R600_Reg128:%vreg10,%vreg36 R600_Reg32:%vreg37
%vreg9<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg6
%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38
%vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7, 0, 0, 0,
%vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0;
R600_Reg32:%vreg11,%vreg7,%vreg38
JUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Peephole Optimizations ***:
# Machine code for function main: SSA
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
BB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
%vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17
%vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16
%vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15
%vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14
%vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18
%vreg20<def> = IMPLICIT_DEF; R600_Reg128:%vreg20
%vreg19<def,tied1> = INSERT_SUBREG %vreg20<tied0>, %vreg14, sel_x;
R600_Reg128:%vreg19,%vreg20 R600_TReg32:%vreg14
%vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2
%vreg22<def> = IMPLICIT_DEF; R600_Reg128:%vreg22
%vreg21<def,tied1> = INSERT_SUBREG %vreg22<tied0>,
%vreg18<kill>, sel_x; R600_Reg128:%vreg21,%vreg22 R600_Reg32:%vreg18
%vreg23<def,tied1> = INSERT_SUBREG %vreg19<tied0>, %vreg15, sel_y;
R600_Reg128:%vreg23,%vreg19 R600_TReg32:%vreg15
%vreg24<def,tied1> = INSERT_SUBREG %vreg21<tied0>, %vreg2, sel_y;
R600_Reg128:%vreg24,%vreg21 R600_Reg32:%vreg2
%vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25
%vreg26<def,tied1> = INSERT_SUBREG %vreg23<tied0>, %vreg16, sel_z;
R600_Reg128:%vreg26,%vreg23 R600_TReg32:%vreg16
%vreg27<def,tied1> = INSERT_SUBREG %vreg24<tied0>,
%vreg25<kill>, sel_z; R600_Reg128:%vreg27,%vreg24 R600_Reg32:%vreg25
%vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28
%vreg3<def,tied1> = INSERT_SUBREG %vreg27<tied0>,
%vreg28<kill>, sel_w; R600_Reg128:%vreg3,%vreg27 R600_Reg32:%vreg28
%vreg1<def,tied1> = INSERT_SUBREG %vreg26<tied0>, %vreg17, sel_w;
R600_Reg128:%vreg1,%vreg26 R600_TReg32:%vreg17
%vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13
%vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0
%vreg33<def> = IMPLICIT_DEF; R600_Reg128:%vreg33
Successors according to CFG: BB#1
BB#1: derived from LLVM BB %25
Predecessors according to CFG: BB#0 BB#3
%vreg5<def> = PHI %vreg2, <BB#0>, %vreg9, <BB#3>;
R600_Reg32:%vreg5,%vreg2,%vreg9
%vreg6<def> = PHI %vreg3, <BB#0>, %vreg10, <BB#3>;
R600_Reg128:%vreg6,%vreg3,%vreg10
%vreg7<def> = PHI %vreg13, <BB#0>, %vreg11, <BB#3>;
R600_Reg32:%vreg7,%vreg13,%vreg11
%vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0,
0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7
%vreg30<def> = COPY %vreg29; GPRI32:%vreg30 R600_Reg32:%vreg29
%PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16; GPRI32:%vreg30
JUMP <BB#3>, pred:%PREDICATE_BIT<kill>
JUMP <BB#2>, pred:%noreg
Successors according to CFG: BB#2(4) BB#3(124)
BB#2: derived from LLVM BB %31
Predecessors according to CFG: BB#1
%vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6
%T2_X<def> = COPY %vreg39; R600_Reg32:%vreg39
%vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6
%T2_Y<def> = COPY %vreg40; R600_Reg32:%vreg40
%vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6
%T2_Z<def> = COPY %vreg41; R600_Reg32:%vreg41
%vreg42<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg42 R600_Reg128:%vreg6
%T2_W<def> = COPY %vreg42; R600_Reg32:%vreg42
%vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1
%T1_X<def> = COPY %vreg43; R600_Reg32:%vreg43
%vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1
%T1_Y<def> = COPY %vreg44; R600_Reg32:%vreg44
%vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1
%T1_Z<def> = COPY %vreg45; R600_Reg32:%vreg45
%vreg46<def> = COPY %vreg1:sel_w; R600_Reg32:%vreg46 R600_Reg128:%vreg1
%T1_W<def> = COPY %vreg46; R600_Reg32:%vreg46
RETURN
BB#3: derived from LLVM BB %41
Predecessors according to CFG: BB#1
%vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6
%vreg32<def,tied1> = INSERT_SUBREG %vreg33<tied0>,
%vreg31<kill>, sel_x; R600_Reg128:%vreg32,%vreg33 R600_Reg32:%vreg31
%vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6
%vreg35<def,tied1> = INSERT_SUBREG %vreg32<tied0>,
%vreg34<kill>, sel_y; R600_Reg128:%vreg35,%vreg32 R600_Reg32:%vreg34
%vreg36<def,tied1> = INSERT_SUBREG %vreg35<tied0>, %vreg5, sel_z;
R600_Reg128:%vreg36,%vreg35 R600_Reg32:%vreg5
%vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6
%vreg10<def,tied1> = INSERT_SUBREG %vreg36<tied0>,
%vreg37<kill>, sel_w; R600_Reg128:%vreg10,%vreg36 R600_Reg32:%vreg37
%vreg9<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg6
%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38
%vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7, 0, 0, 0,
%vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0;
R600_Reg32:%vreg11,%vreg7,%vreg38
JUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Process Implicit Definitions ***:
# Machine code for function main: SSA
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
BB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
%vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17
%vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16
%vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15
%vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14
%vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18
%vreg20<def> = IMPLICIT_DEF; R600_Reg128:%vreg20
%vreg19<def,tied1> = INSERT_SUBREG %vreg20<tied0>, %vreg14, sel_x;
R600_Reg128:%vreg19,%vreg20 R600_TReg32:%vreg14
%vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2
%vreg22<def> = IMPLICIT_DEF; R600_Reg128:%vreg22
%vreg21<def,tied1> = INSERT_SUBREG %vreg22<tied0>,
%vreg18<kill>, sel_x; R600_Reg128:%vreg21,%vreg22 R600_Reg32:%vreg18
%vreg23<def,tied1> = INSERT_SUBREG %vreg19<tied0>, %vreg15, sel_y;
R600_Reg128:%vreg23,%vreg19 R600_TReg32:%vreg15
%vreg24<def,tied1> = INSERT_SUBREG %vreg21<tied0>, %vreg2, sel_y;
R600_Reg128:%vreg24,%vreg21 R600_Reg32:%vreg2
%vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25
%vreg26<def,tied1> = INSERT_SUBREG %vreg23<tied0>, %vreg16, sel_z;
R600_Reg128:%vreg26,%vreg23 R600_TReg32:%vreg16
%vreg27<def,tied1> = INSERT_SUBREG %vreg24<tied0>,
%vreg25<kill>, sel_z; R600_Reg128:%vreg27,%vreg24 R600_Reg32:%vreg25
%vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28
%vreg3<def,tied1> = INSERT_SUBREG %vreg27<tied0>,
%vreg28<kill>, sel_w; R600_Reg128:%vreg3,%vreg27 R600_Reg32:%vreg28
%vreg1<def,tied1> = INSERT_SUBREG %vreg26<tied0>, %vreg17, sel_w;
R600_Reg128:%vreg1,%vreg26 R600_TReg32:%vreg17
%vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13
%vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0
%vreg33<def> = IMPLICIT_DEF; R600_Reg128:%vreg33
Successors according to CFG: BB#1
BB#1: derived from LLVM BB %25
Predecessors according to CFG: BB#0 BB#3
%vreg5<def> = PHI %vreg2, <BB#0>, %vreg9, <BB#3>;
R600_Reg32:%vreg5,%vreg2,%vreg9
%vreg6<def> = PHI %vreg3, <BB#0>, %vreg10, <BB#3>;
R600_Reg128:%vreg6,%vreg3,%vreg10
%vreg7<def> = PHI %vreg13, <BB#0>, %vreg11, <BB#3>;
R600_Reg32:%vreg7,%vreg13,%vreg11
%vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0,
0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7
%vreg30<def> = COPY %vreg29; R600_Reg32:%vreg30,%vreg29
%PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16;
R600_Reg32:%vreg30
JUMP <BB#3>, pred:%PREDICATE_BIT<kill>
JUMP <BB#2>, pred:%noreg
Successors according to CFG: BB#2(4) BB#3(124)
BB#2: derived from LLVM BB %31
Predecessors according to CFG: BB#1
%vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6
%T2_X<def> = COPY %vreg39; R600_Reg32:%vreg39
%vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6
%T2_Y<def> = COPY %vreg40; R600_Reg32:%vreg40
%vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6
%T2_Z<def> = COPY %vreg41; R600_Reg32:%vreg41
%vreg42<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg42 R600_Reg128:%vreg6
%T2_W<def> = COPY %vreg42; R600_Reg32:%vreg42
%vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1
%T1_X<def> = COPY %vreg43; R600_Reg32:%vreg43
%vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1
%T1_Y<def> = COPY %vreg44; R600_Reg32:%vreg44
%vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1
%T1_Z<def> = COPY %vreg45; R600_Reg32:%vreg45
%vreg46<def> = COPY %vreg1:sel_w; R600_Reg32:%vreg46 R600_Reg128:%vreg1
%T1_W<def> = COPY %vreg46; R600_Reg32:%vreg46
RETURN
BB#3: derived from LLVM BB %41
Predecessors according to CFG: BB#1
%vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6
%vreg32<def,tied1> = INSERT_SUBREG %vreg33<tied0>,
%vreg31<kill>, sel_x; R600_Reg128:%vreg32,%vreg33 R600_Reg32:%vreg31
%vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6
%vreg35<def,tied1> = INSERT_SUBREG %vreg32<tied0>,
%vreg34<kill>, sel_y; R600_Reg128:%vreg35,%vreg32 R600_Reg32:%vreg34
%vreg36<def,tied1> = INSERT_SUBREG %vreg35<tied0>, %vreg5, sel_z;
R600_Reg128:%vreg36,%vreg35 R600_Reg32:%vreg5
%vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6
%vreg10<def,tied1> = INSERT_SUBREG %vreg36<tied0>,
%vreg37<kill>, sel_w; R600_Reg128:%vreg10,%vreg36 R600_Reg32:%vreg37
%vreg9<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg6
%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38
%vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7, 0, 0, 0,
%vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0;
R600_Reg32:%vreg11,%vreg7,%vreg38
JUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Remove unreachable machine basic blocks ***:
# Machine code for function main: SSA
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
BB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
%vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17
%vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16
%vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15
%vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14
%vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18
%vreg19<def,tied1> = INSERT_SUBREG %vreg20<undef,tied0>, %vreg14,
sel_x; R600_Reg128:%vreg19,%vreg20 R600_TReg32:%vreg14
%vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2
%vreg21<def,tied1> = INSERT_SUBREG %vreg22<undef,tied0>,
%vreg18<kill>, sel_x; R600_Reg128:%vreg21,%vreg22 R600_Reg32:%vreg18
%vreg23<def,tied1> = INSERT_SUBREG %vreg19<tied0>, %vreg15, sel_y;
R600_Reg128:%vreg23,%vreg19 R600_TReg32:%vreg15
%vreg24<def,tied1> = INSERT_SUBREG %vreg21<tied0>, %vreg2, sel_y;
R600_Reg128:%vreg24,%vreg21 R600_Reg32:%vreg2
%vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25
%vreg26<def,tied1> = INSERT_SUBREG %vreg23<tied0>, %vreg16, sel_z;
R600_Reg128:%vreg26,%vreg23 R600_TReg32:%vreg16
%vreg27<def,tied1> = INSERT_SUBREG %vreg24<tied0>,
%vreg25<kill>, sel_z; R600_Reg128:%vreg27,%vreg24 R600_Reg32:%vreg25
%vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28
%vreg3<def,tied1> = INSERT_SUBREG %vreg27<tied0>,
%vreg28<kill>, sel_w; R600_Reg128:%vreg3,%vreg27 R600_Reg32:%vreg28
%vreg1<def,tied1> = INSERT_SUBREG %vreg26<tied0>, %vreg17, sel_w;
R600_Reg128:%vreg1,%vreg26 R600_TReg32:%vreg17
%vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13
%vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0
Successors according to CFG: BB#1
BB#1: derived from LLVM BB %25
Predecessors according to CFG: BB#0 BB#3
%vreg5<def> = PHI %vreg2, <BB#0>, %vreg9, <BB#3>;
R600_Reg32:%vreg5,%vreg2,%vreg9
%vreg6<def> = PHI %vreg3, <BB#0>, %vreg10, <BB#3>;
R600_Reg128:%vreg6,%vreg3,%vreg10
%vreg7<def> = PHI %vreg13, <BB#0>, %vreg11, <BB#3>;
R600_Reg32:%vreg7,%vreg13,%vreg11
%vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0,
0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7
%vreg30<def> = COPY %vreg29; R600_Reg32:%vreg30,%vreg29
%PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16;
R600_Reg32:%vreg30
JUMP <BB#3>, pred:%PREDICATE_BIT<kill>
JUMP <BB#2>, pred:%noreg
Successors according to CFG: BB#2(4) BB#3(124)
BB#2: derived from LLVM BB %31
Predecessors according to CFG: BB#1
%vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6
%T2_X<def> = COPY %vreg39; R600_Reg32:%vreg39
%vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6
%T2_Y<def> = COPY %vreg40; R600_Reg32:%vreg40
%vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6
%T2_Z<def> = COPY %vreg41; R600_Reg32:%vreg41
%vreg42<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg42 R600_Reg128:%vreg6
%T2_W<def> = COPY %vreg42; R600_Reg32:%vreg42
%vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1
%T1_X<def> = COPY %vreg43; R600_Reg32:%vreg43
%vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1
%T1_Y<def> = COPY %vreg44; R600_Reg32:%vreg44
%vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1
%T1_Z<def> = COPY %vreg45; R600_Reg32:%vreg45
%vreg46<def> = COPY %vreg1:sel_w; R600_Reg32:%vreg46 R600_Reg128:%vreg1
%T1_W<def> = COPY %vreg46; R600_Reg32:%vreg46
RETURN
BB#3: derived from LLVM BB %41
Predecessors according to CFG: BB#1
%vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6
%vreg32<def,tied1> = INSERT_SUBREG %vreg33<undef,tied0>,
%vreg31<kill>, sel_x; R600_Reg128:%vreg32,%vreg33 R600_Reg32:%vreg31
%vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6
%vreg35<def,tied1> = INSERT_SUBREG %vreg32<tied0>,
%vreg34<kill>, sel_y; R600_Reg128:%vreg35,%vreg32 R600_Reg32:%vreg34
%vreg36<def,tied1> = INSERT_SUBREG %vreg35<tied0>, %vreg5, sel_z;
R600_Reg128:%vreg36,%vreg35 R600_Reg32:%vreg5
%vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6
%vreg10<def,tied1> = INSERT_SUBREG %vreg36<tied0>,
%vreg37<kill>, sel_w; R600_Reg128:%vreg10,%vreg36 R600_Reg32:%vreg37
%vreg9<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg6
%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38
%vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7, 0, 0, 0,
%vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0;
R600_Reg32:%vreg11,%vreg7,%vreg38
JUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Live Variable Analysis ***:
# Machine code for function main: SSA
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
BB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
%vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17
%vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16
%vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15
%vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14
%vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18
%vreg19<def,tied1> = INSERT_SUBREG %vreg20<undef,tied0>, %vreg14,
sel_x; R600_Reg128:%vreg19,%vreg20 R600_TReg32:%vreg14
%vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2
%vreg21<def,tied1> = INSERT_SUBREG %vreg22<undef,tied0>,
%vreg18<kill>, sel_x; R600_Reg128:%vreg21,%vreg22 R600_Reg32:%vreg18
%vreg23<def,tied1> = INSERT_SUBREG %vreg19<tied0>, %vreg15, sel_y;
R600_Reg128:%vreg23,%vreg19 R600_TReg32:%vreg15
%vreg24<def,tied1> = INSERT_SUBREG %vreg21<tied0>, %vreg2, sel_y;
R600_Reg128:%vreg24,%vreg21 R600_Reg32:%vreg2
%vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25
%vreg26<def,tied1> = INSERT_SUBREG %vreg23<tied0>, %vreg16, sel_z;
R600_Reg128:%vreg26,%vreg23 R600_TReg32:%vreg16
%vreg27<def,tied1> = INSERT_SUBREG %vreg24<tied0>,
%vreg25<kill>, sel_z; R600_Reg128:%vreg27,%vreg24 R600_Reg32:%vreg25
%vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28
%vreg3<def,tied1> = INSERT_SUBREG %vreg27<tied0>,
%vreg28<kill>, sel_w; R600_Reg128:%vreg3,%vreg27 R600_Reg32:%vreg28
%vreg1<def,tied1> = INSERT_SUBREG %vreg26<tied0>, %vreg17, sel_w;
R600_Reg128:%vreg1,%vreg26 R600_TReg32:%vreg17
%vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13
%vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0
Successors according to CFG: BB#1
BB#1: derived from LLVM BB %25
Predecessors according to CFG: BB#0 BB#3
%vreg5<def> = PHI %vreg2, <BB#0>, %vreg9, <BB#3>;
R600_Reg32:%vreg5,%vreg2,%vreg9
%vreg6<def> = PHI %vreg3, <BB#0>, %vreg10, <BB#3>;
R600_Reg128:%vreg6,%vreg3,%vreg10
%vreg7<def> = PHI %vreg13, <BB#0>, %vreg11, <BB#3>;
R600_Reg32:%vreg7,%vreg13,%vreg11
%vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0,
0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7
%vreg30<def> = COPY %vreg29; R600_Reg32:%vreg30,%vreg29
%PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16;
R600_Reg32:%vreg30
JUMP <BB#3>, pred:%PREDICATE_BIT<kill>
JUMP <BB#2>, pred:%noreg
Successors according to CFG: BB#2(4) BB#3(124)
BB#2: derived from LLVM BB %31
Predecessors according to CFG: BB#1
%vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6
%T2_X<def> = COPY %vreg39; R600_Reg32:%vreg39
%vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6
%T2_Y<def> = COPY %vreg40; R600_Reg32:%vreg40
%vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6
%T2_Z<def> = COPY %vreg41; R600_Reg32:%vreg41
%vreg42<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg42 R600_Reg128:%vreg6
%T2_W<def> = COPY %vreg42; R600_Reg32:%vreg42
%vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1
%T1_X<def> = COPY %vreg43; R600_Reg32:%vreg43
%vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1
%T1_Y<def> = COPY %vreg44; R600_Reg32:%vreg44
%vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1
%T1_Z<def> = COPY %vreg45; R600_Reg32:%vreg45
%vreg46<def> = COPY %vreg1:sel_w; R600_Reg32:%vreg46 R600_Reg128:%vreg1
%T1_W<def> = COPY %vreg46; R600_Reg32:%vreg46
RETURN
BB#3: derived from LLVM BB %41
Predecessors according to CFG: BB#1
%vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6
%vreg32<def,tied1> = INSERT_SUBREG %vreg33<undef,tied0>,
%vreg31<kill>, sel_x; R600_Reg128:%vreg32,%vreg33 R600_Reg32:%vreg31
%vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6
%vreg35<def,tied1> = INSERT_SUBREG %vreg32<tied0>,
%vreg34<kill>, sel_y; R600_Reg128:%vreg35,%vreg32 R600_Reg32:%vreg34
%vreg36<def,tied1> = INSERT_SUBREG %vreg35<tied0>, %vreg5, sel_z;
R600_Reg128:%vreg36,%vreg35 R600_Reg32:%vreg5
%vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6
%vreg10<def,tied1> = INSERT_SUBREG %vreg36<tied0>,
%vreg37<kill>, sel_w; R600_Reg128:%vreg10,%vreg36 R600_Reg32:%vreg37
%vreg9<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg6
%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38
%vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7, 0, 0, 0,
%vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0;
R600_Reg32:%vreg11,%vreg7,%vreg38
JUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Eliminate PHI nodes for register allocation ***:
# Machine code for function main: SSA
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
BB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
%vreg17<def> = COPY %T1_W<kill>; R600_TReg32:%vreg17
%vreg16<def> = COPY %T1_Z<kill>; R600_TReg32:%vreg16
%vreg15<def> = COPY %T1_Y<kill>; R600_TReg32:%vreg15
%vreg14<def> = COPY %T1_X<kill>; R600_TReg32:%vreg14
%vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18
%vreg19<def,tied1> = INSERT_SUBREG %vreg20<undef,tied0>,
%vreg14<kill>, sel_x; R600_Reg128:%vreg19,%vreg20 R600_TReg32:%vreg14
%vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2
%vreg21<def,tied1> = INSERT_SUBREG %vreg22<undef,tied0>,
%vreg18<kill>, sel_x; R600_Reg128:%vreg21,%vreg22 R600_Reg32:%vreg18
%vreg23<def,tied1> = INSERT_SUBREG %vreg19<kill,tied0>,
%vreg15<kill>, sel_y; R600_Reg128:%vreg23,%vreg19 R600_TReg32:%vreg15
%vreg24<def,tied1> = INSERT_SUBREG %vreg21<kill,tied0>, %vreg2,
sel_y; R600_Reg128:%vreg24,%vreg21 R600_Reg32:%vreg2
%vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25
%vreg26<def,tied1> = INSERT_SUBREG %vreg23<kill,tied0>,
%vreg16<kill>, sel_z; R600_Reg128:%vreg26,%vreg23 R600_TReg32:%vreg16
%vreg27<def,tied1> = INSERT_SUBREG %vreg24<kill,tied0>,
%vreg25<kill>, sel_z; R600_Reg128:%vreg27,%vreg24 R600_Reg32:%vreg25
%vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28
%vreg3<def,tied1> = INSERT_SUBREG %vreg27<kill,tied0>,
%vreg28<kill>, sel_w; R600_Reg128:%vreg3,%vreg27 R600_Reg32:%vreg28
%vreg1<def,tied1> = INSERT_SUBREG %vreg26<kill,tied0>,
%vreg17<kill>, sel_w; R600_Reg128:%vreg1,%vreg26 R600_TReg32:%vreg17
%vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13
%vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0
Successors according to CFG: BB#1
BB#1: derived from LLVM BB %25
Predecessors according to CFG: BB#0 BB#3
%vreg5<def> = PHI %vreg2, <BB#0>, %vreg9, <BB#3>;
R600_Reg32:%vreg5,%vreg2,%vreg9
%vreg6<def> = PHI %vreg3, <BB#0>, %vreg10, <BB#3>;
R600_Reg128:%vreg6,%vreg3,%vreg10
%vreg7<def> = PHI %vreg13, <BB#0>, %vreg11, <BB#3>;
R600_Reg32:%vreg7,%vreg13,%vreg11
%vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0,
0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7
%vreg30<def> = COPY %vreg29<kill>; R600_Reg32:%vreg30,%vreg29
%PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16;
R600_Reg32:%vreg30
JUMP <BB#3>, pred:%PREDICATE_BIT
JUMP <BB#2>, pred:%noreg
Successors according to CFG: BB#2(4) BB#3(124)
BB#2: derived from LLVM BB %31
Predecessors according to CFG: BB#1
%vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6
%T2_X<def> = COPY %vreg39<kill>; R600_Reg32:%vreg39
%vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6
%T2_Y<def> = COPY %vreg40<kill>; R600_Reg32:%vreg40
%vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6
%T2_Z<def> = COPY %vreg41<kill>; R600_Reg32:%vreg41
%vreg42<def> = COPY %vreg6:sel_w<kill>; R600_Reg32:%vreg42
R600_Reg128:%vreg6
%T2_W<def> = COPY %vreg42<kill>; R600_Reg32:%vreg42
%vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1
%T1_X<def> = COPY %vreg43<kill>; R600_Reg32:%vreg43
%vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1
%T1_Y<def> = COPY %vreg44<kill>; R600_Reg32:%vreg44
%vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1
%T1_Z<def> = COPY %vreg45<kill>; R600_Reg32:%vreg45
%vreg46<def> = COPY %vreg1:sel_w<kill>; R600_Reg32:%vreg46
R600_Reg128:%vreg1
%T1_W<def> = COPY %vreg46<kill>; R600_Reg32:%vreg46
RETURN %T1_W<imp-use,kill>, %T1_Z<imp-use,kill>,
%T1_Y<imp-use,kill>, %T1_X<imp-use,kill>, %T2_W<imp-use,kill>,
%T2_Z<imp-use,kill>, %T2_Y<imp-use,kill>, %T2_X<imp-use,kill>
BB#3: derived from LLVM BB %41
Predecessors according to CFG: BB#1
%vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6
%vreg32<def,tied1> = INSERT_SUBREG %vreg33<undef,tied0>,
%vreg31<kill>, sel_x; R600_Reg128:%vreg32,%vreg33 R600_Reg32:%vreg31
%vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6
%vreg35<def,tied1> = INSERT_SUBREG %vreg32<kill,tied0>,
%vreg34<kill>, sel_y; R600_Reg128:%vreg35,%vreg32 R600_Reg32:%vreg34
%vreg36<def,tied1> = INSERT_SUBREG %vreg35<kill,tied0>,
%vreg5<kill>, sel_z; R600_Reg128:%vreg36,%vreg35 R600_Reg32:%vreg5
%vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6
%vreg10<def,tied1> = INSERT_SUBREG %vreg36<kill,tied0>,
%vreg37<kill>, sel_w; R600_Reg128:%vreg10,%vreg36 R600_Reg32:%vreg37
%vreg9<def> = COPY %vreg6:sel_z<kill>; R600_Reg32:%vreg9
R600_Reg128:%vreg6
%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38
%vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7<kill>, 0, 0, 0,
%vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0;
R600_Reg32:%vreg11,%vreg7,%vreg38
JUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Two-Address instruction pass ***:
# Machine code for function main: Post SSA
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
BB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
%vreg17<def> = COPY %T1_W<kill>; R600_TReg32:%vreg17
%vreg16<def> = COPY %T1_Z<kill>; R600_TReg32:%vreg16
%vreg15<def> = COPY %T1_Y<kill>; R600_TReg32:%vreg15
%vreg14<def> = COPY %T1_X<kill>; R600_TReg32:%vreg14
%vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18
%vreg19<def,tied1> = INSERT_SUBREG %vreg20<undef,tied0>,
%vreg14<kill>, sel_x; R600_Reg128:%vreg19,%vreg20 R600_TReg32:%vreg14
%vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2
%vreg21<def,tied1> = INSERT_SUBREG %vreg22<undef,tied0>,
%vreg18<kill>, sel_x; R600_Reg128:%vreg21,%vreg22 R600_Reg32:%vreg18
%vreg23<def,tied1> = INSERT_SUBREG %vreg19<kill,tied0>,
%vreg15<kill>, sel_y; R600_Reg128:%vreg23,%vreg19 R600_TReg32:%vreg15
%vreg24<def,tied1> = INSERT_SUBREG %vreg21<kill,tied0>, %vreg2,
sel_y; R600_Reg128:%vreg24,%vreg21 R600_Reg32:%vreg2
%vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25
%vreg26<def,tied1> = INSERT_SUBREG %vreg23<kill,tied0>,
%vreg16<kill>, sel_z; R600_Reg128:%vreg26,%vreg23 R600_TReg32:%vreg16
%vreg27<def,tied1> = INSERT_SUBREG %vreg24<kill,tied0>,
%vreg25<kill>, sel_z; R600_Reg128:%vreg27,%vreg24 R600_Reg32:%vreg25
%vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28
%vreg3<def,tied1> = INSERT_SUBREG %vreg27<kill,tied0>,
%vreg28<kill>, sel_w; R600_Reg128:%vreg3,%vreg27 R600_Reg32:%vreg28
%vreg1<def,tied1> = INSERT_SUBREG %vreg26<kill,tied0>,
%vreg17<kill>, sel_w; R600_Reg128:%vreg1,%vreg26 R600_TReg32:%vreg17
%vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13
%vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0
%vreg47<def> = COPY %vreg2<kill>; R600_Reg32:%vreg47,%vreg2
%vreg48<def> = COPY %vreg3<kill>; R600_Reg128:%vreg48,%vreg3
%vreg49<def> = COPY %vreg13<kill>; R600_Reg32:%vreg49,%vreg13
Successors according to CFG: BB#1
BB#1: derived from LLVM BB %25
Predecessors according to CFG: BB#0 BB#3
%vreg5<def> = COPY %vreg47<kill>; R600_Reg32:%vreg5,%vreg47
%vreg6<def> = COPY %vreg48<kill>; R600_Reg128:%vreg6,%vreg48
%vreg7<def> = COPY %vreg49<kill>; R600_Reg32:%vreg7,%vreg49
%vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0,
0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7
%vreg30<def> = COPY %vreg29<kill>; R600_Reg32:%vreg30,%vreg29
%PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16;
R600_Reg32:%vreg30
JUMP <BB#3>, pred:%PREDICATE_BIT
JUMP <BB#2>, pred:%noreg
Successors according to CFG: BB#2(4) BB#3(124)
BB#2: derived from LLVM BB %31
Predecessors according to CFG: BB#1
%vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6
%T2_X<def> = COPY %vreg39<kill>; R600_Reg32:%vreg39
%vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6
%T2_Y<def> = COPY %vreg40<kill>; R600_Reg32:%vreg40
%vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6
%T2_Z<def> = COPY %vreg41<kill>; R600_Reg32:%vreg41
%vreg42<def> = COPY %vreg6:sel_w<kill>; R600_Reg32:%vreg42
R600_Reg128:%vreg6
%T2_W<def> = COPY %vreg42<kill>; R600_Reg32:%vreg42
%vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1
%T1_X<def> = COPY %vreg43<kill>; R600_Reg32:%vreg43
%vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1
%T1_Y<def> = COPY %vreg44<kill>; R600_Reg32:%vreg44
%vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1
%T1_Z<def> = COPY %vreg45<kill>; R600_Reg32:%vreg45
%vreg46<def> = COPY %vreg1:sel_w<kill>; R600_Reg32:%vreg46
R600_Reg128:%vreg1
%T1_W<def> = COPY %vreg46<kill>; R600_Reg32:%vreg46
RETURN %T1_W<imp-use,kill>, %T1_Z<imp-use,kill>,
%T1_Y<imp-use,kill>, %T1_X<imp-use,kill>, %T2_W<imp-use,kill>,
%T2_Z<imp-use,kill>, %T2_Y<imp-use,kill>, %T2_X<imp-use,kill>
BB#3: derived from LLVM BB %41
Predecessors according to CFG: BB#1
%vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6
%vreg32<def,tied1> = INSERT_SUBREG %vreg33<undef,tied0>,
%vreg31<kill>, sel_x; R600_Reg128:%vreg32,%vreg33 R600_Reg32:%vreg31
%vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6
%vreg35<def,tied1> = INSERT_SUBREG %vreg32<kill,tied0>,
%vreg34<kill>, sel_y; R600_Reg128:%vreg35,%vreg32 R600_Reg32:%vreg34
%vreg36<def,tied1> = INSERT_SUBREG %vreg35<kill,tied0>,
%vreg5<kill>, sel_z; R600_Reg128:%vreg36,%vreg35 R600_Reg32:%vreg5
%vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6
%vreg10<def,tied1> = INSERT_SUBREG %vreg36<kill,tied0>,
%vreg37<kill>, sel_w; R600_Reg128:%vreg10,%vreg36 R600_Reg32:%vreg37
%vreg9<def> = COPY %vreg6:sel_z<kill>; R600_Reg32:%vreg9
R600_Reg128:%vreg6
%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38
%vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7<kill>, 0, 0, 0,
%vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0;
R600_Reg32:%vreg11,%vreg7,%vreg38
%vreg47<def> = COPY %vreg9<kill>; R600_Reg32:%vreg47,%vreg9
%vreg48<def> = COPY %vreg10<kill>; R600_Reg128:%vreg48,%vreg10
%vreg49<def> = COPY %vreg11<kill>; R600_Reg32:%vreg49,%vreg11
JUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Slot index numbering ***:
# Machine code for function main: Post SSA
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
BB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
%vreg17<def> = COPY %T1_W<kill>; R600_TReg32:%vreg17
%vreg16<def> = COPY %T1_Z<kill>; R600_TReg32:%vreg16
%vreg15<def> = COPY %T1_Y<kill>; R600_TReg32:%vreg15
%vreg14<def> = COPY %T1_X<kill>; R600_TReg32:%vreg14
%vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18
%vreg19:sel_x<def,read-undef> = COPY %vreg14<kill>;
R600_Reg128:%vreg19 R600_TReg32:%vreg14
%vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2
%vreg21:sel_x<def,read-undef> = COPY %vreg18<kill>;
R600_Reg128:%vreg21 R600_Reg32:%vreg18
%vreg23<def> = COPY %vreg19<kill>; R600_Reg128:%vreg23,%vreg19
%vreg23:sel_y<def> = COPY %vreg15<kill>; R600_Reg128:%vreg23
R600_TReg32:%vreg15
%vreg24<def> = COPY %vreg21<kill>; R600_Reg128:%vreg24,%vreg21
%vreg24:sel_y<def> = COPY %vreg2; R600_Reg128:%vreg24 R600_Reg32:%vreg2
%vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25
%vreg26<def> = COPY %vreg23<kill>; R600_Reg128:%vreg26,%vreg23
%vreg26:sel_z<def> = COPY %vreg16<kill>; R600_Reg128:%vreg26
R600_TReg32:%vreg16
%vreg27<def> = COPY %vreg24<kill>; R600_Reg128:%vreg27,%vreg24
%vreg27:sel_z<def> = COPY %vreg25<kill>; R600_Reg128:%vreg27
R600_Reg32:%vreg25
%vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28
%vreg3<def> = COPY %vreg27<kill>; R600_Reg128:%vreg3,%vreg27
%vreg3:sel_w<def> = COPY %vreg28<kill>; R600_Reg128:%vreg3
R600_Reg32:%vreg28
%vreg1<def> = COPY %vreg26<kill>; R600_Reg128:%vreg1,%vreg26
%vreg1:sel_w<def> = COPY %vreg17<kill>; R600_Reg128:%vreg1
R600_TReg32:%vreg17
%vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13
%vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0
%vreg47<def> = COPY %vreg2<kill>; R600_Reg32:%vreg47,%vreg2
%vreg48<def> = COPY %vreg3<kill>; R600_Reg128:%vreg48,%vreg3
%vreg49<def> = COPY %vreg13<kill>; R600_Reg32:%vreg49,%vreg13
Successors according to CFG: BB#1
BB#1: derived from LLVM BB %25
Predecessors according to CFG: BB#0 BB#3
%vreg5<def> = COPY %vreg47<kill>; R600_Reg32:%vreg5,%vreg47
%vreg6<def> = COPY %vreg48<kill>; R600_Reg128:%vreg6,%vreg48
%vreg7<def> = COPY %vreg49<kill>; R600_Reg32:%vreg7,%vreg49
%vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0,
0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7
%vreg30<def> = COPY %vreg29<kill>; R600_Reg32:%vreg30,%vreg29
%PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16;
R600_Reg32:%vreg30
JUMP <BB#3>, pred:%PREDICATE_BIT
JUMP <BB#2>, pred:%noreg
Successors according to CFG: BB#2(4) BB#3(124)
BB#2: derived from LLVM BB %31
Predecessors according to CFG: BB#1
%vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6
%T2_X<def> = COPY %vreg39<kill>; R600_Reg32:%vreg39
%vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6
%T2_Y<def> = COPY %vreg40<kill>; R600_Reg32:%vreg40
%vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6
%T2_Z<def> = COPY %vreg41<kill>; R600_Reg32:%vreg41
%vreg42<def> = COPY %vreg6:sel_w<kill>; R600_Reg32:%vreg42
R600_Reg128:%vreg6
%T2_W<def> = COPY %vreg42<kill>; R600_Reg32:%vreg42
%vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1
%T1_X<def> = COPY %vreg43<kill>; R600_Reg32:%vreg43
%vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1
%T1_Y<def> = COPY %vreg44<kill>; R600_Reg32:%vreg44
%vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1
%T1_Z<def> = COPY %vreg45<kill>; R600_Reg32:%vreg45
%vreg46<def> = COPY %vreg1:sel_w<kill>; R600_Reg32:%vreg46
R600_Reg128:%vreg1
%T1_W<def> = COPY %vreg46<kill>; R600_Reg32:%vreg46
RETURN %T1_W<imp-use,kill>, %T1_Z<imp-use,kill>,
%T1_Y<imp-use,kill>, %T1_X<imp-use,kill>, %T2_W<imp-use,kill>,
%T2_Z<imp-use,kill>, %T2_Y<imp-use,kill>, %T2_X<imp-use,kill>
BB#3: derived from LLVM BB %41
Predecessors according to CFG: BB#1
%vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6
%vreg32:sel_x<def,read-undef> = COPY %vreg31<kill>;
R600_Reg128:%vreg32 R600_Reg32:%vreg31
%vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6
%vreg35<def> = COPY %vreg32<kill>; R600_Reg128:%vreg35,%vreg32
%vreg35:sel_y<def> = COPY %vreg34<kill>; R600_Reg128:%vreg35
R600_Reg32:%vreg34
%vreg36<def> = COPY %vreg35<kill>; R600_Reg128:%vreg36,%vreg35
%vreg36:sel_z<def> = COPY %vreg5<kill>; R600_Reg128:%vreg36
R600_Reg32:%vreg5
%vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6
%vreg10<def> = COPY %vreg36<kill>; R600_Reg128:%vreg10,%vreg36
%vreg10:sel_w<def> = COPY %vreg37<kill>; R600_Reg128:%vreg10
R600_Reg32:%vreg37
%vreg9<def> = COPY %vreg6:sel_z<kill>; R600_Reg32:%vreg9
R600_Reg128:%vreg6
%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38
%vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7<kill>, 0, 0, 0,
%vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0;
R600_Reg32:%vreg11,%vreg7,%vreg38
%vreg47<def> = COPY %vreg9<kill>; R600_Reg32:%vreg47,%vreg9
%vreg48<def> = COPY %vreg10<kill>; R600_Reg128:%vreg48,%vreg10
%vreg49<def> = COPY %vreg11<kill>; R600_Reg32:%vreg49,%vreg11
JUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Live Interval Analysis ***:
# Machine code for function main: Post SSA
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
0BBB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
16B%vreg17<def> = COPY %T1_W<kill>; R600_TReg32:%vreg17
32B%vreg16<def> = COPY %T1_Z<kill>; R600_TReg32:%vreg16
48B%vreg15<def> = COPY %T1_Y<kill>; R600_TReg32:%vreg15
64B%vreg14<def> = COPY %T1_X<kill>; R600_TReg32:%vreg14
80B%vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18
96B%vreg19:sel_x<def,read-undef> = COPY %vreg14<kill>;
R600_Reg128:%vreg19 R600_TReg32:%vreg14
112B%vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2
128B%vreg21:sel_x<def,read-undef> = COPY %vreg18<kill>;
R600_Reg128:%vreg21 R600_Reg32:%vreg18
144B%vreg23<def> = COPY %vreg19<kill>; R600_Reg128:%vreg23,%vreg19
160B%vreg23:sel_y<def> = COPY %vreg15<kill>; R600_Reg128:%vreg23
R600_TReg32:%vreg15
176B%vreg24<def> = COPY %vreg21<kill>; R600_Reg128:%vreg24,%vreg21
192B%vreg24:sel_y<def> = COPY %vreg2; R600_Reg128:%vreg24
R600_Reg32:%vreg2
208B%vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25
224B%vreg26<def> = COPY %vreg23<kill>; R600_Reg128:%vreg26,%vreg23
240B%vreg26:sel_z<def> = COPY %vreg16<kill>; R600_Reg128:%vreg26
R600_TReg32:%vreg16
256B%vreg27<def> = COPY %vreg24<kill>; R600_Reg128:%vreg27,%vreg24
272B%vreg27:sel_z<def> = COPY %vreg25<kill>; R600_Reg128:%vreg27
R600_Reg32:%vreg25
288B%vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28
304B%vreg3<def> = COPY %vreg27<kill>; R600_Reg128:%vreg3,%vreg27
320B%vreg3:sel_w<def> = COPY %vreg28<kill>; R600_Reg128:%vreg3
R600_Reg32:%vreg28
336B%vreg1<def> = COPY %vreg26<kill>; R600_Reg128:%vreg1,%vreg26
352B%vreg1:sel_w<def> = COPY %vreg17<kill>; R600_Reg128:%vreg1
R600_TReg32:%vreg17
368B%vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13
384B%vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0
400B%vreg47<def> = COPY %vreg2<kill>; R600_Reg32:%vreg47,%vreg2
416B%vreg48<def> = COPY %vreg3<kill>; R600_Reg128:%vreg48,%vreg3
432B%vreg49<def> = COPY %vreg13<kill>; R600_Reg32:%vreg49,%vreg13
Successors according to CFG: BB#1
448BBB#1: derived from LLVM BB %25
Predecessors according to CFG: BB#0 BB#3
464B%vreg5<def> = COPY %vreg47<kill>; R600_Reg32:%vreg5,%vreg47
480B%vreg6<def> = COPY %vreg48<kill>; R600_Reg128:%vreg6,%vreg48
496B%vreg7<def> = COPY %vreg49<kill>; R600_Reg32:%vreg7,%vreg49
512B%vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0,
0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7
528B%vreg30<def> = COPY %vreg29<kill>; R600_Reg32:%vreg30,%vreg29
544B%PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16;
R600_Reg32:%vreg30
560BJUMP <BB#3>, pred:%PREDICATE_BIT
576BJUMP <BB#2>, pred:%noreg
Successors according to CFG: BB#2(4) BB#3(124)
592BBB#2: derived from LLVM BB %31
Predecessors according to CFG: BB#1
608B%vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39
R600_Reg128:%vreg6
624B%T2_X<def> = COPY %vreg39<kill>; R600_Reg32:%vreg39
640B%vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40
R600_Reg128:%vreg6
656B%T2_Y<def> = COPY %vreg40<kill>; R600_Reg32:%vreg40
672B%vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41
R600_Reg128:%vreg6
688B%T2_Z<def> = COPY %vreg41<kill>; R600_Reg32:%vreg41
704B%vreg42<def> = COPY %vreg6:sel_w<kill>; R600_Reg32:%vreg42
R600_Reg128:%vreg6
720B%T2_W<def> = COPY %vreg42<kill>; R600_Reg32:%vreg42
736B%vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43
R600_Reg128:%vreg1
752B%T1_X<def> = COPY %vreg43<kill>; R600_Reg32:%vreg43
768B%vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44
R600_Reg128:%vreg1
784B%T1_Y<def> = COPY %vreg44<kill>; R600_Reg32:%vreg44
800B%vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45
R600_Reg128:%vreg1
816B%T1_Z<def> = COPY %vreg45<kill>; R600_Reg32:%vreg45
832B%vreg46<def> = COPY %vreg1:sel_w<kill>; R600_Reg32:%vreg46
R600_Reg128:%vreg1
848B%T1_W<def> = COPY %vreg46<kill>; R600_Reg32:%vreg46
864BRETURN %T1_W<imp-use,kill>, %T1_Z<imp-use,kill>,
%T1_Y<imp-use,kill>, %T1_X<imp-use,kill>, %T2_W<imp-use,kill>,
%T2_Z<imp-use,kill>, %T2_Y<imp-use,kill>, %T2_X<imp-use,kill>
880BBB#3: derived from LLVM BB %41
Predecessors according to CFG: BB#1
896B%vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31
R600_Reg128:%vreg6
912B%vreg32:sel_x<def,read-undef> = COPY %vreg31<kill>;
R600_Reg128:%vreg32 R600_Reg32:%vreg31
928B%vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34
R600_Reg128:%vreg6
944B%vreg35<def> = COPY %vreg32<kill>; R600_Reg128:%vreg35,%vreg32
960B%vreg35:sel_y<def> = COPY %vreg34<kill>; R600_Reg128:%vreg35
R600_Reg32:%vreg34
976B%vreg36<def> = COPY %vreg35<kill>; R600_Reg128:%vreg36,%vreg35
992B%vreg36:sel_z<def> = COPY %vreg5<kill>; R600_Reg128:%vreg36
R600_Reg32:%vreg5
1008B%vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37
R600_Reg128:%vreg6
1024B%vreg10<def> = COPY %vreg36<kill>; R600_Reg128:%vreg10,%vreg36
1040B%vreg10:sel_w<def> = COPY %vreg37<kill>; R600_Reg128:%vreg10
R600_Reg32:%vreg37
1056B%vreg9<def> = COPY %vreg6:sel_z<kill>; R600_Reg32:%vreg9
R600_Reg128:%vreg6
1072B%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38
1088B%vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7<kill>, 0, 0, 0,
%vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0;
R600_Reg32:%vreg11,%vreg7,%vreg38
1104B%vreg47<def> = COPY %vreg9<kill>; R600_Reg32:%vreg47,%vreg9
1120B%vreg48<def> = COPY %vreg10<kill>; R600_Reg128:%vreg48,%vreg10
1136B%vreg49<def> = COPY %vreg11<kill>; R600_Reg32:%vreg49,%vreg11
1152BJUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Debug Variable Analysis ***:
# Machine code for function main: Post SSA
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
0BBB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
16B%vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17
32B%vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16
48B%vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15
64B%vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14
80B%vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18
96B%vreg19:sel_x<def,read-undef> = COPY %vreg14<kill>;
R600_Reg128:%vreg19 R600_TReg32:%vreg14
112B%vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2
128B%vreg21:sel_x<def,read-undef> = COPY %vreg18<kill>;
R600_Reg128:%vreg21 R600_Reg32:%vreg18
144B%vreg23<def> = COPY %vreg19<kill>; R600_Reg128:%vreg23,%vreg19
160B%vreg23:sel_y<def> = COPY %vreg15<kill>; R600_Reg128:%vreg23
R600_TReg32:%vreg15
176B%vreg24<def> = COPY %vreg21<kill>; R600_Reg128:%vreg24,%vreg21
192B%vreg24:sel_y<def> = COPY %vreg2; R600_Reg128:%vreg24
R600_Reg32:%vreg2
208B%vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25
224B%vreg26<def> = COPY %vreg23<kill>; R600_Reg128:%vreg26,%vreg23
240B%vreg26:sel_z<def> = COPY %vreg16<kill>; R600_Reg128:%vreg26
R600_TReg32:%vreg16
256B%vreg27<def> = COPY %vreg24<kill>; R600_Reg128:%vreg27,%vreg24
272B%vreg27:sel_z<def> = COPY %vreg25<kill>; R600_Reg128:%vreg27
R600_Reg32:%vreg25
288B%vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28
304B%vreg3<def> = COPY %vreg27<kill>; R600_Reg128:%vreg3,%vreg27
320B%vreg3:sel_w<def> = COPY %vreg28<kill>; R600_Reg128:%vreg3
R600_Reg32:%vreg28
336B%vreg1<def> = COPY %vreg26<kill>; R600_Reg128:%vreg1,%vreg26
352B%vreg1:sel_w<def> = COPY %vreg17<kill>; R600_Reg128:%vreg1
R600_TReg32:%vreg17
368B%vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13
384B%vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0
400B%vreg47<def> = COPY %vreg2<kill>; R600_Reg32:%vreg47,%vreg2
416B%vreg48<def> = COPY %vreg3<kill>; R600_Reg128:%vreg48,%vreg3
432B%vreg49<def> = COPY %vreg13<kill>; R600_Reg32:%vreg49,%vreg13
Successors according to CFG: BB#1
448BBB#1: derived from LLVM BB %25
Predecessors according to CFG: BB#0 BB#3
464B%vreg5<def> = COPY %vreg47<kill>; R600_Reg32:%vreg5,%vreg47
480B%vreg6<def> = COPY %vreg48<kill>; R600_Reg128:%vreg6,%vreg48
496B%vreg7<def> = COPY %vreg49<kill>; R600_Reg32:%vreg7,%vreg49
512B%vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0,
0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7
528B%vreg30<def> = COPY %vreg29<kill>; R600_Reg32:%vreg30,%vreg29
544B%PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16;
R600_Reg32:%vreg30
560BJUMP <BB#3>, pred:%PREDICATE_BIT
576BJUMP <BB#2>, pred:%noreg
Successors according to CFG: BB#2(4) BB#3(124)
592BBB#2: derived from LLVM BB %31
Predecessors according to CFG: BB#1
608B%vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39
R600_Reg128:%vreg6
624B%T2_X<def> = COPY %vreg39<kill>; R600_Reg32:%vreg39
640B%vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40
R600_Reg128:%vreg6
656B%T2_Y<def> = COPY %vreg40<kill>; R600_Reg32:%vreg40
672B%vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41
R600_Reg128:%vreg6
688B%T2_Z<def> = COPY %vreg41<kill>; R600_Reg32:%vreg41
704B%vreg42<def> = COPY %vreg6:sel_w<kill>; R600_Reg32:%vreg42
R600_Reg128:%vreg6
720B%T2_W<def> = COPY %vreg42<kill>; R600_Reg32:%vreg42
736B%vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43
R600_Reg128:%vreg1
752B%T1_X<def> = COPY %vreg43<kill>; R600_Reg32:%vreg43
768B%vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44
R600_Reg128:%vreg1
784B%T1_Y<def> = COPY %vreg44<kill>; R600_Reg32:%vreg44
800B%vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45
R600_Reg128:%vreg1
816B%T1_Z<def> = COPY %vreg45<kill>; R600_Reg32:%vreg45
832B%vreg46<def> = COPY %vreg1:sel_w<kill>; R600_Reg32:%vreg46
R600_Reg128:%vreg1
848B%T1_W<def> = COPY %vreg46<kill>; R600_Reg32:%vreg46
864BRETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>,
%T1_X<imp-use>, %T2_W<imp-use,kill>, %T2_Z<imp-use,kill>,
%T2_Y<imp-use,kill>, %T2_X<imp-use,kill>
880BBB#3: derived from LLVM BB %41
Predecessors according to CFG: BB#1
896B%vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31
R600_Reg128:%vreg6
912B%vreg32:sel_x<def,read-undef> = COPY %vreg31<kill>;
R600_Reg128:%vreg32 R600_Reg32:%vreg31
928B%vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34
R600_Reg128:%vreg6
944B%vreg35<def> = COPY %vreg32<kill>; R600_Reg128:%vreg35,%vreg32
960B%vreg35:sel_y<def> = COPY %vreg34<kill>; R600_Reg128:%vreg35
R600_Reg32:%vreg34
976B%vreg36<def> = COPY %vreg35<kill>; R600_Reg128:%vreg36,%vreg35
992B%vreg36:sel_z<def> = COPY %vreg5<kill>; R600_Reg128:%vreg36
R600_Reg32:%vreg5
1008B%vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37
R600_Reg128:%vreg6
1024B%vreg10<def> = COPY %vreg36<kill>; R600_Reg128:%vreg10,%vreg36
1040B%vreg10:sel_w<def> = COPY %vreg37<kill>; R600_Reg128:%vreg10
R600_Reg32:%vreg37
1056B%vreg9<def> = COPY %vreg6:sel_z<kill>; R600_Reg32:%vreg9
R600_Reg128:%vreg6
1072B%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38
1088B%vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7<kill>, 0, 0, 0,
%vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0;
R600_Reg32:%vreg11,%vreg7,%vreg38
1104B%vreg47<def> = COPY %vreg9<kill>; R600_Reg32:%vreg47,%vreg9
1120B%vreg48<def> = COPY %vreg10<kill>; R600_Reg128:%vreg48,%vreg10
1136B%vreg49<def> = COPY %vreg11<kill>; R600_Reg32:%vreg49,%vreg11
1152BJUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Simple Register Coalescing ***:
# Machine code for function main: Post SSA
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
0BBB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
16B%vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17
32B%vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16
48B%vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15
64B%vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14
80B%vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18
96B%vreg19:sel_x<def,read-undef> = COPY %vreg14<kill>;
R600_Reg128:%vreg19 R600_TReg32:%vreg14
112B%vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2
128B%vreg21:sel_x<def,read-undef> = COPY %vreg18<kill>;
R600_Reg128:%vreg21 R600_Reg32:%vreg18
144B%vreg23<def> = COPY %vreg19<kill>; R600_Reg128:%vreg23,%vreg19
160B%vreg23:sel_y<def> = COPY %vreg15<kill>; R600_Reg128:%vreg23
R600_TReg32:%vreg15
176B%vreg24<def> = COPY %vreg21<kill>; R600_Reg128:%vreg24,%vreg21
192B%vreg24:sel_y<def> = COPY %vreg2; R600_Reg128:%vreg24
R600_Reg32:%vreg2
208B%vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25
224B%vreg26<def> = COPY %vreg23<kill>; R600_Reg128:%vreg26,%vreg23
240B%vreg26:sel_z<def> = COPY %vreg16<kill>; R600_Reg128:%vreg26
R600_TReg32:%vreg16
256B%vreg27<def> = COPY %vreg24<kill>; R600_Reg128:%vreg27,%vreg24
272B%vreg27:sel_z<def> = COPY %vreg25<kill>; R600_Reg128:%vreg27
R600_Reg32:%vreg25
288B%vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28
304B%vreg3<def> = COPY %vreg27<kill>; R600_Reg128:%vreg3,%vreg27
320B%vreg3:sel_w<def> = COPY %vreg28<kill>; R600_Reg128:%vreg3
R600_Reg32:%vreg28
336B%vreg1<def> = COPY %vreg26<kill>; R600_Reg128:%vreg1,%vreg26
352B%vreg1:sel_w<def> = COPY %vreg17<kill>; R600_Reg128:%vreg1
R600_TReg32:%vreg17
368B%vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13
384B%vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0
400B%vreg47<def> = COPY %vreg2<kill>; R600_Reg32:%vreg47,%vreg2
416B%vreg48<def> = COPY %vreg3<kill>; R600_Reg128:%vreg48,%vreg3
432B%vreg49<def> = COPY %vreg13<kill>; R600_Reg32:%vreg49,%vreg13
Successors according to CFG: BB#1
448BBB#1: derived from LLVM BB %25
Predecessors according to CFG: BB#0 BB#3
464B%vreg5<def> = COPY %vreg47<kill>; R600_Reg32:%vreg5,%vreg47
480B%vreg6<def> = COPY %vreg48<kill>; R600_Reg128:%vreg6,%vreg48
496B%vreg7<def> = COPY %vreg49<kill>; R600_Reg32:%vreg7,%vreg49
512B%vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0,
0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7
528B%vreg30<def> = COPY %vreg29<kill>; R600_Reg32:%vreg30,%vreg29
544B%PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16;
R600_Reg32:%vreg30
560BJUMP <BB#3>, pred:%PREDICATE_BIT
576BJUMP <BB#2>, pred:%noreg
Successors according to CFG: BB#2(4) BB#3(124)
592BBB#2: derived from LLVM BB %31
Predecessors according to CFG: BB#1
608B%vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39
R600_Reg128:%vreg6
624B%T2_X<def> = COPY %vreg39<kill>; R600_Reg32:%vreg39
640B%vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40
R600_Reg128:%vreg6
656B%T2_Y<def> = COPY %vreg40<kill>; R600_Reg32:%vreg40
672B%vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41
R600_Reg128:%vreg6
688B%T2_Z<def> = COPY %vreg41<kill>; R600_Reg32:%vreg41
704B%vreg42<def> = COPY %vreg6:sel_w<kill>; R600_Reg32:%vreg42
R600_Reg128:%vreg6
720B%T2_W<def> = COPY %vreg42<kill>; R600_Reg32:%vreg42
736B%vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43
R600_Reg128:%vreg1
752B%T1_X<def> = COPY %vreg43<kill>; R600_Reg32:%vreg43
768B%vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44
R600_Reg128:%vreg1
784B%T1_Y<def> = COPY %vreg44<kill>; R600_Reg32:%vreg44
800B%vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45
R600_Reg128:%vreg1
816B%T1_Z<def> = COPY %vreg45<kill>; R600_Reg32:%vreg45
832B%vreg46<def> = COPY %vreg1:sel_w<kill>; R600_Reg32:%vreg46
R600_Reg128:%vreg1
848B%T1_W<def> = COPY %vreg46<kill>; R600_Reg32:%vreg46
864BRETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>,
%T1_X<imp-use>, %T2_W<imp-use,kill>, %T2_Z<imp-use,kill>,
%T2_Y<imp-use,kill>, %T2_X<imp-use,kill>
880BBB#3: derived from LLVM BB %41
Predecessors according to CFG: BB#1
896B%vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31
R600_Reg128:%vreg6
912B%vreg32:sel_x<def,read-undef> = COPY %vreg31<kill>;
R600_Reg128:%vreg32 R600_Reg32:%vreg31
928B%vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34
R600_Reg128:%vreg6
944B%vreg35<def> = COPY %vreg32<kill>; R600_Reg128:%vreg35,%vreg32
960B%vreg35:sel_y<def> = COPY %vreg34<kill>; R600_Reg128:%vreg35
R600_Reg32:%vreg34
976B%vreg36<def> = COPY %vreg35<kill>; R600_Reg128:%vreg36,%vreg35
992B%vreg36:sel_z<def> = COPY %vreg5<kill>; R600_Reg128:%vreg36
R600_Reg32:%vreg5
1008B%vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37
R600_Reg128:%vreg6
1024B%vreg10<def> = COPY %vreg36<kill>; R600_Reg128:%vreg10,%vreg36
1040B%vreg10:sel_w<def> = COPY %vreg37<kill>; R600_Reg128:%vreg10
R600_Reg32:%vreg37
1056B%vreg9<def> = COPY %vreg6:sel_z<kill>; R600_Reg32:%vreg9
R600_Reg128:%vreg6
1072B%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38
1088B%vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7<kill>, 0, 0, 0,
%vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0;
R600_Reg32:%vreg11,%vreg7,%vreg38
1104B%vreg47<def> = COPY %vreg9<kill>; R600_Reg32:%vreg47,%vreg9
1120B%vreg48<def> = COPY %vreg10<kill>; R600_Reg128:%vreg48,%vreg10
1136B%vreg49<def> = COPY %vreg11<kill>; R600_Reg32:%vreg49,%vreg11
1152BJUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Live Stack Slot Analysis ***:
# Machine code for function main: Post SSA
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
0BBB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
16B%vreg1:sel_w<def,read-undef> = COPY %T1_W; R600_Reg128:%vreg1
32B%vreg1:sel_z<def> = COPY %T1_Z; R600_Reg128:%vreg1
48B%vreg1:sel_y<def> = COPY %T1_Y; R600_Reg128:%vreg1
64B%vreg1:sel_x<def> = COPY %T1_X; R600_Reg128:%vreg1
128B%vreg27:sel_x<def,read-undef> = COPY %C1_X; R600_Reg128:%vreg27
192B%vreg27:sel_y<def> = COPY %C1_Y; R600_Reg128:%vreg27
272B%vreg27:sel_z<def> = COPY %C1_Z; R600_Reg128:%vreg27
320B%vreg27:sel_w<def> = COPY %C1_W; R600_Reg128:%vreg27
368B%vreg49<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg49
Successors according to CFG: BB#1
448BBB#1: derived from LLVM BB %25
Predecessors according to CFG: BB#0 BB#3
512B%vreg30<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %vreg49, 0,
0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg30,%vreg49
544B%PREDICATE_BIT<def> = PRED_X %vreg30, 152, 16; R600_Reg32:%vreg30
560BJUMP <BB#3>, pred:%PREDICATE_BIT
576BJUMP <BB#2>, pred:%noreg
Successors according to CFG: BB#2(4) BB#3(124)
592BBB#2: derived from LLVM BB %31
Predecessors according to CFG: BB#1
624B%T2_X<def> = COPY %vreg27:sel_x; R600_Reg128:%vreg27
656B%T2_Y<def> = COPY %vreg27:sel_y; R600_Reg128:%vreg27
688B%T2_Z<def> = COPY %vreg27:sel_z; R600_Reg128:%vreg27
720B%T2_W<def> = COPY %vreg27:sel_w; R600_Reg128:%vreg27
752B%T1_X<def> = COPY %vreg1:sel_x; R600_Reg128:%vreg1
784B%T1_Y<def> = COPY %vreg1:sel_y; R600_Reg128:%vreg1
816B%T1_Z<def> = COPY %vreg1:sel_z; R600_Reg128:%vreg1
848B%T1_W<def> = COPY %vreg1:sel_w; R600_Reg128:%vreg1
864BRETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>,
%T1_X<imp-use>, %T2_W<imp-use,kill>, %T2_Z<imp-use,kill>,
%T2_Y<imp-use,kill>, %T2_X<imp-use,kill>
880BBB#3: derived from LLVM BB %41
Predecessors according to CFG: BB#1
1072B%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38
1088B%vreg49<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg49, 0, 0, 0,
%vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0;
R600_Reg32:%vreg49,%vreg38
1152BJUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Calculate spill weights ***:
# Machine code for function main: Post SSA
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
0BBB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
16B%vreg1:sel_w<def,read-undef> = COPY %T1_W; R600_Reg128:%vreg1
32B%vreg1:sel_z<def> = COPY %T1_Z; R600_Reg128:%vreg1
48B%vreg1:sel_y<def> = COPY %T1_Y; R600_Reg128:%vreg1
64B%vreg1:sel_x<def> = COPY %T1_X; R600_Reg128:%vreg1
128B%vreg27:sel_x<def,read-undef> = COPY %C1_X; R600_Reg128:%vreg27
192B%vreg27:sel_y<def> = COPY %C1_Y; R600_Reg128:%vreg27
272B%vreg27:sel_z<def> = COPY %C1_Z; R600_Reg128:%vreg27
320B%vreg27:sel_w<def> = COPY %C1_W; R600_Reg128:%vreg27
368B%vreg49<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg49
Successors according to CFG: BB#1
448BBB#1: derived from LLVM BB %25
Predecessors according to CFG: BB#0 BB#3
512B%vreg30<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %vreg49, 0,
0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg30,%vreg49
544B%PREDICATE_BIT<def> = PRED_X %vreg30, 152, 16; R600_Reg32:%vreg30
560BJUMP <BB#3>, pred:%PREDICATE_BIT
576BJUMP <BB#2>, pred:%noreg
Successors according to CFG: BB#2(4) BB#3(124)
592BBB#2: derived from LLVM BB %31
Predecessors according to CFG: BB#1
624B%T2_X<def> = COPY %vreg27:sel_x; R600_Reg128:%vreg27
656B%T2_Y<def> = COPY %vreg27:sel_y; R600_Reg128:%vreg27
688B%T2_Z<def> = COPY %vreg27:sel_z; R600_Reg128:%vreg27
720B%T2_W<def> = COPY %vreg27:sel_w; R600_Reg128:%vreg27
752B%T1_X<def> = COPY %vreg1:sel_x; R600_Reg128:%vreg1
784B%T1_Y<def> = COPY %vreg1:sel_y; R600_Reg128:%vreg1
816B%T1_Z<def> = COPY %vreg1:sel_z; R600_Reg128:%vreg1
848B%T1_W<def> = COPY %vreg1:sel_w; R600_Reg128:%vreg1
864BRETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>,
%T1_X<imp-use>, %T2_W<imp-use,kill>, %T2_Z<imp-use,kill>,
%T2_Y<imp-use,kill>, %T2_X<imp-use,kill>
880BBB#3: derived from LLVM BB %41
Predecessors according to CFG: BB#1
1072B%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38
1088B%vreg49<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg49, 0, 0, 0,
%vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0;
R600_Reg32:%vreg49,%vreg38
1152BJUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Virtual Register Map ***:
# Machine code for function main: Post SSA
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
0BBB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
16B%vreg1:sel_w<def,read-undef> = COPY %T1_W; R600_Reg128:%vreg1
32B%vreg1:sel_z<def> = COPY %T1_Z; R600_Reg128:%vreg1
48B%vreg1:sel_y<def> = COPY %T1_Y; R600_Reg128:%vreg1
64B%vreg1:sel_x<def> = COPY %T1_X; R600_Reg128:%vreg1
128B%vreg27:sel_x<def,read-undef> = COPY %C1_X; R600_Reg128:%vreg27
192B%vreg27:sel_y<def> = COPY %C1_Y; R600_Reg128:%vreg27
272B%vreg27:sel_z<def> = COPY %C1_Z; R600_Reg128:%vreg27
320B%vreg27:sel_w<def> = COPY %C1_W; R600_Reg128:%vreg27
368B%vreg49<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg49
Successors according to CFG: BB#1
448BBB#1: derived from LLVM BB %25
Predecessors according to CFG: BB#0 BB#3
512B%vreg30<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %vreg49, 0,
0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg30,%vreg49
544B%PREDICATE_BIT<def> = PRED_X %vreg30, 152, 16; R600_Reg32:%vreg30
560BJUMP <BB#3>, pred:%PREDICATE_BIT
576BJUMP <BB#2>, pred:%noreg
Successors according to CFG: BB#2(4) BB#3(124)
592BBB#2: derived from LLVM BB %31
Predecessors according to CFG: BB#1
624B%T2_X<def> = COPY %vreg27:sel_x; R600_Reg128:%vreg27
656B%T2_Y<def> = COPY %vreg27:sel_y; R600_Reg128:%vreg27
688B%T2_Z<def> = COPY %vreg27:sel_z; R600_Reg128:%vreg27
720B%T2_W<def> = COPY %vreg27:sel_w; R600_Reg128:%vreg27
752B%T1_X<def> = COPY %vreg1:sel_x; R600_Reg128:%vreg1
784B%T1_Y<def> = COPY %vreg1:sel_y; R600_Reg128:%vreg1
816B%T1_Z<def> = COPY %vreg1:sel_z; R600_Reg128:%vreg1
848B%T1_W<def> = COPY %vreg1:sel_w; R600_Reg128:%vreg1
864BRETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>,
%T1_X<imp-use>, %T2_W<imp-use,kill>, %T2_Z<imp-use,kill>,
%T2_Y<imp-use,kill>, %T2_X<imp-use,kill>
880BBB#3: derived from LLVM BB %41
Predecessors according to CFG: BB#1
1072B%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38
1088B%vreg49<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg49, 0, 0, 0,
%vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0;
R600_Reg32:%vreg49,%vreg38
1152BJUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Live Register Matrix ***:
# Machine code for function main: Post SSA
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
0BBB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
16B%vreg1:sel_w<def,read-undef> = COPY %T1_W; R600_Reg128:%vreg1
32B%vreg1:sel_z<def> = COPY %T1_Z; R600_Reg128:%vreg1
48B%vreg1:sel_y<def> = COPY %T1_Y; R600_Reg128:%vreg1
64B%vreg1:sel_x<def> = COPY %T1_X; R600_Reg128:%vreg1
128B%vreg27:sel_x<def,read-undef> = COPY %C1_X; R600_Reg128:%vreg27
192B%vreg27:sel_y<def> = COPY %C1_Y; R600_Reg128:%vreg27
272B%vreg27:sel_z<def> = COPY %C1_Z; R600_Reg128:%vreg27
320B%vreg27:sel_w<def> = COPY %C1_W; R600_Reg128:%vreg27
368B%vreg49<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg49
Successors according to CFG: BB#1
448BBB#1: derived from LLVM BB %25
Predecessors according to CFG: BB#0 BB#3
512B%vreg30<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %vreg49, 0,
0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg30,%vreg49
544B%PREDICATE_BIT<def> = PRED_X %vreg30, 152, 16; R600_Reg32:%vreg30
560BJUMP <BB#3>, pred:%PREDICATE_BIT
576BJUMP <BB#2>, pred:%noreg
Successors according to CFG: BB#2(4) BB#3(124)
592BBB#2: derived from LLVM BB %31
Predecessors according to CFG: BB#1
624B%T2_X<def> = COPY %vreg27:sel_x; R600_Reg128:%vreg27
656B%T2_Y<def> = COPY %vreg27:sel_y; R600_Reg128:%vreg27
688B%T2_Z<def> = COPY %vreg27:sel_z; R600_Reg128:%vreg27
720B%T2_W<def> = COPY %vreg27:sel_w; R600_Reg128:%vreg27
752B%T1_X<def> = COPY %vreg1:sel_x; R600_Reg128:%vreg1
784B%T1_Y<def> = COPY %vreg1:sel_y; R600_Reg128:%vreg1
816B%T1_Z<def> = COPY %vreg1:sel_z; R600_Reg128:%vreg1
848B%T1_W<def> = COPY %vreg1:sel_w; R600_Reg128:%vreg1
864BRETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>,
%T1_X<imp-use>, %T2_W<imp-use,kill>, %T2_Z<imp-use,kill>,
%T2_Y<imp-use,kill>, %T2_X<imp-use,kill>
880BBB#3: derived from LLVM BB %41
Predecessors according to CFG: BB#1
1072B%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38
1088B%vreg49<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg49, 0, 0, 0,
%vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0;
R600_Reg32:%vreg49,%vreg38
1152BJUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Virtual Register Rewriter ***:
# Machine code for function main: Post SSA
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
0BBB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
16B%vreg1:sel_w<def,read-undef> = COPY %T1_W; R600_Reg128:%vreg1
32B%vreg1:sel_z<def> = COPY %T1_Z; R600_Reg128:%vreg1
48B%vreg1:sel_y<def> = COPY %T1_Y; R600_Reg128:%vreg1
64B%vreg1:sel_x<def> = COPY %T1_X; R600_Reg128:%vreg1
128B%vreg27:sel_x<def,read-undef> = COPY %C1_X; R600_Reg128:%vreg27
192B%vreg27:sel_y<def> = COPY %C1_Y; R600_Reg128:%vreg27
272B%vreg27:sel_z<def> = COPY %C1_Z; R600_Reg128:%vreg27
320B%vreg27:sel_w<def> = COPY %C1_W; R600_Reg128:%vreg27
368B%vreg49<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg49
Successors according to CFG: BB#1
448BBB#1: derived from LLVM BB %25
Predecessors according to CFG: BB#0 BB#3
512B%vreg30<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %vreg49, 0,
0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg30,%vreg49
544B%PREDICATE_BIT<def> = PRED_X %vreg30, 152, 16; R600_Reg32:%vreg30
560BJUMP <BB#3>, pred:%PREDICATE_BIT
576BJUMP <BB#2>, pred:%noreg
Successors according to CFG: BB#2(4) BB#3(124)
592BBB#2: derived from LLVM BB %31
Predecessors according to CFG: BB#1
624B%T2_X<def> = COPY %vreg27:sel_x; R600_Reg128:%vreg27
656B%T2_Y<def> = COPY %vreg27:sel_y; R600_Reg128:%vreg27
688B%T2_Z<def> = COPY %vreg27:sel_z; R600_Reg128:%vreg27
720B%T2_W<def> = COPY %vreg27:sel_w; R600_Reg128:%vreg27
752B%T1_X<def> = COPY %vreg1:sel_x; R600_Reg128:%vreg1
784B%T1_Y<def> = COPY %vreg1:sel_y; R600_Reg128:%vreg1
816B%T1_Z<def> = COPY %vreg1:sel_z; R600_Reg128:%vreg1
848B%T1_W<def> = COPY %vreg1:sel_w; R600_Reg128:%vreg1
864BRETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>,
%T1_X<imp-use>, %T2_W<imp-use>, %T2_Z<imp-use>,
%T2_Y<imp-use>, %T2_X<imp-use>
880BBB#3: derived from LLVM BB %41
Predecessors according to CFG: BB#1
1072B%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38
1088B%vreg49<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg49, 0, 0, 0,
%vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0;
R600_Reg32:%vreg49,%vreg38
1152BJUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Stack Slot Coloring ***:
# Machine code for function main: Post SSA
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
0BBB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
16B%T1_W<def> = KILL %T1_W, %T1_XYZW<imp-def>
32B%T1_Z<def> = KILL %T1_Z, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
48B%T1_Y<def> = KILL %T1_Y, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
64B%T1_X<def> = KILL %T1_X, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
128B%T2_X<def> = COPY %C1_X, %T2_XYZW<imp-def>
192B%T2_Y<def> = COPY %C1_Y, %T2_XYZW<imp-use,kill>,
%T2_XYZW<imp-def>
272B%T2_Z<def> = COPY %C1_Z, %T2_XYZW<imp-use,kill>,
%T2_XYZW<imp-def>
320B%T2_W<def> = COPY %C1_W, %T2_XYZW<imp-use,kill>,
%T2_XYZW<imp-def>
368B%T3_X<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0
Successors according to CFG: BB#1
448BBB#1: derived from LLVM BB %25
Live Ins: %T1_XYZW %T2_XYZW %T3_X
Predecessors according to CFG: BB#0 BB#3
512B%T3_Y<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %T3_X, 0, 0,
0, 1, pred:%PRED_SEL_OFF, 0
544B%PREDICATE_BIT<def> = PRED_X %T3_Y<kill>, 152, 16
560BJUMP <BB#3>, pred:%PREDICATE_BIT
576BJUMP <BB#2>, pred:%noreg
Successors according to CFG: BB#2(4) BB#3(124)
592BBB#2: derived from LLVM BB %31
Live Ins: %T1_XYZW %T2_XYZW
Predecessors according to CFG: BB#1
864BRETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>,
%T1_X<imp-use>, %T2_W<imp-use>, %T2_Z<imp-use>,
%T2_Y<imp-use>, %T2_X<imp-use>
880BBB#3: derived from LLVM BB %41
Live Ins: %T1_XYZW %T2_XYZW %T3_X
Predecessors according to CFG: BB#1
1072B%T3_Y<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1
1088B%T3_X<def> = ADD_INT 0, 0, 1, 0, 0, 0, %T3_X<kill>, 0, 0, 0,
%T3_Y<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0
1152BJUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Machine Loop Invariant Code Motion ***:
# Machine code for function main: Post SSA
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
BB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
%T1_W<def> = KILL %T1_W, %T1_XYZW<imp-def>
%T1_Z<def> = KILL %T1_Z, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
%T1_Y<def> = KILL %T1_Y, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
%T1_X<def> = KILL %T1_X, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
%T2_X<def> = COPY %C1_X, %T2_XYZW<imp-def>
%T2_Y<def> = COPY %C1_Y, %T2_XYZW<imp-use,kill>,
%T2_XYZW<imp-def>
%T2_Z<def> = COPY %C1_Z, %T2_XYZW<imp-use,kill>,
%T2_XYZW<imp-def>
%T2_W<def> = COPY %C1_W, %T2_XYZW<imp-use,kill>,
%T2_XYZW<imp-def>
%T3_X<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0
Successors according to CFG: BB#1
BB#1: derived from LLVM BB %25
Live Ins: %T1_XYZW %T2_XYZW %T3_X
Predecessors according to CFG: BB#0 BB#3
%T3_Y<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %T3_X, 0, 0, 0,
1, pred:%PRED_SEL_OFF, 0
%PREDICATE_BIT<def> = PRED_X %T3_Y<kill>, 152, 16
JUMP <BB#3>, pred:%PREDICATE_BIT
JUMP <BB#2>, pred:%noreg
Successors according to CFG: BB#2(4) BB#3(124)
BB#2: derived from LLVM BB %31
Live Ins: %T1_XYZW %T2_XYZW
Predecessors according to CFG: BB#1
RETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>,
%T1_X<imp-use>, %T2_W<imp-use>, %T2_Z<imp-use>,
%T2_Y<imp-use>, %T2_X<imp-use>
BB#3: derived from LLVM BB %41
Live Ins: %T1_XYZW %T2_XYZW %T3_X
Predecessors according to CFG: BB#1
%T3_Y<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1
%T3_X<def> = ADD_INT 0, 0, 1, 0, 0, 0, %T3_X<kill>, 0, 0, 0,
%T3_Y<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0
JUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Prologue/Epilogue Insertion & Frame Finalization ***:
# Machine code for function main: Post SSA
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
BB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
%T1_W<def> = KILL %T1_W, %T1_XYZW<imp-def>
%T1_Z<def> = KILL %T1_Z, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
%T1_Y<def> = KILL %T1_Y, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
%T1_X<def> = KILL %T1_X, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
%T2_X<def> = COPY %C1_X, %T2_XYZW<imp-def>
%T2_Y<def> = COPY %C1_Y, %T2_XYZW<imp-use,kill>,
%T2_XYZW<imp-def>
%T2_Z<def> = COPY %C1_Z, %T2_XYZW<imp-use,kill>,
%T2_XYZW<imp-def>
%T2_W<def> = COPY %C1_W, %T2_XYZW<imp-use,kill>,
%T2_XYZW<imp-def>
%T3_X<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0
Successors according to CFG: BB#1
BB#1: derived from LLVM BB %25
Live Ins: %T1_XYZW %T2_XYZW %T3_X
Predecessors according to CFG: BB#0 BB#3
%T3_Y<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %T3_X, 0, 0, 0,
1, pred:%PRED_SEL_OFF, 0
%PREDICATE_BIT<def> = PRED_X %T3_Y<kill>, 152, 16
JUMP <BB#3>, pred:%PREDICATE_BIT
JUMP <BB#2>, pred:%noreg
Successors according to CFG: BB#2(4) BB#3(124)
BB#2: derived from LLVM BB %31
Live Ins: %T1_XYZW %T2_XYZW
Predecessors according to CFG: BB#1
RETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>,
%T1_X<imp-use>, %T2_W<imp-use>, %T2_Z<imp-use>,
%T2_Y<imp-use>, %T2_X<imp-use>
BB#3: derived from LLVM BB %41
Live Ins: %T1_XYZW %T2_XYZW %T3_X
Predecessors according to CFG: BB#1
%T3_Y<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1
%T3_X<def> = ADD_INT 0, 0, 1, 0, 0, 0, %T3_X<kill>, 0, 0, 0,
%T3_Y<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0
JUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Control Flow Optimizer ***:
# Machine code for function main: Post SSA
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
BB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
%T1_W<def> = KILL %T1_W, %T1_XYZW<imp-def>
%T1_Z<def> = KILL %T1_Z, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
%T1_Y<def> = KILL %T1_Y, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
%T1_X<def> = KILL %T1_X, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
%T2_X<def> = COPY %C1_X, %T2_XYZW<imp-def>
%T2_Y<def> = COPY %C1_Y, %T2_XYZW<imp-use,kill>,
%T2_XYZW<imp-def>
%T2_Z<def> = COPY %C1_Z, %T2_XYZW<imp-use,kill>,
%T2_XYZW<imp-def>
%T2_W<def> = COPY %C1_W, %T2_XYZW<imp-use,kill>,
%T2_XYZW<imp-def>
%T3_X<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0
Successors according to CFG: BB#1
BB#1: derived from LLVM BB %25
Live Ins: %T1_XYZW %T2_XYZW %T3_X
Predecessors according to CFG: BB#0 BB#3
%T3_Y<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %T3_X, 0, 0, 0,
1, pred:%PRED_SEL_OFF, 0
%PREDICATE_BIT<def> = PRED_X %T3_Y<kill>, 152, 16
JUMP <BB#3>, pred:%PREDICATE_BIT
JUMP <BB#2>, pred:%noreg
Successors according to CFG: BB#2(4) BB#3(124)
BB#2: derived from LLVM BB %31
Live Ins: %T1_XYZW %T2_XYZW
Predecessors according to CFG: BB#1
RETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>,
%T1_X<imp-use>, %T2_W<imp-use>, %T2_Z<imp-use>,
%T2_Y<imp-use>, %T2_X<imp-use>
BB#3: derived from LLVM BB %41
Live Ins: %T1_XYZW %T2_XYZW %T3_X
Predecessors according to CFG: BB#1
%T3_Y<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1
%T3_X<def> = ADD_INT 0, 0, 1, 0, 0, 0, %T3_X<kill>, 0, 0, 0,
%T3_Y<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0
JUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Tail Duplication ***:
# Machine code for function main: Post SSA, not tracking liveness
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
BB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
%T1_W<def> = KILL %T1_W, %T1_XYZW<imp-def>
%T1_Z<def> = KILL %T1_Z, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
%T1_Y<def> = KILL %T1_Y, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
%T1_X<def> = KILL %T1_X, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
%T2_X<def> = COPY %C1_X, %T2_XYZW<imp-def>
%T2_Y<def> = COPY %C1_Y, %T2_XYZW<imp-use,kill>,
%T2_XYZW<imp-def>
%T2_Z<def> = COPY %C1_Z, %T2_XYZW<imp-use,kill>,
%T2_XYZW<imp-def>
%T2_W<def> = COPY %C1_W, %T2_XYZW<imp-use,kill>,
%T2_XYZW<imp-def>
%T3_X<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0
Successors according to CFG: BB#1
BB#1: derived from LLVM BB %25
Live Ins: %T1_XYZW %T2_XYZW %T3_X
Predecessors according to CFG: BB#0 BB#3
%T3_Y<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %T3_X, 0, 0, 0,
1, pred:%PRED_SEL_OFF, 0
%PREDICATE_BIT<def> = PRED_X %T3_Y<kill>, 152, 16
JUMP <BB#3>, pred:%PREDICATE_BIT<kill>
Successors according to CFG: BB#2(4) BB#3(124)
BB#2: derived from LLVM BB %31
Live Ins: %T1_XYZW %T2_XYZW
Predecessors according to CFG: BB#1
RETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>,
%T1_X<imp-use>, %T2_W<imp-use>, %T2_Z<imp-use>,
%T2_Y<imp-use>, %T2_X<imp-use>
BB#3: derived from LLVM BB %41
Live Ins: %T1_XYZW %T2_XYZW %T3_X
Predecessors according to CFG: BB#1
%T3_Y<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1
%T3_X<def> = ADD_INT 0, 0, 1, 0, 0, 0, %T3_X<kill>, 0, 0, 0,
%T3_Y<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0
JUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Machine Copy Propagation Pass ***:
# Machine code for function main: Post SSA, not tracking liveness
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
BB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
%T1_W<def> = KILL %T1_W, %T1_XYZW<imp-def>
%T1_Z<def> = KILL %T1_Z, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
%T1_Y<def> = KILL %T1_Y, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
%T1_X<def> = KILL %T1_X, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
%T2_X<def> = COPY %C1_X, %T2_XYZW<imp-def>
%T2_Y<def> = COPY %C1_Y, %T2_XYZW<imp-use,kill>,
%T2_XYZW<imp-def>
%T2_Z<def> = COPY %C1_Z, %T2_XYZW<imp-use,kill>,
%T2_XYZW<imp-def>
%T2_W<def> = COPY %C1_W, %T2_XYZW<imp-use,kill>,
%T2_XYZW<imp-def>
%T3_X<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0
Successors according to CFG: BB#1
BB#1: derived from LLVM BB %25
Live Ins: %T1_XYZW %T2_XYZW %T3_X
Predecessors according to CFG: BB#0 BB#3
%T3_Y<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %T3_X, 0, 0, 0,
1, pred:%PRED_SEL_OFF, 0
%PREDICATE_BIT<def> = PRED_X %T3_Y<kill>, 152, 16
JUMP <BB#3>, pred:%PREDICATE_BIT<kill>
Successors according to CFG: BB#2(4) BB#3(124)
BB#2: derived from LLVM BB %31
Live Ins: %T1_XYZW %T2_XYZW
Predecessors according to CFG: BB#1
RETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>,
%T1_X<imp-use>, %T2_W<imp-use>, %T2_Z<imp-use>,
%T2_Y<imp-use>, %T2_X<imp-use>
BB#3: derived from LLVM BB %41
Live Ins: %T1_XYZW %T2_XYZW %T3_X
Predecessors according to CFG: BB#1
%T3_Y<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1
%T3_X<def> = ADD_INT 0, 0, 1, 0, 0, 0, %T3_X<kill>, 0, 0, 0,
%T3_Y<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0
JUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Post-RA pseudo instruction expansion pass ***:
# Machine code for function main: Post SSA, not tracking liveness
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
BB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
%T1_W<def> = KILL %T1_W, %T1_XYZW<imp-def>
%T1_Z<def> = KILL %T1_Z, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
%T1_Y<def> = KILL %T1_Y, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
%T1_X<def> = KILL %T1_X, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
%T2_X<def> = COPY %C1_X, %T2_XYZW<imp-def>
%T2_Y<def> = COPY %C1_Y, %T2_XYZW<imp-use,kill>,
%T2_XYZW<imp-def>
%T2_Z<def> = COPY %C1_Z, %T2_XYZW<imp-use,kill>,
%T2_XYZW<imp-def>
%T2_W<def> = COPY %C1_W, %T2_XYZW<imp-use,kill>,
%T2_XYZW<imp-def>
%T3_X<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0
Successors according to CFG: BB#1
BB#1: derived from LLVM BB %25
Live Ins: %T1_XYZW %T2_XYZW %T3_X
Predecessors according to CFG: BB#0 BB#3
%T3_Y<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %T3_X, 0, 0, 0,
1, pred:%PRED_SEL_OFF, 0
%PREDICATE_BIT<def> = PRED_X %T3_Y<kill>, 152, 16
JUMP <BB#3>, pred:%PREDICATE_BIT<kill>
Successors according to CFG: BB#2(4) BB#3(124)
BB#2: derived from LLVM BB %31
Live Ins: %T1_XYZW %T2_XYZW
Predecessors according to CFG: BB#1
RETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>,
%T1_X<imp-use>, %T2_W<imp-use>, %T2_Z<imp-use>,
%T2_Y<imp-use>, %T2_X<imp-use>
BB#3: derived from LLVM BB %41
Live Ins: %T1_XYZW %T2_XYZW %T3_X
Predecessors according to CFG: BB#1
%T3_Y<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1
%T3_X<def> = ADD_INT 0, 0, 1, 0, 0, 0, %T3_X<kill>, 0, 0, 0,
%T3_Y<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0
JUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before If Converter ***:
# Machine code for function main: Post SSA, not tracking liveness
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
BB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
%T1_W<def> = KILL %T1_W, %T1_XYZW<imp-def>
%T1_Z<def> = KILL %T1_Z, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
%T1_Y<def> = KILL %T1_Y, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
%T1_X<def> = KILL %T1_X, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
%T2_X<def> = MOV 1, 0, 0, 0, %C1_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0,
%T2_XYZW<imp-def>
%T2_Y<def> = MOV 1, 0, 0, 0, %C1_Y, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0,
%T2_XYZW<imp-def>
%T2_Z<def> = MOV 1, 0, 0, 0, %C1_Z, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0,
%T2_XYZW<imp-def>
%T2_W<def> = MOV 1, 0, 0, 0, %C1_W, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0,
%T2_XYZW<imp-def>
%T3_X<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0
Successors according to CFG: BB#1
BB#1: derived from LLVM BB %25
Live Ins: %T1_XYZW %T2_XYZW %T3_X
Predecessors according to CFG: BB#0 BB#3
%T3_Y<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %T3_X, 0, 0, 0,
1, pred:%PRED_SEL_OFF, 0
%PREDICATE_BIT<def> = PRED_X %T3_Y<kill>, 152, 16
JUMP <BB#3>, pred:%PREDICATE_BIT<kill>
Successors according to CFG: BB#2(4) BB#3(124)
BB#2: derived from LLVM BB %31
Live Ins: %T1_XYZW %T2_XYZW
Predecessors according to CFG: BB#1
RETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>,
%T1_X<imp-use>, %T2_W<imp-use>, %T2_Z<imp-use>,
%T2_Y<imp-use>, %T2_X<imp-use>
BB#3: derived from LLVM BB %41
Live Ins: %T1_XYZW %T2_XYZW %T3_X
Predecessors according to CFG: BB#1
%T3_Y<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1
%T3_X<def> = ADD_INT 0, 0, 1, 0, 0, 0, %T3_X<kill>, 0, 0, 0,
%T3_Y<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0
JUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Post RA top-down list latency scheduler ***:
# Machine code for function main: Post SSA, not tracking liveness
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
BB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
%T1_W<def> = KILL %T1_W, %T1_XYZW<imp-def>
%T1_Z<def> = KILL %T1_Z, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
%T1_Y<def> = KILL %T1_Y, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
%T1_X<def> = KILL %T1_X, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
%T2_X<def> = MOV 1, 0, 0, 0, %C1_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0,
%T2_XYZW<imp-def>
%T2_Y<def> = MOV 1, 0, 0, 0, %C1_Y, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0,
%T2_XYZW<imp-def>
%T2_Z<def> = MOV 1, 0, 0, 0, %C1_Z, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0,
%T2_XYZW<imp-def>
%T2_W<def> = MOV 1, 0, 0, 0, %C1_W, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0,
%T2_XYZW<imp-def>
%T3_X<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0
Successors according to CFG: BB#1
BB#1: derived from LLVM BB %25
Live Ins: %T1_XYZW %T2_XYZW %T3_X
Predecessors according to CFG: BB#0 BB#3
%T3_Y<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %T3_X, 0, 0, 0,
1, pred:%PRED_SEL_OFF, 0
%PREDICATE_BIT<def> = PRED_X %T3_Y<kill>, 152, 16
JUMP <BB#3>, pred:%PREDICATE_BIT<kill>
Successors according to CFG: BB#2(4) BB#3(124)
BB#2: derived from LLVM BB %31
Live Ins: %T1_XYZW %T2_XYZW
Predecessors according to CFG: BB#1
RETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>,
%T1_X<imp-use>, %T2_W<imp-use>, %T2_Z<imp-use>,
%T2_Y<imp-use>, %T2_X<imp-use>
BB#3: derived from LLVM BB %41
Live Ins: %T1_XYZW %T2_XYZW %T3_X
Predecessors according to CFG: BB#1
%T3_Y<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1
%T3_X<def> = ADD_INT 0, 0, 1, 0, 0, 0, %T3_X<kill>, 0, 0, 0,
%T3_Y<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0
JUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Analyze Machine Code For Garbage Collection ***:
# Machine code for function main: Post SSA, not tracking liveness
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
BB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
%T1_W<def> = KILL %T1_W, %T1_XYZW<imp-def>
%T1_Z<def> = KILL %T1_Z, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
%T1_Y<def> = KILL %T1_Y, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
%T1_X<def> = KILL %T1_X, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
%T2_X<def> = MOV 1, 0, 0, 0, %C1_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0,
%T2_XYZW<imp-def>
%T2_Y<def> = MOV 1, 0, 0, 0, %C1_Y, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0,
%T2_XYZW<imp-def>
%T2_Z<def> = MOV 1, 0, 0, 0, %C1_Z, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0,
%T2_XYZW<imp-def>
%T2_W<def> = MOV 1, 0, 0, 0, %C1_W, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0,
%T2_XYZW<imp-def>
%T3_X<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0
Successors according to CFG: BB#1
BB#1: derived from LLVM BB %25
Live Ins: %T1_XYZW %T2_XYZW %T3_X
Predecessors according to CFG: BB#0 BB#3
%T3_Y<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %T3_X, 0, 0, 0,
1, pred:%PRED_SEL_OFF, 0
%PREDICATE_BIT<def> = PRED_X %T3_Y<kill>, 152, 16
JUMP <BB#3>, pred:%PREDICATE_BIT<kill>
Successors according to CFG: BB#2(4) BB#3(124)
BB#2: derived from LLVM BB %31
Live Ins: %T1_XYZW %T2_XYZW
Predecessors according to CFG: BB#1
RETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>,
%T1_X<imp-use>, %T2_W<imp-use>, %T2_Z<imp-use>,
%T2_Y<imp-use>, %T2_X<imp-use>
BB#3: derived from LLVM BB %41
Live Ins: %T1_XYZW %T2_XYZW %T3_X
Predecessors according to CFG: BB#1
%T3_Y<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1
%T3_X<def> = ADD_INT 0, 0, 1, 0, 0, 0, %T3_X<kill>, 0, 0, 0,
%T3_Y<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0
JUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Branch Probability Basic Block Placement ***:
# Machine code for function main: Post SSA, not tracking liveness
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
BB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
%T1_W<def> = KILL %T1_W, %T1_XYZW<imp-def>
%T1_Z<def> = KILL %T1_Z, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
%T1_Y<def> = KILL %T1_Y, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
%T1_X<def> = KILL %T1_X, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
%T2_X<def> = MOV 1, 0, 0, 0, %C1_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0,
%T2_XYZW<imp-def>
%T2_Y<def> = MOV 1, 0, 0, 0, %C1_Y, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0,
%T2_XYZW<imp-def>
%T2_Z<def> = MOV 1, 0, 0, 0, %C1_Z, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0,
%T2_XYZW<imp-def>
%T2_W<def> = MOV 1, 0, 0, 0, %C1_W, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0,
%T2_XYZW<imp-def>
%T3_X<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0
Successors according to CFG: BB#1
BB#1: derived from LLVM BB %25
Live Ins: %T1_XYZW %T2_XYZW %T3_X
Predecessors according to CFG: BB#0 BB#3
%T3_Y<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %T3_X, 0, 0, 0,
1, pred:%PRED_SEL_OFF, 0
%PREDICATE_BIT<def> = PRED_X %T3_Y<kill>, 152, 16
JUMP <BB#3>, pred:%PREDICATE_BIT<kill>
Successors according to CFG: BB#2(4) BB#3(124)
BB#2: derived from LLVM BB %31
Live Ins: %T1_XYZW %T2_XYZW
Predecessors according to CFG: BB#1
RETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>,
%T1_X<imp-use>, %T2_W<imp-use>, %T2_Z<imp-use>,
%T2_Y<imp-use>, %T2_X<imp-use>
BB#3: derived from LLVM BB %41
Live Ins: %T1_XYZW %T2_XYZW %T3_X
Predecessors according to CFG: BB#1
%T3_Y<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1
%T3_X<def> = ADD_INT 0, 0, 1, 0, 0, 0, %T3_X<kill>, 0, 0, 0,
%T3_Y<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0
JUMP <BB#1>, pred:%noreg
Successors according to CFG: BB#1
# End machine code for function main.
# *** IR Dump Before Finalize machine instruction bundles ***:
# Machine code for function main: Post SSA, not tracking liveness
Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W
in %vreg17
Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X
BB#0: derived from LLVM BB %0
Live Ins: %T1_X %T1_Y %T1_Z %T1_W
%T1_W<def> = KILL %T1_W, %T1_XYZW<imp-def>
%T1_Z<def> = KILL %T1_Z, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
%T1_Y<def> = KILL %T1_Y, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
%T1_X<def> = KILL %T1_X, %T1_XYZW<imp-use,kill>,
%T1_XYZW<imp-def>
%T2_X<def> = MOV 1, 0, 0, 0, %C1_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0,
%T2_XYZW<imp-def>
%T2_Y<def> = MOV 1, 0, 0, 0, %C1_Y, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0,
%T2_XYZW<imp-def>
%T2_Z<def> = MOV 1, 0, 0, 0, %C1_Z, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0,
%T2_XYZW<imp-def>
%T2_W<def> = MOV 1, 0, 0, 0, %C1_W, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0,
%T2_XYZW<imp-def>
%T3_X<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 0
WHILELOOP
%T3_Y<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %T3_X, 0, 0, 0,
1, pred:%PRED_SEL_OFF, 0
%PREDICATE_BIT<def> = PRED_SETE_INT 1, 0, 0, 0, 0, 0, %T3_Y, 0, 0, 0,
%ZERO, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0
BREAK_LOGICALZ_i32 %PREDICATE_BIT
%T3_Y<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1,
pred:%PRED_SEL_OFF, 1
%T3_X<def> = ADD_INT 0, 0, 1, 0, 0, 0, %T3_X<kill>, 0, 0, 0,
%T3_Y<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0
ENDLOOP
RETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>,
%T1_X<imp-use>, %T2_W<imp-use>, %T2_Z<imp-use>,
%T2_Y<imp-use>, %T2_X<imp-use>
# End machine code for function main.
Ivan Llopard
2012-Oct-25 06:08 UTC
[LLVMdev] RegisterCoalescing Pass seems to ignore part of CFG.
Hi Vincent, On 24/10/2012 23:26, Vincent Lejeune wrote:> Hi, > > I don't know if my llvm ir code is faulty, or if I spot a bug in the RegisterCoalescing Pass, so I'm posting my issue on the ML. Shader and print-before-all dump are given below. > > The interessing part is the vreg6/vreg48 reduction : before RegCoalescing, the machine code is : > > // BEFORE LOOP > ... Some COPYs.... > 400B%vreg47<def> = COPY %vreg2<kill>; R600_Reg32:%vreg47,%vreg2 > 416B%vreg48<def> = COPY %vreg3<kill>; R600_Reg128:%vreg48,%vreg3 > 432B%vreg49<def> = COPY %vreg13<kill>; R600_Reg32:%vreg49,%vreg13 > Successors according to CFG: BB#1 > > > // LOOP CONDITION > 464B%vreg5<def> = COPY %vreg47<kill>; R600_Reg32:%vreg5,%vreg47 > 480B%vreg6<def> = COPY %vreg48<kill>; R600_Reg128:%vreg6,%vreg48 > 496B%vreg7<def> = COPY %vreg49<kill>; R600_Reg32:%vreg7,%vreg49 > 512B%vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7 > 528B%vreg30<def> = COPY %vreg29<kill>; R600_Reg32:%vreg30,%vreg29 > 544B%PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16; R600_Reg32:%vreg30 > 560BJUMP <BB#3>, pred:%PREDICATE_BIT > 576BJUMP <BB#2>, pred:%noreg > > // LOOP BODY > 896B%vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6 > 912B%vreg32:sel_x<def,read-undef> = COPY %vreg31<kill>; R600_Reg128:%vreg32 R600_Reg32:%vreg31 > 928B%vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6 > 944B%vreg35<def> = COPY %vreg32<kill>; R600_Reg128:%vreg35,%vreg32 > 960B%vreg35:sel_y<def> = COPY %vreg34<kill>; R600_Reg128:%vreg35 R600_Reg32:%vreg34 > 976B%vreg36<def> = COPY %vreg35<kill>; R600_Reg128:%vreg36,%vreg35 > 992B%vreg36:sel_z<def> = COPY %vreg5<kill>; R600_Reg128:%vreg36 R600_Reg32:%vreg5 > 1008B%vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6 > 1024B%vreg10<def> = COPY %vreg36<kill>; R600_Reg128:%vreg10,%vreg36 > 1040B%vreg10:sel_w<def> = COPY %vreg37<kill>; R600_Reg128:%vreg10 R600_Reg32:%vreg37 > 1056B%vreg9<def> = COPY %vreg6:sel_z<kill>; R600_Reg32:%vreg9 R600_Reg128:%vreg6 > 1072B%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38 > 1088B%vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7<kill>, 0, 0, 0, %vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg11,%vreg7,%vreg38 > 1104B%vreg47<def> = COPY %vreg9<kill>; R600_Reg32:%vreg47,%vreg9 > 1120B%vreg48<def> = COPY %vreg10<kill>; R600_Reg128:%vreg48,%vreg10 > 1136B%vreg49<def> = COPY %vreg11<kill>; R600_Reg32:%vreg49,%vreg11 > 1152BJUMP <BB#1>, pred:%noreg > > // EXPORTED VALUES > 608B%vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6 > 624B%T2_X<def> = COPY %vreg39<kill>; R600_Reg32:%vreg39 > 640B%vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6 > 656B%T2_Y<def> = COPY %vreg40<kill>; R600_Reg32:%vreg40 > 672B%vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6 > 688B%T2_Z<def> = COPY %vreg41<kill>; R600_Reg32:%vreg41 > 704B%vreg42<def> = COPY %vreg6:sel_w<kill>; R600_Reg32:%vreg42 R600_Reg128:%vreg6 > 720B%T2_W<def> = COPY %vreg42<kill>; R600_Reg32:%vreg42 > > And after the pass : > > //Before Loop > ...Some COPYs... > 128B%vreg27:sel_x<def,read-undef> = COPY %C1_X; R600_Reg128:%vreg27 > 192B%vreg27:sel_y<def> = COPY %C1_Y; R600_Reg128:%vreg27 > 272B%vreg27:sel_z<def> = COPY %C1_Z; R600_Reg128:%vreg27 > 320B%vreg27:sel_w<def> = COPY %C1_W; R600_Reg128:%vreg27 > > //LOOP CONDITION > 512B%vreg30<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %vreg49, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg30,%vreg49 > 544B%PREDICATE_BIT<def> = PRED_X %vreg30, 152, 16; R600_Reg32:%vreg30 > 560BJUMP <BB#3>, pred:%PREDICATE_BIT > 576BJUMP <BB#2>, pred:%noreg > > //LOOP BODY > 1072B%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38 > 1088B%vreg49<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg49, 0, 0, 0, %vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg49,%vreg38 > 1152BJUMP <BB#1>, pred:%noreg > > // EXPORTED VALUES > 624B%T2_X<def> = COPY %vreg27:sel_x; R600_Reg128:%vreg27 > 656B%T2_Y<def> = COPY %vreg27:sel_y; R600_Reg128:%vreg27 > 688B%T2_Z<def> = COPY %vreg27:sel_z; R600_Reg128:%vreg27 > 720B%T2_W<def> = COPY %vreg27:sel_w; R600_Reg128:%vreg27 > > > Apparently, the pass assumed that it's still in SSA mode, and join vreg6 with vreg27, thus ignoring the body block that can modify vreg48 value, and thus vreg6 value. > I don't know if I should manually tell the pass that it's not in SSA mode (I assume that previous pass like 2 address simplification pass does it), if I miss something in my LLVM IR, > or if it's a bug.PHIElim and TwoAddress passes leave SSA form. May be a missed something in your code but %vreg48 seems to be there after PHI elimination. PHIElim tags those kind of registers as being PHIJoin regs, updating LiveVariables pass, so the regcoalescer is aware of them (some SSA info is still alive but the reg coalescer will invalidate that information after joining intervals). PHIJoin regs doesn't get modified by any other instruction than copies. Anyway, IMHO if your code is faulty there should be a bug somewhere else. Ivan> > Regards, > Vincent > > The LLVM IR is the following : > ____________________________________________________ > ; ModuleID = 'glsl-to-llvm' > > define void @main() { > call void @llvm.AMDGPU.reserve.reg(i32 0) > call void @llvm.AMDGPU.reserve.reg(i32 1) > call void @llvm.AMDGPU.reserve.reg(i32 2) > call void @llvm.AMDGPU.reserve.reg(i32 3) > %1 = call float @llvm.AMDGPU.load.const(i32 0) > %2 = bitcast float %1 to i32 > %3 = call float @llvm.AMDGPU.load.const(i32 4) > %4 = insertelement <4 x float> undef, float %3, i32 0 > %5 = call float @llvm.AMDGPU.load.const(i32 5) > %6 = insertelement <4 x float> %4, float %5, i32 1 > %7 = call float @llvm.AMDGPU.load.const(i32 6) > %8 = insertelement <4 x float> %6, float %7, i32 2 > %9 = call float @llvm.AMDGPU.load.const(i32 7) > %10 = insertelement <4 x float> %8, float %9, i32 3 > %11 = call float @llvm.R600.load.input(i32 4) > %12 = insertelement <4 x float> undef, float %11, i32 0 > %13 = call float @llvm.R600.load.input(i32 5) > %14 = insertelement <4 x float> %12, float %13, i32 1 > %15 = call float @llvm.R600.load.input(i32 6) > %16 = insertelement <4 x float> %14, float %15, i32 2 > %17 = call float @llvm.R600.load.input(i32 7) > %18 = insertelement <4 x float> %16, float %17, i32 3 > %19 = shufflevector <4 x float> %10, <4 x float> %10, <1 x i32> <i32 1> > %20 = extractelement <1 x float> %19, i32 0 > %21 = insertelement <1 x float> undef, float %20, i32 0 > %22 = shufflevector <1 x float> undef, <1 x float> %21, <1 x i32> <i32 1> > %23 = extractelement <1 x float> %22, i32 0 > %24 = shufflevector <4 x float> undef, <4 x float> %10, <4 x i32> <i32 4, i32 5, i32 6, i32 7> > br label %25 > > ; <label>:25 ; preds = %41, %0 > %26 = phi float [ %45, %41 ], [ undef, %0 ] > %27 = phi float [ %50, %41 ], [ %23, %0 ] > %28 = phi <4 x float> [ %53, %41 ], [ %24, %0 ] > %29 = phi i32 [ %58, %41 ], [ 0, %0 ] > %30 = icmp sge i32 %29, %2 > br i1 %30, label %31, label %41 > > ; <label>:31 ; preds = %25 > %32 = shufflevector <4 x float> undef, <4 x float> %18, <4 x i32> <i32 4, i32 5, i32 6, i32 7> > %33 = extractelement <4 x float> %28, i32 0 > call void @llvm.AMDGPU.store.output(float %33, i32 8) > %34 = extractelement <4 x float> %28, i32 1 > call void @llvm.AMDGPU.store.output(float %34, i32 9) > %35 = extractelement <4 x float> %28, i32 2 > call void @llvm.AMDGPU.store.output(float %35, i32 10) > %36 = extractelement <4 x float> %28, i32 3 > call void @llvm.AMDGPU.store.output(float %36, i32 11) > %37 = extractelement <4 x float> %32, i32 0 > call void @llvm.AMDGPU.store.output(float %37, i32 4) > %38 = extractelement <4 x float> %32, i32 1 > call void @llvm.AMDGPU.store.output(float %38, i32 5) > %39 = extractelement <4 x float> %32, i32 2 > call void @llvm.AMDGPU.store.output(float %39, i32 6) > %40 = extractelement <4 x float> %32, i32 3 > call void @llvm.AMDGPU.store.output(float %40, i32 7) > ret void > > ; <label>:41 ; preds = %25 > %42 = insertelement <1 x float> undef, float %27, i32 0 > %43 = insertelement <1 x float> undef, float %26, i32 0 > %44 = shufflevector <1 x float> %43, <1 x float> %42, <1 x i32> <i32 1> > %45 = extractelement <1 x float> %44, i32 0 > %46 = shufflevector <4 x float> %28, <4 x float> %28, <1 x i32> <i32 2> > %47 = extractelement <1 x float> %46, i32 0 > %48 = insertelement <1 x float> undef, float %47, i32 0 > %49 = shufflevector <1 x float> %42, <1 x float> %48, <1 x i32> <i32 1> > %50 = extractelement <1 x float> %49, i32 0 > %51 = insertelement <1 x float> undef, float %45, i32 0 > %52 = shufflevector <1 x float> %51, <1 x float> %51, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef> > %53 = shufflevector <4 x float> %28, <4 x float> %52, <4 x i32> <i32 0, i32 1, i32 4, i32 3> > %54 = add i32 %29, 1 > %55 = insertelement <1 x i32> undef, i32 %54, i32 0 > %56 = insertelement <1 x i32> undef, i32 %29, i32 0 > %57 = shufflevector <1 x i32> %56, <1 x i32> %55, <1 x i32> <i32 1> > %58 = extractelement <1 x i32> %57, i32 0 > br label %25 > } > > declare float @llvm.AMDGPU.load.const(i32) readnone > > declare float @llvm.R600.load.input(i32) readnone > > declare void @llvm.AMDGPU.store.output(float, i32) > > declare void @llvm.AMDGPU.reserve.reg(i32) > > declare float @llvm.R600.load.input.perspective(i32) readnone > > declare float @llvm.R600.load.input.constant(i32) readnone > > declare float @llvm.R600.load.input.linear(i32) readnone > > _________________________________________________________________ > The print before all dump is : > > *** IR Dump Before Preliminary module verification *** > define void @main() { > call void @llvm.AMDGPU.reserve.reg(i32 0) > call void @llvm.AMDGPU.reserve.reg(i32 1) > call void @llvm.AMDGPU.reserve.reg(i32 2) > call void @llvm.AMDGPU.reserve.reg(i32 3) > %1 = call float @llvm.AMDGPU.load.const(i32 0) > %2 = bitcast float %1 to i32 > %3 = call float @llvm.AMDGPU.load.const(i32 4) > %4 = insertelement <4 x float> undef, float %3, i32 0 > %5 = call float @llvm.AMDGPU.load.const(i32 5) > %6 = insertelement <4 x float> %4, float %5, i32 1 > %7 = call float @llvm.AMDGPU.load.const(i32 6) > %8 = insertelement <4 x float> %6, float %7, i32 2 > %9 = call float @llvm.AMDGPU.load.const(i32 7) > %10 = insertelement <4 x float> %8, float %9, i32 3 > %11 = call float @llvm.R600.load.input(i32 4) > %12 = insertelement <4 x float> undef, float %11, i32 0 > %13 = call float @llvm.R600.load.input(i32 5) > %14 = insertelement <4 x float> %12, float %13, i32 1 > %15 = call float @llvm.R600.load.input(i32 6) > %16 = insertelement <4 x float> %14, float %15, i32 2 > %17 = call float @llvm.R600.load.input(i32 7) > %18 = insertelement <4 x float> %16, float %17, i32 3 > %19 = shufflevector <4 x float> %10, <4 x float> %10, <1 x i32> <i32 1> > %20 = extractelement <1 x float> %19, i32 0 > %21 = insertelement <1 x float> undef, float %20, i32 0 > %22 = shufflevector <1 x float> undef, <1 x float> %21, <1 x i32> <i32 1> > %23 = extractelement <1 x float> %22, i32 0 > %24 = shufflevector <4 x float> undef, <4 x float> %10, <4 x i32> <i32 4, i32 5, i32 6, i32 7> > br label %25 > > ; <label>:25 ; preds = %41, %0 > %26 = phi float [ %45, %41 ], [ undef, %0 ] > %27 = phi float [ %50, %41 ], [ %23, %0 ] > %28 = phi <4 x float> [ %53, %41 ], [ %24, %0 ] > %29 = phi i32 [ %58, %41 ], [ 0, %0 ] > %30 = icmp sge i32 %29, %2 > br i1 %30, label %31, label %41 > > ; <label>:31 ; preds = %25 > %32 = shufflevector <4 x float> undef, <4 x float> %18, <4 x i32> <i32 4, i32 5, i32 6, i32 7> > %33 = extractelement <4 x float> %28, i32 0 > call void @llvm.AMDGPU.store.output(float %33, i32 8) > %34 = extractelement <4 x float> %28, i32 1 > call void @llvm.AMDGPU.store.output(float %34, i32 9) > %35 = extractelement <4 x float> %28, i32 2 > call void @llvm.AMDGPU.store.output(float %35, i32 10) > %36 = extractelement <4 x float> %28, i32 3 > call void @llvm.AMDGPU.store.output(float %36, i32 11) > %37 = extractelement <4 x float> %32, i32 0 > call void @llvm.AMDGPU.store.output(float %37, i32 4) > %38 = extractelement <4 x float> %32, i32 1 > call void @llvm.AMDGPU.store.output(float %38, i32 5) > %39 = extractelement <4 x float> %32, i32 2 > call void @llvm.AMDGPU.store.output(float %39, i32 6) > %40 = extractelement <4 x float> %32, i32 3 > call void @llvm.AMDGPU.store.output(float %40, i32 7) > ret void > > ; <label>:41 ; preds = %25 > %42 = insertelement <1 x float> undef, float %27, i32 0 > %43 = insertelement <1 x float> undef, float %26, i32 0 > %44 = shufflevector <1 x float> %43, <1 x float> %42, <1 x i32> <i32 1> > %45 = extractelement <1 x float> %44, i32 0 > %46 = shufflevector <4 x float> %28, <4 x float> %28, <1 x i32> <i32 2> > %47 = extractelement <1 x float> %46, i32 0 > %48 = insertelement <1 x float> undef, float %47, i32 0 > %49 = shufflevector <1 x float> %42, <1 x float> %48, <1 x i32> <i32 1> > %50 = extractelement <1 x float> %49, i32 0 > %51 = insertelement <1 x float> undef, float %45, i32 0 > %52 = shufflevector <1 x float> %51, <1 x float> %51, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef> > %53 = shufflevector <4 x float> %28, <4 x float> %52, <4 x i32> <i32 0, i32 1, i32 4, i32 3> > %54 = add i32 %29, 1 > %55 = insertelement <1 x i32> undef, i32 %54, i32 0 > %56 = insertelement <1 x i32> undef, i32 %29, i32 0 > %57 = shufflevector <1 x i32> %56, <1 x i32> %55, <1 x i32> <i32 1> > %58 = extractelement <1 x i32> %57, i32 0 > br label %25 > } > *** IR Dump Before Module Verifier *** > define void @main() { > call void @llvm.AMDGPU.reserve.reg(i32 0) > call void @llvm.AMDGPU.reserve.reg(i32 1) > call void @llvm.AMDGPU.reserve.reg(i32 2) > call void @llvm.AMDGPU.reserve.reg(i32 3) > %1 = call float @llvm.AMDGPU.load.const(i32 0) > %2 = bitcast float %1 to i32 > %3 = call float @llvm.AMDGPU.load.const(i32 4) > %4 = insertelement <4 x float> undef, float %3, i32 0 > %5 = call float @llvm.AMDGPU.load.const(i32 5) > %6 = insertelement <4 x float> %4, float %5, i32 1 > %7 = call float @llvm.AMDGPU.load.const(i32 6) > %8 = insertelement <4 x float> %6, float %7, i32 2 > %9 = call float @llvm.AMDGPU.load.const(i32 7) > %10 = insertelement <4 x float> %8, float %9, i32 3 > %11 = call float @llvm.R600.load.input(i32 4) > %12 = insertelement <4 x float> undef, float %11, i32 0 > %13 = call float @llvm.R600.load.input(i32 5) > %14 = insertelement <4 x float> %12, float %13, i32 1 > %15 = call float @llvm.R600.load.input(i32 6) > %16 = insertelement <4 x float> %14, float %15, i32 2 > %17 = call float @llvm.R600.load.input(i32 7) > %18 = insertelement <4 x float> %16, float %17, i32 3 > %19 = shufflevector <4 x float> %10, <4 x float> %10, <1 x i32> <i32 1> > %20 = extractelement <1 x float> %19, i32 0 > %21 = insertelement <1 x float> undef, float %20, i32 0 > %22 = shufflevector <1 x float> undef, <1 x float> %21, <1 x i32> <i32 1> > %23 = extractelement <1 x float> %22, i32 0 > %24 = shufflevector <4 x float> undef, <4 x float> %10, <4 x i32> <i32 4, i32 5, i32 6, i32 7> > br label %25 > > ; <label>:25 ; preds = %41, %0 > %26 = phi float [ %45, %41 ], [ undef, %0 ] > %27 = phi float [ %50, %41 ], [ %23, %0 ] > %28 = phi <4 x float> [ %53, %41 ], [ %24, %0 ] > %29 = phi i32 [ %58, %41 ], [ 0, %0 ] > %30 = icmp sge i32 %29, %2 > br i1 %30, label %31, label %41 > > ; <label>:31 ; preds = %25 > %32 = shufflevector <4 x float> undef, <4 x float> %18, <4 x i32> <i32 4, i32 5, i32 6, i32 7> > %33 = extractelement <4 x float> %28, i32 0 > call void @llvm.AMDGPU.store.output(float %33, i32 8) > %34 = extractelement <4 x float> %28, i32 1 > call void @llvm.AMDGPU.store.output(float %34, i32 9) > %35 = extractelement <4 x float> %28, i32 2 > call void @llvm.AMDGPU.store.output(float %35, i32 10) > %36 = extractelement <4 x float> %28, i32 3 > call void @llvm.AMDGPU.store.output(float %36, i32 11) > %37 = extractelement <4 x float> %32, i32 0 > call void @llvm.AMDGPU.store.output(float %37, i32 4) > %38 = extractelement <4 x float> %32, i32 1 > call void @llvm.AMDGPU.store.output(float %38, i32 5) > %39 = extractelement <4 x float> %32, i32 2 > call void @llvm.AMDGPU.store.output(float %39, i32 6) > %40 = extractelement <4 x float> %32, i32 3 > call void @llvm.AMDGPU.store.output(float %40, i32 7) > ret void > > ; <label>:41 ; preds = %25 > %42 = insertelement <1 x float> undef, float %27, i32 0 > %43 = insertelement <1 x float> undef, float %26, i32 0 > %44 = shufflevector <1 x float> %43, <1 x float> %42, <1 x i32> <i32 1> > %45 = extractelement <1 x float> %44, i32 0 > %46 = shufflevector <4 x float> %28, <4 x float> %28, <1 x i32> <i32 2> > %47 = extractelement <1 x float> %46, i32 0 > %48 = insertelement <1 x float> undef, float %47, i32 0 > %49 = shufflevector <1 x float> %42, <1 x float> %48, <1 x i32> <i32 1> > %50 = extractelement <1 x float> %49, i32 0 > %51 = insertelement <1 x float> undef, float %45, i32 0 > %52 = shufflevector <1 x float> %51, <1 x float> %51, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef> > %53 = shufflevector <4 x float> %28, <4 x float> %52, <4 x i32> <i32 0, i32 1, i32 4, i32 3> > %54 = add i32 %29, 1 > %55 = insertelement <1 x i32> undef, i32 %54, i32 0 > %56 = insertelement <1 x i32> undef, i32 %29, i32 0 > %57 = shufflevector <1 x i32> %56, <1 x i32> %55, <1 x i32> <i32 1> > %58 = extractelement <1 x i32> %57, i32 0 > br label %25 > } > *** IR Dump Before Canonicalize natural loops *** > ; <label>:25 ; preds = %41, %0 > %26 = phi float [ %45, %41 ], [ undef, %0 ] > %27 = phi float [ %50, %41 ], [ %23, %0 ] > %28 = phi <4 x float> [ %53, %41 ], [ %24, %0 ] > %29 = phi i32 [ %58, %41 ], [ 0, %0 ] > %30 = icmp sge i32 %29, %2 > br i1 %30, label %31, label %41 > > ; <label>:41 ; preds = %25 > %42 = insertelement <1 x float> undef, float %27, i32 0 > %43 = insertelement <1 x float> undef, float %26, i32 0 > %44 = shufflevector <1 x float> %43, <1 x float> %42, <1 x i32> <i32 1> > %45 = extractelement <1 x float> %44, i32 0 > %46 = shufflevector <4 x float> %28, <4 x float> %28, <1 x i32> <i32 2> > %47 = extractelement <1 x float> %46, i32 0 > %48 = insertelement <1 x float> undef, float %47, i32 0 > %49 = shufflevector <1 x float> %42, <1 x float> %48, <1 x i32> <i32 1> > %50 = extractelement <1 x float> %49, i32 0 > %51 = insertelement <1 x float> undef, float %45, i32 0 > %52 = shufflevector <1 x float> %51, <1 x float> %51, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef> > %53 = shufflevector <4 x float> %28, <4 x float> %52, <4 x i32> <i32 0, i32 1, i32 4, i32 3> > %54 = add i32 %29, 1 > %55 = insertelement <1 x i32> undef, i32 %54, i32 0 > %56 = insertelement <1 x i32> undef, i32 %29, i32 0 > %57 = shufflevector <1 x i32> %56, <1 x i32> %55, <1 x i32> <i32 1> > %58 = extractelement <1 x i32> %57, i32 0 > br label %25 > *** IR Dump Before Canonicalize natural loops *** > ; <label>:25 ; preds = %41, %0 > %26 = phi float [ %45, %41 ], [ undef, %0 ] > %27 = phi float [ %50, %41 ], [ %23, %0 ] > %28 = phi <4 x float> [ %53, %41 ], [ %24, %0 ] > %29 = phi i32 [ %58, %41 ], [ 0, %0 ] > %30 = icmp sge i32 %29, %2 > br i1 %30, label %31, label %41 > > ; <label>:41 ; preds = %25 > %42 = insertelement <1 x float> undef, float %27, i32 0 > %43 = insertelement <1 x float> undef, float %26, i32 0 > %44 = shufflevector <1 x float> %43, <1 x float> %42, <1 x i32> <i32 1> > %45 = extractelement <1 x float> %44, i32 0 > %46 = shufflevector <4 x float> %28, <4 x float> %28, <1 x i32> <i32 2> > %47 = extractelement <1 x float> %46, i32 0 > %48 = insertelement <1 x float> undef, float %47, i32 0 > %49 = shufflevector <1 x float> %42, <1 x float> %48, <1 x i32> <i32 1> > %50 = extractelement <1 x float> %49, i32 0 > %51 = insertelement <1 x float> undef, float %45, i32 0 > %52 = shufflevector <1 x float> %51, <1 x float> %51, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef> > %53 = shufflevector <4 x float> %28, <4 x float> %52, <4 x i32> <i32 0, i32 1, i32 4, i32 3> > %54 = add i32 %29, 1 > %55 = insertelement <1 x i32> undef, i32 %54, i32 0 > %56 = insertelement <1 x i32> undef, i32 %29, i32 0 > %57 = shufflevector <1 x i32> %56, <1 x i32> %55, <1 x i32> <i32 1> > %58 = extractelement <1 x i32> %57, i32 0 > br label %25 > *** IR Dump Before Loop Strength Reduction *** > ; <label>:25 ; preds = %41, %0 > %26 = phi float [ %45, %41 ], [ undef, %0 ] > %27 = phi float [ %50, %41 ], [ %23, %0 ] > %28 = phi <4 x float> [ %53, %41 ], [ %24, %0 ] > %29 = phi i32 [ %58, %41 ], [ 0, %0 ] > %30 = icmp sge i32 %29, %2 > br i1 %30, label %31, label %41 > > ; <label>:41 ; preds = %25 > %42 = insertelement <1 x float> undef, float %27, i32 0 > %43 = insertelement <1 x float> undef, float %26, i32 0 > %44 = shufflevector <1 x float> %43, <1 x float> %42, <1 x i32> <i32 1> > %45 = extractelement <1 x float> %44, i32 0 > %46 = shufflevector <4 x float> %28, <4 x float> %28, <1 x i32> <i32 2> > %47 = extractelement <1 x float> %46, i32 0 > %48 = insertelement <1 x float> undef, float %47, i32 0 > %49 = shufflevector <1 x float> %42, <1 x float> %48, <1 x i32> <i32 1> > %50 = extractelement <1 x float> %49, i32 0 > %51 = insertelement <1 x float> undef, float %45, i32 0 > %52 = shufflevector <1 x float> %51, <1 x float> %51, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef> > %53 = shufflevector <4 x float> %28, <4 x float> %52, <4 x i32> <i32 0, i32 1, i32 4, i32 3> > %54 = add i32 %29, 1 > %55 = insertelement <1 x i32> undef, i32 %54, i32 0 > %56 = insertelement <1 x i32> undef, i32 %29, i32 0 > %57 = shufflevector <1 x i32> %56, <1 x i32> %55, <1 x i32> <i32 1> > %58 = extractelement <1 x i32> %57, i32 0 > br label %25 > *** IR Dump Before Lower Garbage Collection Instructions *** > define void @main() { > call void @llvm.AMDGPU.reserve.reg(i32 0) > call void @llvm.AMDGPU.reserve.reg(i32 1) > call void @llvm.AMDGPU.reserve.reg(i32 2) > call void @llvm.AMDGPU.reserve.reg(i32 3) > %1 = call float @llvm.AMDGPU.load.const(i32 0) > %2 = bitcast float %1 to i32 > %3 = call float @llvm.AMDGPU.load.const(i32 4) > %4 = insertelement <4 x float> undef, float %3, i32 0 > %5 = call float @llvm.AMDGPU.load.const(i32 5) > %6 = insertelement <4 x float> %4, float %5, i32 1 > %7 = call float @llvm.AMDGPU.load.const(i32 6) > %8 = insertelement <4 x float> %6, float %7, i32 2 > %9 = call float @llvm.AMDGPU.load.const(i32 7) > %10 = insertelement <4 x float> %8, float %9, i32 3 > %11 = call float @llvm.R600.load.input(i32 4) > %12 = insertelement <4 x float> undef, float %11, i32 0 > %13 = call float @llvm.R600.load.input(i32 5) > %14 = insertelement <4 x float> %12, float %13, i32 1 > %15 = call float @llvm.R600.load.input(i32 6) > %16 = insertelement <4 x float> %14, float %15, i32 2 > %17 = call float @llvm.R600.load.input(i32 7) > %18 = insertelement <4 x float> %16, float %17, i32 3 > %19 = shufflevector <4 x float> %10, <4 x float> %10, <1 x i32> <i32 1> > %20 = extractelement <1 x float> %19, i32 0 > %21 = insertelement <1 x float> undef, float %20, i32 0 > %22 = shufflevector <1 x float> undef, <1 x float> %21, <1 x i32> <i32 1> > %23 = extractelement <1 x float> %22, i32 0 > %24 = shufflevector <4 x float> undef, <4 x float> %10, <4 x i32> <i32 4, i32 5, i32 6, i32 7> > br label %25 > > ; <label>:25 ; preds = %41, %0 > %26 = phi float [ %45, %41 ], [ undef, %0 ] > %27 = phi float [ %50, %41 ], [ %23, %0 ] > %28 = phi <4 x float> [ %53, %41 ], [ %24, %0 ] > %29 = phi i32 [ %58, %41 ], [ 0, %0 ] > %30 = icmp sge i32 %29, %2 > br i1 %30, label %31, label %41 > > ; <label>:31 ; preds = %25 > %32 = shufflevector <4 x float> undef, <4 x float> %18, <4 x i32> <i32 4, i32 5, i32 6, i32 7> > %33 = extractelement <4 x float> %28, i32 0 > call void @llvm.AMDGPU.store.output(float %33, i32 8) > %34 = extractelement <4 x float> %28, i32 1 > call void @llvm.AMDGPU.store.output(float %34, i32 9) > %35 = extractelement <4 x float> %28, i32 2 > call void @llvm.AMDGPU.store.output(float %35, i32 10) > %36 = extractelement <4 x float> %28, i32 3 > call void @llvm.AMDGPU.store.output(float %36, i32 11) > %37 = extractelement <4 x float> %32, i32 0 > call void @llvm.AMDGPU.store.output(float %37, i32 4) > %38 = extractelement <4 x float> %32, i32 1 > call void @llvm.AMDGPU.store.output(float %38, i32 5) > %39 = extractelement <4 x float> %32, i32 2 > call void @llvm.AMDGPU.store.output(float %39, i32 6) > %40 = extractelement <4 x float> %32, i32 3 > call void @llvm.AMDGPU.store.output(float %40, i32 7) > ret void > > ; <label>:41 ; preds = %25 > %42 = insertelement <1 x float> undef, float %27, i32 0 > %43 = insertelement <1 x float> undef, float %26, i32 0 > %44 = shufflevector <1 x float> %43, <1 x float> %42, <1 x i32> <i32 1> > %45 = extractelement <1 x float> %44, i32 0 > %46 = shufflevector <4 x float> %28, <4 x float> %28, <1 x i32> <i32 2> > %47 = extractelement <1 x float> %46, i32 0 > %48 = insertelement <1 x float> undef, float %47, i32 0 > %49 = shufflevector <1 x float> %42, <1 x float> %48, <1 x i32> <i32 1> > %50 = extractelement <1 x float> %49, i32 0 > %51 = insertelement <1 x float> undef, float %45, i32 0 > %52 = shufflevector <1 x float> %51, <1 x float> %51, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef> > %53 = shufflevector <4 x float> %28, <4 x float> %52, <4 x i32> <i32 0, i32 1, i32 4, i32 3> > %54 = add i32 %29, 1 > %55 = insertelement <1 x i32> undef, i32 %54, i32 0 > %56 = insertelement <1 x i32> undef, i32 %29, i32 0 > %57 = shufflevector <1 x i32> %56, <1 x i32> %55, <1 x i32> <i32 1> > %58 = extractelement <1 x i32> %57, i32 0 > br label %25 > } > *** IR Dump Before Remove unreachable blocks from the CFG *** > define void @main() { > call void @llvm.AMDGPU.reserve.reg(i32 0) > call void @llvm.AMDGPU.reserve.reg(i32 1) > call void @llvm.AMDGPU.reserve.reg(i32 2) > call void @llvm.AMDGPU.reserve.reg(i32 3) > %1 = call float @llvm.AMDGPU.load.const(i32 0) > %2 = bitcast float %1 to i32 > %3 = call float @llvm.AMDGPU.load.const(i32 4) > %4 = insertelement <4 x float> undef, float %3, i32 0 > %5 = call float @llvm.AMDGPU.load.const(i32 5) > %6 = insertelement <4 x float> %4, float %5, i32 1 > %7 = call float @llvm.AMDGPU.load.const(i32 6) > %8 = insertelement <4 x float> %6, float %7, i32 2 > %9 = call float @llvm.AMDGPU.load.const(i32 7) > %10 = insertelement <4 x float> %8, float %9, i32 3 > %11 = call float @llvm.R600.load.input(i32 4) > %12 = insertelement <4 x float> undef, float %11, i32 0 > %13 = call float @llvm.R600.load.input(i32 5) > %14 = insertelement <4 x float> %12, float %13, i32 1 > %15 = call float @llvm.R600.load.input(i32 6) > %16 = insertelement <4 x float> %14, float %15, i32 2 > %17 = call float @llvm.R600.load.input(i32 7) > %18 = insertelement <4 x float> %16, float %17, i32 3 > %19 = shufflevector <4 x float> %10, <4 x float> %10, <1 x i32> <i32 1> > %20 = extractelement <1 x float> %19, i32 0 > %21 = insertelement <1 x float> undef, float %20, i32 0 > %22 = shufflevector <1 x float> undef, <1 x float> %21, <1 x i32> <i32 1> > %23 = extractelement <1 x float> %22, i32 0 > %24 = shufflevector <4 x float> undef, <4 x float> %10, <4 x i32> <i32 4, i32 5, i32 6, i32 7> > br label %25 > > ; <label>:25 ; preds = %41, %0 > %26 = phi float [ %45, %41 ], [ undef, %0 ] > %27 = phi float [ %50, %41 ], [ %23, %0 ] > %28 = phi <4 x float> [ %53, %41 ], [ %24, %0 ] > %29 = phi i32 [ %58, %41 ], [ 0, %0 ] > %30 = icmp sge i32 %29, %2 > br i1 %30, label %31, label %41 > > ; <label>:31 ; preds = %25 > %32 = shufflevector <4 x float> undef, <4 x float> %18, <4 x i32> <i32 4, i32 5, i32 6, i32 7> > %33 = extractelement <4 x float> %28, i32 0 > call void @llvm.AMDGPU.store.output(float %33, i32 8) > %34 = extractelement <4 x float> %28, i32 1 > call void @llvm.AMDGPU.store.output(float %34, i32 9) > %35 = extractelement <4 x float> %28, i32 2 > call void @llvm.AMDGPU.store.output(float %35, i32 10) > %36 = extractelement <4 x float> %28, i32 3 > call void @llvm.AMDGPU.store.output(float %36, i32 11) > %37 = extractelement <4 x float> %32, i32 0 > call void @llvm.AMDGPU.store.output(float %37, i32 4) > %38 = extractelement <4 x float> %32, i32 1 > call void @llvm.AMDGPU.store.output(float %38, i32 5) > %39 = extractelement <4 x float> %32, i32 2 > call void @llvm.AMDGPU.store.output(float %39, i32 6) > %40 = extractelement <4 x float> %32, i32 3 > call void @llvm.AMDGPU.store.output(float %40, i32 7) > ret void > > ; <label>:41 ; preds = %25 > %42 = insertelement <1 x float> undef, float %27, i32 0 > %43 = insertelement <1 x float> undef, float %26, i32 0 > %44 = shufflevector <1 x float> %43, <1 x float> %42, <1 x i32> <i32 1> > %45 = extractelement <1 x float> %44, i32 0 > %46 = shufflevector <4 x float> %28, <4 x float> %28, <1 x i32> <i32 2> > %47 = extractelement <1 x float> %46, i32 0 > %48 = insertelement <1 x float> undef, float %47, i32 0 > %49 = shufflevector <1 x float> %42, <1 x float> %48, <1 x i32> <i32 1> > %50 = extractelement <1 x float> %49, i32 0 > %51 = insertelement <1 x float> undef, float %45, i32 0 > %52 = shufflevector <1 x float> %51, <1 x float> %51, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef> > %53 = shufflevector <4 x float> %28, <4 x float> %52, <4 x i32> <i32 0, i32 1, i32 4, i32 3> > %54 = add i32 %29, 1 > %55 = insertelement <1 x i32> undef, i32 %54, i32 0 > %56 = insertelement <1 x i32> undef, i32 %29, i32 0 > %57 = shufflevector <1 x i32> %56, <1 x i32> %55, <1 x i32> <i32 1> > %58 = extractelement <1 x i32> %57, i32 0 > br label %25 > } > *** IR Dump Before Lower invoke and unwind, for unwindless code generators *** > define void @main() { > call void @llvm.AMDGPU.reserve.reg(i32 0) > call void @llvm.AMDGPU.reserve.reg(i32 1) > call void @llvm.AMDGPU.reserve.reg(i32 2) > call void @llvm.AMDGPU.reserve.reg(i32 3) > %1 = call float @llvm.AMDGPU.load.const(i32 0) > %2 = bitcast float %1 to i32 > %3 = call float @llvm.AMDGPU.load.const(i32 4) > %4 = insertelement <4 x float> undef, float %3, i32 0 > %5 = call float @llvm.AMDGPU.load.const(i32 5) > %6 = insertelement <4 x float> %4, float %5, i32 1 > %7 = call float @llvm.AMDGPU.load.const(i32 6) > %8 = insertelement <4 x float> %6, float %7, i32 2 > %9 = call float @llvm.AMDGPU.load.const(i32 7) > %10 = insertelement <4 x float> %8, float %9, i32 3 > %11 = call float @llvm.R600.load.input(i32 4) > %12 = insertelement <4 x float> undef, float %11, i32 0 > %13 = call float @llvm.R600.load.input(i32 5) > %14 = insertelement <4 x float> %12, float %13, i32 1 > %15 = call float @llvm.R600.load.input(i32 6) > %16 = insertelement <4 x float> %14, float %15, i32 2 > %17 = call float @llvm.R600.load.input(i32 7) > %18 = insertelement <4 x float> %16, float %17, i32 3 > %19 = shufflevector <4 x float> %10, <4 x float> %10, <1 x i32> <i32 1> > %20 = extractelement <1 x float> %19, i32 0 > %21 = insertelement <1 x float> undef, float %20, i32 0 > %22 = shufflevector <1 x float> undef, <1 x float> %21, <1 x i32> <i32 1> > %23 = extractelement <1 x float> %22, i32 0 > %24 = shufflevector <4 x float> undef, <4 x float> %10, <4 x i32> <i32 4, i32 5, i32 6, i32 7> > br label %25 > > ; <label>:25 ; preds = %41, %0 > %26 = phi float [ %45, %41 ], [ undef, %0 ] > %27 = phi float [ %50, %41 ], [ %23, %0 ] > %28 = phi <4 x float> [ %53, %41 ], [ %24, %0 ] > %29 = phi i32 [ %58, %41 ], [ 0, %0 ] > %30 = icmp sge i32 %29, %2 > br i1 %30, label %31, label %41 > > ; <label>:31 ; preds = %25 > %32 = shufflevector <4 x float> undef, <4 x float> %18, <4 x i32> <i32 4, i32 5, i32 6, i32 7> > %33 = extractelement <4 x float> %28, i32 0 > call void @llvm.AMDGPU.store.output(float %33, i32 8) > %34 = extractelement <4 x float> %28, i32 1 > call void @llvm.AMDGPU.store.output(float %34, i32 9) > %35 = extractelement <4 x float> %28, i32 2 > call void @llvm.AMDGPU.store.output(float %35, i32 10) > %36 = extractelement <4 x float> %28, i32 3 > call void @llvm.AMDGPU.store.output(float %36, i32 11) > %37 = extractelement <4 x float> %32, i32 0 > call void @llvm.AMDGPU.store.output(float %37, i32 4) > %38 = extractelement <4 x float> %32, i32 1 > call void @llvm.AMDGPU.store.output(float %38, i32 5) > %39 = extractelement <4 x float> %32, i32 2 > call void @llvm.AMDGPU.store.output(float %39, i32 6) > %40 = extractelement <4 x float> %32, i32 3 > call void @llvm.AMDGPU.store.output(float %40, i32 7) > ret void > > ; <label>:41 ; preds = %25 > %42 = insertelement <1 x float> undef, float %27, i32 0 > %43 = insertelement <1 x float> undef, float %26, i32 0 > %44 = shufflevector <1 x float> %43, <1 x float> %42, <1 x i32> <i32 1> > %45 = extractelement <1 x float> %44, i32 0 > %46 = shufflevector <4 x float> %28, <4 x float> %28, <1 x i32> <i32 2> > %47 = extractelement <1 x float> %46, i32 0 > %48 = insertelement <1 x float> undef, float %47, i32 0 > %49 = shufflevector <1 x float> %42, <1 x float> %48, <1 x i32> <i32 1> > %50 = extractelement <1 x float> %49, i32 0 > %51 = insertelement <1 x float> undef, float %45, i32 0 > %52 = shufflevector <1 x float> %51, <1 x float> %51, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef> > %53 = shufflevector <4 x float> %28, <4 x float> %52, <4 x i32> <i32 0, i32 1, i32 4, i32 3> > %54 = add i32 %29, 1 > %55 = insertelement <1 x i32> undef, i32 %54, i32 0 > %56 = insertelement <1 x i32> undef, i32 %29, i32 0 > %57 = shufflevector <1 x i32> %56, <1 x i32> %55, <1 x i32> <i32 1> > %58 = extractelement <1 x i32> %57, i32 0 > br label %25 > } > *** IR Dump Before Remove unreachable blocks from the CFG *** > define void @main() { > call void @llvm.AMDGPU.reserve.reg(i32 0) > call void @llvm.AMDGPU.reserve.reg(i32 1) > call void @llvm.AMDGPU.reserve.reg(i32 2) > call void @llvm.AMDGPU.reserve.reg(i32 3) > %1 = call float @llvm.AMDGPU.load.const(i32 0) > %2 = bitcast float %1 to i32 > %3 = call float @llvm.AMDGPU.load.const(i32 4) > %4 = insertelement <4 x float> undef, float %3, i32 0 > %5 = call float @llvm.AMDGPU.load.const(i32 5) > %6 = insertelement <4 x float> %4, float %5, i32 1 > %7 = call float @llvm.AMDGPU.load.const(i32 6) > %8 = insertelement <4 x float> %6, float %7, i32 2 > %9 = call float @llvm.AMDGPU.load.const(i32 7) > %10 = insertelement <4 x float> %8, float %9, i32 3 > %11 = call float @llvm.R600.load.input(i32 4) > %12 = insertelement <4 x float> undef, float %11, i32 0 > %13 = call float @llvm.R600.load.input(i32 5) > %14 = insertelement <4 x float> %12, float %13, i32 1 > %15 = call float @llvm.R600.load.input(i32 6) > %16 = insertelement <4 x float> %14, float %15, i32 2 > %17 = call float @llvm.R600.load.input(i32 7) > %18 = insertelement <4 x float> %16, float %17, i32 3 > %19 = shufflevector <4 x float> %10, <4 x float> %10, <1 x i32> <i32 1> > %20 = extractelement <1 x float> %19, i32 0 > %21 = insertelement <1 x float> undef, float %20, i32 0 > %22 = shufflevector <1 x float> undef, <1 x float> %21, <1 x i32> <i32 1> > %23 = extractelement <1 x float> %22, i32 0 > %24 = shufflevector <4 x float> undef, <4 x float> %10, <4 x i32> <i32 4, i32 5, i32 6, i32 7> > br label %25 > > ; <label>:25 ; preds = %41, %0 > %26 = phi float [ %45, %41 ], [ undef, %0 ] > %27 = phi float [ %50, %41 ], [ %23, %0 ] > %28 = phi <4 x float> [ %53, %41 ], [ %24, %0 ] > %29 = phi i32 [ %58, %41 ], [ 0, %0 ] > %30 = icmp sge i32 %29, %2 > br i1 %30, label %31, label %41 > > ; <label>:31 ; preds = %25 > %32 = shufflevector <4 x float> undef, <4 x float> %18, <4 x i32> <i32 4, i32 5, i32 6, i32 7> > %33 = extractelement <4 x float> %28, i32 0 > call void @llvm.AMDGPU.store.output(float %33, i32 8) > %34 = extractelement <4 x float> %28, i32 1 > call void @llvm.AMDGPU.store.output(float %34, i32 9) > %35 = extractelement <4 x float> %28, i32 2 > call void @llvm.AMDGPU.store.output(float %35, i32 10) > %36 = extractelement <4 x float> %28, i32 3 > call void @llvm.AMDGPU.store.output(float %36, i32 11) > %37 = extractelement <4 x float> %32, i32 0 > call void @llvm.AMDGPU.store.output(float %37, i32 4) > %38 = extractelement <4 x float> %32, i32 1 > call void @llvm.AMDGPU.store.output(float %38, i32 5) > %39 = extractelement <4 x float> %32, i32 2 > call void @llvm.AMDGPU.store.output(float %39, i32 6) > %40 = extractelement <4 x float> %32, i32 3 > call void @llvm.AMDGPU.store.output(float %40, i32 7) > ret void > > ; <label>:41 ; preds = %25 > %42 = insertelement <1 x float> undef, float %27, i32 0 > %43 = insertelement <1 x float> undef, float %26, i32 0 > %44 = shufflevector <1 x float> %43, <1 x float> %42, <1 x i32> <i32 1> > %45 = extractelement <1 x float> %44, i32 0 > %46 = shufflevector <4 x float> %28, <4 x float> %28, <1 x i32> <i32 2> > %47 = extractelement <1 x float> %46, i32 0 > %48 = insertelement <1 x float> undef, float %47, i32 0 > %49 = shufflevector <1 x float> %42, <1 x float> %48, <1 x i32> <i32 1> > %50 = extractelement <1 x float> %49, i32 0 > %51 = insertelement <1 x float> undef, float %45, i32 0 > %52 = shufflevector <1 x float> %51, <1 x float> %51, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef> > %53 = shufflevector <4 x float> %28, <4 x float> %52, <4 x i32> <i32 0, i32 1, i32 4, i32 3> > %54 = add i32 %29, 1 > %55 = insertelement <1 x i32> undef, i32 %54, i32 0 > %56 = insertelement <1 x i32> undef, i32 %29, i32 0 > %57 = shufflevector <1 x i32> %56, <1 x i32> %55, <1 x i32> <i32 1> > %58 = extractelement <1 x i32> %57, i32 0 > br label %25 > } > *** IR Dump Before Optimize for code generation *** > define void @main() { > call void @llvm.AMDGPU.reserve.reg(i32 0) > call void @llvm.AMDGPU.reserve.reg(i32 1) > call void @llvm.AMDGPU.reserve.reg(i32 2) > call void @llvm.AMDGPU.reserve.reg(i32 3) > %1 = call float @llvm.AMDGPU.load.const(i32 0) > %2 = bitcast float %1 to i32 > %3 = call float @llvm.AMDGPU.load.const(i32 4) > %4 = insertelement <4 x float> undef, float %3, i32 0 > %5 = call float @llvm.AMDGPU.load.const(i32 5) > %6 = insertelement <4 x float> %4, float %5, i32 1 > %7 = call float @llvm.AMDGPU.load.const(i32 6) > %8 = insertelement <4 x float> %6, float %7, i32 2 > %9 = call float @llvm.AMDGPU.load.const(i32 7) > %10 = insertelement <4 x float> %8, float %9, i32 3 > %11 = call float @llvm.R600.load.input(i32 4) > %12 = insertelement <4 x float> undef, float %11, i32 0 > %13 = call float @llvm.R600.load.input(i32 5) > %14 = insertelement <4 x float> %12, float %13, i32 1 > %15 = call float @llvm.R600.load.input(i32 6) > %16 = insertelement <4 x float> %14, float %15, i32 2 > %17 = call float @llvm.R600.load.input(i32 7) > %18 = insertelement <4 x float> %16, float %17, i32 3 > %19 = shufflevector <4 x float> %10, <4 x float> %10, <1 x i32> <i32 1> > %20 = extractelement <1 x float> %19, i32 0 > %21 = insertelement <1 x float> undef, float %20, i32 0 > %22 = shufflevector <1 x float> undef, <1 x float> %21, <1 x i32> <i32 1> > %23 = extractelement <1 x float> %22, i32 0 > %24 = shufflevector <4 x float> undef, <4 x float> %10, <4 x i32> <i32 4, i32 5, i32 6, i32 7> > br label %25 > > ; <label>:25 ; preds = %41, %0 > %26 = phi float [ %45, %41 ], [ undef, %0 ] > %27 = phi float [ %50, %41 ], [ %23, %0 ] > %28 = phi <4 x float> [ %53, %41 ], [ %24, %0 ] > %29 = phi i32 [ %58, %41 ], [ 0, %0 ] > %30 = icmp sge i32 %29, %2 > br i1 %30, label %31, label %41 > > ; <label>:31 ; preds = %25 > %32 = shufflevector <4 x float> undef, <4 x float> %18, <4 x i32> <i32 4, i32 5, i32 6, i32 7> > %33 = extractelement <4 x float> %28, i32 0 > call void @llvm.AMDGPU.store.output(float %33, i32 8) > %34 = extractelement <4 x float> %28, i32 1 > call void @llvm.AMDGPU.store.output(float %34, i32 9) > %35 = extractelement <4 x float> %28, i32 2 > call void @llvm.AMDGPU.store.output(float %35, i32 10) > %36 = extractelement <4 x float> %28, i32 3 > call void @llvm.AMDGPU.store.output(float %36, i32 11) > %37 = extractelement <4 x float> %32, i32 0 > call void @llvm.AMDGPU.store.output(float %37, i32 4) > %38 = extractelement <4 x float> %32, i32 1 > call void @llvm.AMDGPU.store.output(float %38, i32 5) > %39 = extractelement <4 x float> %32, i32 2 > call void @llvm.AMDGPU.store.output(float %39, i32 6) > %40 = extractelement <4 x float> %32, i32 3 > call void @llvm.AMDGPU.store.output(float %40, i32 7) > ret void > > ; <label>:41 ; preds = %25 > %42 = insertelement <1 x float> undef, float %27, i32 0 > %43 = insertelement <1 x float> undef, float %26, i32 0 > %44 = shufflevector <1 x float> %43, <1 x float> %42, <1 x i32> <i32 1> > %45 = extractelement <1 x float> %44, i32 0 > %46 = shufflevector <4 x float> %28, <4 x float> %28, <1 x i32> <i32 2> > %47 = extractelement <1 x float> %46, i32 0 > %48 = insertelement <1 x float> undef, float %47, i32 0 > %49 = shufflevector <1 x float> %42, <1 x float> %48, <1 x i32> <i32 1> > %50 = extractelement <1 x float> %49, i32 0 > %51 = insertelement <1 x float> undef, float %45, i32 0 > %52 = shufflevector <1 x float> %51, <1 x float> %51, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef> > %53 = shufflevector <4 x float> %28, <4 x float> %52, <4 x i32> <i32 0, i32 1, i32 4, i32 3> > %54 = add i32 %29, 1 > %55 = insertelement <1 x i32> undef, i32 %54, i32 0 > %56 = insertelement <1 x i32> undef, i32 %29, i32 0 > %57 = shufflevector <1 x i32> %56, <1 x i32> %55, <1 x i32> <i32 1> > %58 = extractelement <1 x i32> %57, i32 0 > br label %25 > } > *** IR Dump Before Insert stack protectors *** > define void @main() { > call void @llvm.AMDGPU.reserve.reg(i32 0) > call void @llvm.AMDGPU.reserve.reg(i32 1) > call void @llvm.AMDGPU.reserve.reg(i32 2) > call void @llvm.AMDGPU.reserve.reg(i32 3) > %1 = call float @llvm.AMDGPU.load.const(i32 0) > %2 = bitcast float %1 to i32 > %3 = call float @llvm.AMDGPU.load.const(i32 4) > %4 = insertelement <4 x float> undef, float %3, i32 0 > %5 = call float @llvm.AMDGPU.load.const(i32 5) > %6 = insertelement <4 x float> %4, float %5, i32 1 > %7 = call float @llvm.AMDGPU.load.const(i32 6) > %8 = insertelement <4 x float> %6, float %7, i32 2 > %9 = call float @llvm.AMDGPU.load.const(i32 7) > %10 = insertelement <4 x float> %8, float %9, i32 3 > %11 = call float @llvm.R600.load.input(i32 4) > %12 = insertelement <4 x float> undef, float %11, i32 0 > %13 = call float @llvm.R600.load.input(i32 5) > %14 = insertelement <4 x float> %12, float %13, i32 1 > %15 = call float @llvm.R600.load.input(i32 6) > %16 = insertelement <4 x float> %14, float %15, i32 2 > %17 = call float @llvm.R600.load.input(i32 7) > %18 = insertelement <4 x float> %16, float %17, i32 3 > %19 = shufflevector <4 x float> %10, <4 x float> %10, <1 x i32> <i32 1> > %20 = extractelement <1 x float> %19, i32 0 > %21 = insertelement <1 x float> undef, float %20, i32 0 > %22 = shufflevector <1 x float> undef, <1 x float> %21, <1 x i32> <i32 1> > %23 = extractelement <1 x float> %22, i32 0 > %24 = shufflevector <4 x float> undef, <4 x float> %10, <4 x i32> <i32 4, i32 5, i32 6, i32 7> > br label %25 > > ; <label>:25 ; preds = %41, %0 > %26 = phi float [ %45, %41 ], [ undef, %0 ] > %27 = phi float [ %50, %41 ], [ %23, %0 ] > %28 = phi <4 x float> [ %53, %41 ], [ %24, %0 ] > %29 = phi i32 [ %58, %41 ], [ 0, %0 ] > %30 = icmp sge i32 %29, %2 > br i1 %30, label %31, label %41 > > ; <label>:31 ; preds = %25 > %32 = shufflevector <4 x float> undef, <4 x float> %18, <4 x i32> <i32 4, i32 5, i32 6, i32 7> > %33 = extractelement <4 x float> %28, i32 0 > call void @llvm.AMDGPU.store.output(float %33, i32 8) > %34 = extractelement <4 x float> %28, i32 1 > call void @llvm.AMDGPU.store.output(float %34, i32 9) > %35 = extractelement <4 x float> %28, i32 2 > call void @llvm.AMDGPU.store.output(float %35, i32 10) > %36 = extractelement <4 x float> %28, i32 3 > call void @llvm.AMDGPU.store.output(float %36, i32 11) > %37 = extractelement <4 x float> %32, i32 0 > call void @llvm.AMDGPU.store.output(float %37, i32 4) > %38 = extractelement <4 x float> %32, i32 1 > call void @llvm.AMDGPU.store.output(float %38, i32 5) > %39 = extractelement <4 x float> %32, i32 2 > call void @llvm.AMDGPU.store.output(float %39, i32 6) > %40 = extractelement <4 x float> %32, i32 3 > call void @llvm.AMDGPU.store.output(float %40, i32 7) > ret void > > ; <label>:41 ; preds = %25 > %42 = insertelement <1 x float> undef, float %27, i32 0 > %43 = insertelement <1 x float> undef, float %26, i32 0 > %44 = shufflevector <1 x float> %43, <1 x float> %42, <1 x i32> <i32 1> > %45 = extractelement <1 x float> %44, i32 0 > %46 = shufflevector <4 x float> %28, <4 x float> %28, <1 x i32> <i32 2> > %47 = extractelement <1 x float> %46, i32 0 > %48 = insertelement <1 x float> undef, float %47, i32 0 > %49 = shufflevector <1 x float> %42, <1 x float> %48, <1 x i32> <i32 1> > %50 = extractelement <1 x float> %49, i32 0 > %51 = insertelement <1 x float> undef, float %45, i32 0 > %52 = shufflevector <1 x float> %51, <1 x float> %51, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef> > %53 = shufflevector <4 x float> %28, <4 x float> %52, <4 x i32> <i32 0, i32 1, i32 4, i32 3> > %54 = add i32 %29, 1 > %55 = insertelement <1 x i32> undef, i32 %54, i32 0 > %56 = insertelement <1 x i32> undef, i32 %29, i32 0 > %57 = shufflevector <1 x i32> %56, <1 x i32> %55, <1 x i32> <i32 1> > %58 = extractelement <1 x i32> %57, i32 0 > br label %25 > } > *** IR Dump Before Preliminary module verification *** > define void @main() { > call void @llvm.AMDGPU.reserve.reg(i32 0) > call void @llvm.AMDGPU.reserve.reg(i32 1) > call void @llvm.AMDGPU.reserve.reg(i32 2) > call void @llvm.AMDGPU.reserve.reg(i32 3) > %1 = call float @llvm.AMDGPU.load.const(i32 0) > %2 = bitcast float %1 to i32 > %3 = call float @llvm.AMDGPU.load.const(i32 4) > %4 = insertelement <4 x float> undef, float %3, i32 0 > %5 = call float @llvm.AMDGPU.load.const(i32 5) > %6 = insertelement <4 x float> %4, float %5, i32 1 > %7 = call float @llvm.AMDGPU.load.const(i32 6) > %8 = insertelement <4 x float> %6, float %7, i32 2 > %9 = call float @llvm.AMDGPU.load.const(i32 7) > %10 = insertelement <4 x float> %8, float %9, i32 3 > %11 = call float @llvm.R600.load.input(i32 4) > %12 = insertelement <4 x float> undef, float %11, i32 0 > %13 = call float @llvm.R600.load.input(i32 5) > %14 = insertelement <4 x float> %12, float %13, i32 1 > %15 = call float @llvm.R600.load.input(i32 6) > %16 = insertelement <4 x float> %14, float %15, i32 2 > %17 = call float @llvm.R600.load.input(i32 7) > %18 = insertelement <4 x float> %16, float %17, i32 3 > %19 = shufflevector <4 x float> %10, <4 x float> %10, <1 x i32> <i32 1> > %20 = extractelement <1 x float> %19, i32 0 > %21 = insertelement <1 x float> undef, float %20, i32 0 > %22 = shufflevector <1 x float> undef, <1 x float> %21, <1 x i32> <i32 1> > %23 = extractelement <1 x float> %22, i32 0 > %24 = shufflevector <4 x float> undef, <4 x float> %10, <4 x i32> <i32 4, i32 5, i32 6, i32 7> > br label %25 > > ; <label>:25 ; preds = %41, %0 > %26 = phi float [ %45, %41 ], [ undef, %0 ] > %27 = phi float [ %50, %41 ], [ %23, %0 ] > %28 = phi <4 x float> [ %53, %41 ], [ %24, %0 ] > %29 = phi i32 [ %58, %41 ], [ 0, %0 ] > %30 = icmp sge i32 %29, %2 > br i1 %30, label %31, label %41 > > ; <label>:31 ; preds = %25 > %32 = shufflevector <4 x float> undef, <4 x float> %18, <4 x i32> <i32 4, i32 5, i32 6, i32 7> > %33 = extractelement <4 x float> %28, i32 0 > call void @llvm.AMDGPU.store.output(float %33, i32 8) > %34 = extractelement <4 x float> %28, i32 1 > call void @llvm.AMDGPU.store.output(float %34, i32 9) > %35 = extractelement <4 x float> %28, i32 2 > call void @llvm.AMDGPU.store.output(float %35, i32 10) > %36 = extractelement <4 x float> %28, i32 3 > call void @llvm.AMDGPU.store.output(float %36, i32 11) > %37 = extractelement <4 x float> %32, i32 0 > call void @llvm.AMDGPU.store.output(float %37, i32 4) > %38 = extractelement <4 x float> %32, i32 1 > call void @llvm.AMDGPU.store.output(float %38, i32 5) > %39 = extractelement <4 x float> %32, i32 2 > call void @llvm.AMDGPU.store.output(float %39, i32 6) > %40 = extractelement <4 x float> %32, i32 3 > call void @llvm.AMDGPU.store.output(float %40, i32 7) > ret void > > ; <label>:41 ; preds = %25 > %42 = insertelement <1 x float> undef, float %27, i32 0 > %43 = insertelement <1 x float> undef, float %26, i32 0 > %44 = shufflevector <1 x float> %43, <1 x float> %42, <1 x i32> <i32 1> > %45 = extractelement <1 x float> %44, i32 0 > %46 = shufflevector <4 x float> %28, <4 x float> %28, <1 x i32> <i32 2> > %47 = extractelement <1 x float> %46, i32 0 > %48 = insertelement <1 x float> undef, float %47, i32 0 > %49 = shufflevector <1 x float> %42, <1 x float> %48, <1 x i32> <i32 1> > %50 = extractelement <1 x float> %49, i32 0 > %51 = insertelement <1 x float> undef, float %45, i32 0 > %52 = shufflevector <1 x float> %51, <1 x float> %51, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef> > %53 = shufflevector <4 x float> %28, <4 x float> %52, <4 x i32> <i32 0, i32 1, i32 4, i32 3> > %54 = add i32 %29, 1 > %55 = insertelement <1 x i32> undef, i32 %54, i32 0 > %56 = insertelement <1 x i32> undef, i32 %29, i32 0 > %57 = shufflevector <1 x i32> %56, <1 x i32> %55, <1 x i32> <i32 1> > %58 = extractelement <1 x i32> %57, i32 0 > br label %25 > } > *** IR Dump Before Module Verifier *** > define void @main() { > call void @llvm.AMDGPU.reserve.reg(i32 0) > call void @llvm.AMDGPU.reserve.reg(i32 1) > call void @llvm.AMDGPU.reserve.reg(i32 2) > call void @llvm.AMDGPU.reserve.reg(i32 3) > %1 = call float @llvm.AMDGPU.load.const(i32 0) > %2 = bitcast float %1 to i32 > %3 = call float @llvm.AMDGPU.load.const(i32 4) > %4 = insertelement <4 x float> undef, float %3, i32 0 > %5 = call float @llvm.AMDGPU.load.const(i32 5) > %6 = insertelement <4 x float> %4, float %5, i32 1 > %7 = call float @llvm.AMDGPU.load.const(i32 6) > %8 = insertelement <4 x float> %6, float %7, i32 2 > %9 = call float @llvm.AMDGPU.load.const(i32 7) > %10 = insertelement <4 x float> %8, float %9, i32 3 > %11 = call float @llvm.R600.load.input(i32 4) > %12 = insertelement <4 x float> undef, float %11, i32 0 > %13 = call float @llvm.R600.load.input(i32 5) > %14 = insertelement <4 x float> %12, float %13, i32 1 > %15 = call float @llvm.R600.load.input(i32 6) > %16 = insertelement <4 x float> %14, float %15, i32 2 > %17 = call float @llvm.R600.load.input(i32 7) > %18 = insertelement <4 x float> %16, float %17, i32 3 > %19 = shufflevector <4 x float> %10, <4 x float> %10, <1 x i32> <i32 1> > %20 = extractelement <1 x float> %19, i32 0 > %21 = insertelement <1 x float> undef, float %20, i32 0 > %22 = shufflevector <1 x float> undef, <1 x float> %21, <1 x i32> <i32 1> > %23 = extractelement <1 x float> %22, i32 0 > %24 = shufflevector <4 x float> undef, <4 x float> %10, <4 x i32> <i32 4, i32 5, i32 6, i32 7> > br label %25 > > ; <label>:25 ; preds = %41, %0 > %26 = phi float [ %45, %41 ], [ undef, %0 ] > %27 = phi float [ %50, %41 ], [ %23, %0 ] > %28 = phi <4 x float> [ %53, %41 ], [ %24, %0 ] > %29 = phi i32 [ %58, %41 ], [ 0, %0 ] > %30 = icmp sge i32 %29, %2 > br i1 %30, label %31, label %41 > > ; <label>:31 ; preds = %25 > %32 = shufflevector <4 x float> undef, <4 x float> %18, <4 x i32> <i32 4, i32 5, i32 6, i32 7> > %33 = extractelement <4 x float> %28, i32 0 > call void @llvm.AMDGPU.store.output(float %33, i32 8) > %34 = extractelement <4 x float> %28, i32 1 > call void @llvm.AMDGPU.store.output(float %34, i32 9) > %35 = extractelement <4 x float> %28, i32 2 > call void @llvm.AMDGPU.store.output(float %35, i32 10) > %36 = extractelement <4 x float> %28, i32 3 > call void @llvm.AMDGPU.store.output(float %36, i32 11) > %37 = extractelement <4 x float> %32, i32 0 > call void @llvm.AMDGPU.store.output(float %37, i32 4) > %38 = extractelement <4 x float> %32, i32 1 > call void @llvm.AMDGPU.store.output(float %38, i32 5) > %39 = extractelement <4 x float> %32, i32 2 > call void @llvm.AMDGPU.store.output(float %39, i32 6) > %40 = extractelement <4 x float> %32, i32 3 > call void @llvm.AMDGPU.store.output(float %40, i32 7) > ret void > > ; <label>:41 ; preds = %25 > %42 = insertelement <1 x float> undef, float %27, i32 0 > %43 = insertelement <1 x float> undef, float %26, i32 0 > %44 = shufflevector <1 x float> %43, <1 x float> %42, <1 x i32> <i32 1> > %45 = extractelement <1 x float> %44, i32 0 > %46 = shufflevector <4 x float> %28, <4 x float> %28, <1 x i32> <i32 2> > %47 = extractelement <1 x float> %46, i32 0 > %48 = insertelement <1 x float> undef, float %47, i32 0 > %49 = shufflevector <1 x float> %42, <1 x float> %48, <1 x i32> <i32 1> > %50 = extractelement <1 x float> %49, i32 0 > %51 = insertelement <1 x float> undef, float %45, i32 0 > %52 = shufflevector <1 x float> %51, <1 x float> %51, <4 x i32> <i32 0, i32 undef, i32 undef, i32 undef> > %53 = shufflevector <4 x float> %28, <4 x float> %52, <4 x i32> <i32 0, i32 1, i32 4, i32 3> > %54 = add i32 %29, 1 > %55 = insertelement <1 x i32> undef, i32 %54, i32 0 > %56 = insertelement <1 x i32> undef, i32 %29, i32 0 > %57 = shufflevector <1 x i32> %56, <1 x i32> %55, <1 x i32> <i32 1> > %58 = extractelement <1 x i32> %57, i32 0 > br label %25 > } > # *** IR Dump Before Expand ISel Pseudo-instructions ***: > # Machine code for function main: SSA > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > BB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > %vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17 > %vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16 > %vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15 > %vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14 > %vreg18<def> = R600_LOAD_CONST 4; R600_Reg32:%vreg18 > %vreg20<def> = IMPLICIT_DEF; R600_Reg128:%vreg20 > %vreg19<def,tied1> = INSERT_SUBREG %vreg20<tied0>, %vreg14, sel_x; R600_Reg128:%vreg19,%vreg20 R600_TReg32:%vreg14 > %vreg2<def> = R600_LOAD_CONST 5; R600_Reg32:%vreg2 > %vreg22<def> = IMPLICIT_DEF; R600_Reg128:%vreg22 > %vreg21<def,tied1> = INSERT_SUBREG %vreg22<tied0>, %vreg18<kill>, sel_x; R600_Reg128:%vreg21,%vreg22 R600_Reg32:%vreg18 > RESERVE_REG 0 > %vreg23<def,tied1> = INSERT_SUBREG %vreg19<tied0>, %vreg15, sel_y; R600_Reg128:%vreg23,%vreg19 R600_TReg32:%vreg15 > %vreg24<def,tied1> = INSERT_SUBREG %vreg21<tied0>, %vreg2, sel_y; R600_Reg128:%vreg24,%vreg21 R600_Reg32:%vreg2 > %vreg25<def> = R600_LOAD_CONST 6; R600_Reg32:%vreg25 > %vreg26<def,tied1> = INSERT_SUBREG %vreg23<tied0>, %vreg16, sel_z; R600_Reg128:%vreg26,%vreg23 R600_TReg32:%vreg16 > RESERVE_REG 1 > %vreg27<def,tied1> = INSERT_SUBREG %vreg24<tied0>, %vreg25<kill>, sel_z; R600_Reg128:%vreg27,%vreg24 R600_Reg32:%vreg25 > %vreg28<def> = R600_LOAD_CONST 7; R600_Reg32:%vreg28 > RESERVE_REG 2 > %vreg3<def,tied1> = INSERT_SUBREG %vreg27<tied0>, %vreg28<kill>, sel_w; R600_Reg128:%vreg3,%vreg27 R600_Reg32:%vreg28 > %vreg1<def,tied1> = INSERT_SUBREG %vreg26<tied0>, %vreg17, sel_w; R600_Reg128:%vreg1,%vreg26 R600_TReg32:%vreg17 > %vreg13<def> = MOV_IMM_I32 0; R600_Reg32:%vreg13 > %vreg0<def> = R600_LOAD_CONST 0; R600_Reg32:%vreg0 > %vreg12<def> = IMPLICIT_DEF; R600_Reg32:%vreg12 > RESERVE_REG 3 > Successors according to CFG: BB#1 > > BB#1: derived from LLVM BB %25 > Predecessors according to CFG: BB#0 BB#3 > %vreg4<def> = PHI %vreg12, <BB#0>, %vreg8, <BB#3>; R600_Reg32:%vreg4,%vreg12,%vreg8 > %vreg5<def> = PHI %vreg2, <BB#0>, %vreg9, <BB#3>; R600_Reg32:%vreg5,%vreg2,%vreg9 > %vreg6<def> = PHI %vreg3, <BB#0>, %vreg10, <BB#3>; R600_Reg128:%vreg6,%vreg3,%vreg10 > %vreg7<def> = PHI %vreg13, <BB#0>, %vreg11, <BB#3>; R600_Reg32:%vreg7,%vreg13,%vreg11 > %vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7 > %vreg30<def> = COPY %vreg29; GPRI32:%vreg30 R600_Reg32:%vreg29 > BRANCH_COND_i32 <BB#3>, %vreg30<kill>; GPRI32:%vreg30 > BRANCH <BB#2> > Successors according to CFG: BB#2(4) BB#3(124) > > BB#2: derived from LLVM BB %31 > Predecessors according to CFG: BB#1 > %vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6 > %T2_X<def> = COPY %vreg39; R600_Reg32:%vreg39 > %vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6 > %T2_Y<def> = COPY %vreg40; R600_Reg32:%vreg40 > %vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6 > %T2_Z<def> = COPY %vreg41; R600_Reg32:%vreg41 > %vreg42<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg42 R600_Reg128:%vreg6 > %T2_W<def> = COPY %vreg42; R600_Reg32:%vreg42 > %vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1 > %T1_X<def> = COPY %vreg43; R600_Reg32:%vreg43 > %vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1 > %T1_Y<def> = COPY %vreg44; R600_Reg32:%vreg44 > %vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1 > %T1_Z<def> = COPY %vreg45; R600_Reg32:%vreg45 > %vreg46<def> = COPY %vreg1:sel_w; R600_Reg32:%vreg46 R600_Reg128:%vreg1 > %T1_W<def> = COPY %vreg46; R600_Reg32:%vreg46 > RETURN > > BB#3: derived from LLVM BB %41 > Predecessors according to CFG: BB#1 > %vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6 > %vreg33<def> = IMPLICIT_DEF; R600_Reg128:%vreg33 > %vreg32<def,tied1> = INSERT_SUBREG %vreg33<tied0>, %vreg31<kill>, sel_x; R600_Reg128:%vreg32,%vreg33 R600_Reg32:%vreg31 > %vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6 > %vreg35<def,tied1> = INSERT_SUBREG %vreg32<tied0>, %vreg34<kill>, sel_y; R600_Reg128:%vreg35,%vreg32 R600_Reg32:%vreg34 > %vreg36<def,tied1> = INSERT_SUBREG %vreg35<tied0>, %vreg5, sel_z; R600_Reg128:%vreg36,%vreg35 R600_Reg32:%vreg5 > %vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6 > %vreg10<def,tied1> = INSERT_SUBREG %vreg36<tied0>, %vreg37<kill>, sel_w; R600_Reg128:%vreg10,%vreg36 R600_Reg32:%vreg37 > %vreg9<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg6 > %vreg38<def> = MOV_IMM_I32 1; R600_Reg32:%vreg38 > %vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7, 0, 0, 0, %vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg11,%vreg7,%vreg38 > %vreg8<def> = COPY %vreg5; R600_Reg32:%vreg8,%vreg5 > BRANCH <BB#1> > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Tail Duplication ***: > # Machine code for function main: SSA > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > BB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > %vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17 > %vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16 > %vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15 > %vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14 > %vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18 > %vreg20<def> = IMPLICIT_DEF; R600_Reg128:%vreg20 > %vreg19<def,tied1> = INSERT_SUBREG %vreg20<tied0>, %vreg14, sel_x; R600_Reg128:%vreg19,%vreg20 R600_TReg32:%vreg14 > %vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2 > %vreg22<def> = IMPLICIT_DEF; R600_Reg128:%vreg22 > %vreg21<def,tied1> = INSERT_SUBREG %vreg22<tied0>, %vreg18<kill>, sel_x; R600_Reg128:%vreg21,%vreg22 R600_Reg32:%vreg18 > %vreg23<def,tied1> = INSERT_SUBREG %vreg19<tied0>, %vreg15, sel_y; R600_Reg128:%vreg23,%vreg19 R600_TReg32:%vreg15 > %vreg24<def,tied1> = INSERT_SUBREG %vreg21<tied0>, %vreg2, sel_y; R600_Reg128:%vreg24,%vreg21 R600_Reg32:%vreg2 > %vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25 > %vreg26<def,tied1> = INSERT_SUBREG %vreg23<tied0>, %vreg16, sel_z; R600_Reg128:%vreg26,%vreg23 R600_TReg32:%vreg16 > %vreg27<def,tied1> = INSERT_SUBREG %vreg24<tied0>, %vreg25<kill>, sel_z; R600_Reg128:%vreg27,%vreg24 R600_Reg32:%vreg25 > %vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28 > %vreg3<def,tied1> = INSERT_SUBREG %vreg27<tied0>, %vreg28<kill>, sel_w; R600_Reg128:%vreg3,%vreg27 R600_Reg32:%vreg28 > %vreg1<def,tied1> = INSERT_SUBREG %vreg26<tied0>, %vreg17, sel_w; R600_Reg128:%vreg1,%vreg26 R600_TReg32:%vreg17 > %vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13 > %vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0 > %vreg12<def> = IMPLICIT_DEF; R600_Reg32:%vreg12 > Successors according to CFG: BB#1 > > BB#1: derived from LLVM BB %25 > Predecessors according to CFG: BB#0 BB#3 > %vreg4<def> = PHI %vreg12, <BB#0>, %vreg8, <BB#3>; R600_Reg32:%vreg4,%vreg12,%vreg8 > %vreg5<def> = PHI %vreg2, <BB#0>, %vreg9, <BB#3>; R600_Reg32:%vreg5,%vreg2,%vreg9 > %vreg6<def> = PHI %vreg3, <BB#0>, %vreg10, <BB#3>; R600_Reg128:%vreg6,%vreg3,%vreg10 > %vreg7<def> = PHI %vreg13, <BB#0>, %vreg11, <BB#3>; R600_Reg32:%vreg7,%vreg13,%vreg11 > %vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7 > %vreg30<def> = COPY %vreg29; GPRI32:%vreg30 R600_Reg32:%vreg29 > %PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16; GPRI32:%vreg30 > JUMP <BB#3>, pred:%PREDICATE_BIT<kill> > JUMP <BB#2>, pred:%noreg > Successors according to CFG: BB#2(4) BB#3(124) > > BB#2: derived from LLVM BB %31 > Predecessors according to CFG: BB#1 > %vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6 > %T2_X<def> = COPY %vreg39; R600_Reg32:%vreg39 > %vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6 > %T2_Y<def> = COPY %vreg40; R600_Reg32:%vreg40 > %vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6 > %T2_Z<def> = COPY %vreg41; R600_Reg32:%vreg41 > %vreg42<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg42 R600_Reg128:%vreg6 > %T2_W<def> = COPY %vreg42; R600_Reg32:%vreg42 > %vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1 > %T1_X<def> = COPY %vreg43; R600_Reg32:%vreg43 > %vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1 > %T1_Y<def> = COPY %vreg44; R600_Reg32:%vreg44 > %vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1 > %T1_Z<def> = COPY %vreg45; R600_Reg32:%vreg45 > %vreg46<def> = COPY %vreg1:sel_w; R600_Reg32:%vreg46 R600_Reg128:%vreg1 > %T1_W<def> = COPY %vreg46; R600_Reg32:%vreg46 > RETURN > > BB#3: derived from LLVM BB %41 > Predecessors according to CFG: BB#1 > %vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6 > %vreg33<def> = IMPLICIT_DEF; R600_Reg128:%vreg33 > %vreg32<def,tied1> = INSERT_SUBREG %vreg33<tied0>, %vreg31<kill>, sel_x; R600_Reg128:%vreg32,%vreg33 R600_Reg32:%vreg31 > %vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6 > %vreg35<def,tied1> = INSERT_SUBREG %vreg32<tied0>, %vreg34<kill>, sel_y; R600_Reg128:%vreg35,%vreg32 R600_Reg32:%vreg34 > %vreg36<def,tied1> = INSERT_SUBREG %vreg35<tied0>, %vreg5, sel_z; R600_Reg128:%vreg36,%vreg35 R600_Reg32:%vreg5 > %vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6 > %vreg10<def,tied1> = INSERT_SUBREG %vreg36<tied0>, %vreg37<kill>, sel_w; R600_Reg128:%vreg10,%vreg36 R600_Reg32:%vreg37 > %vreg9<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg6 > %vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38 > %vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7, 0, 0, 0, %vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg11,%vreg7,%vreg38 > %vreg8<def> = COPY %vreg5; R600_Reg32:%vreg8,%vreg5 > JUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Optimize machine instruction PHIs ***: > # Machine code for function main: SSA > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > BB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > %vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17 > %vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16 > %vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15 > %vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14 > %vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18 > %vreg20<def> = IMPLICIT_DEF; R600_Reg128:%vreg20 > %vreg19<def,tied1> = INSERT_SUBREG %vreg20<tied0>, %vreg14, sel_x; R600_Reg128:%vreg19,%vreg20 R600_TReg32:%vreg14 > %vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2 > %vreg22<def> = IMPLICIT_DEF; R600_Reg128:%vreg22 > %vreg21<def,tied1> = INSERT_SUBREG %vreg22<tied0>, %vreg18<kill>, sel_x; R600_Reg128:%vreg21,%vreg22 R600_Reg32:%vreg18 > %vreg23<def,tied1> = INSERT_SUBREG %vreg19<tied0>, %vreg15, sel_y; R600_Reg128:%vreg23,%vreg19 R600_TReg32:%vreg15 > %vreg24<def,tied1> = INSERT_SUBREG %vreg21<tied0>, %vreg2, sel_y; R600_Reg128:%vreg24,%vreg21 R600_Reg32:%vreg2 > %vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25 > %vreg26<def,tied1> = INSERT_SUBREG %vreg23<tied0>, %vreg16, sel_z; R600_Reg128:%vreg26,%vreg23 R600_TReg32:%vreg16 > %vreg27<def,tied1> = INSERT_SUBREG %vreg24<tied0>, %vreg25<kill>, sel_z; R600_Reg128:%vreg27,%vreg24 R600_Reg32:%vreg25 > %vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28 > %vreg3<def,tied1> = INSERT_SUBREG %vreg27<tied0>, %vreg28<kill>, sel_w; R600_Reg128:%vreg3,%vreg27 R600_Reg32:%vreg28 > %vreg1<def,tied1> = INSERT_SUBREG %vreg26<tied0>, %vreg17, sel_w; R600_Reg128:%vreg1,%vreg26 R600_TReg32:%vreg17 > %vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13 > %vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0 > %vreg12<def> = IMPLICIT_DEF; R600_Reg32:%vreg12 > Successors according to CFG: BB#1 > > BB#1: derived from LLVM BB %25 > Predecessors according to CFG: BB#0 BB#3 > %vreg4<def> = PHI %vreg12, <BB#0>, %vreg8, <BB#3>; R600_Reg32:%vreg4,%vreg12,%vreg8 > %vreg5<def> = PHI %vreg2, <BB#0>, %vreg9, <BB#3>; R600_Reg32:%vreg5,%vreg2,%vreg9 > %vreg6<def> = PHI %vreg3, <BB#0>, %vreg10, <BB#3>; R600_Reg128:%vreg6,%vreg3,%vreg10 > %vreg7<def> = PHI %vreg13, <BB#0>, %vreg11, <BB#3>; R600_Reg32:%vreg7,%vreg13,%vreg11 > %vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7 > %vreg30<def> = COPY %vreg29; GPRI32:%vreg30 R600_Reg32:%vreg29 > %PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16; GPRI32:%vreg30 > JUMP <BB#3>, pred:%PREDICATE_BIT<kill> > JUMP <BB#2>, pred:%noreg > Successors according to CFG: BB#2(4) BB#3(124) > > BB#2: derived from LLVM BB %31 > Predecessors according to CFG: BB#1 > %vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6 > %T2_X<def> = COPY %vreg39; R600_Reg32:%vreg39 > %vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6 > %T2_Y<def> = COPY %vreg40; R600_Reg32:%vreg40 > %vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6 > %T2_Z<def> = COPY %vreg41; R600_Reg32:%vreg41 > %vreg42<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg42 R600_Reg128:%vreg6 > %T2_W<def> = COPY %vreg42; R600_Reg32:%vreg42 > %vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1 > %T1_X<def> = COPY %vreg43; R600_Reg32:%vreg43 > %vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1 > %T1_Y<def> = COPY %vreg44; R600_Reg32:%vreg44 > %vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1 > %T1_Z<def> = COPY %vreg45; R600_Reg32:%vreg45 > %vreg46<def> = COPY %vreg1:sel_w; R600_Reg32:%vreg46 R600_Reg128:%vreg1 > %T1_W<def> = COPY %vreg46; R600_Reg32:%vreg46 > RETURN > > BB#3: derived from LLVM BB %41 > Predecessors according to CFG: BB#1 > %vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6 > %vreg33<def> = IMPLICIT_DEF; R600_Reg128:%vreg33 > %vreg32<def,tied1> = INSERT_SUBREG %vreg33<tied0>, %vreg31<kill>, sel_x; R600_Reg128:%vreg32,%vreg33 R600_Reg32:%vreg31 > %vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6 > %vreg35<def,tied1> = INSERT_SUBREG %vreg32<tied0>, %vreg34<kill>, sel_y; R600_Reg128:%vreg35,%vreg32 R600_Reg32:%vreg34 > %vreg36<def,tied1> = INSERT_SUBREG %vreg35<tied0>, %vreg5, sel_z; R600_Reg128:%vreg36,%vreg35 R600_Reg32:%vreg5 > %vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6 > %vreg10<def,tied1> = INSERT_SUBREG %vreg36<tied0>, %vreg37<kill>, sel_w; R600_Reg128:%vreg10,%vreg36 R600_Reg32:%vreg37 > %vreg9<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg6 > %vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38 > %vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7, 0, 0, 0, %vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg11,%vreg7,%vreg38 > %vreg8<def> = COPY %vreg5; R600_Reg32:%vreg8,%vreg5 > JUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Slot index numbering ***: > # Machine code for function main: SSA > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > BB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > %vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17 > %vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16 > %vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15 > %vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14 > %vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18 > %vreg20<def> = IMPLICIT_DEF; R600_Reg128:%vreg20 > %vreg19<def,tied1> = INSERT_SUBREG %vreg20<tied0>, %vreg14, sel_x; R600_Reg128:%vreg19,%vreg20 R600_TReg32:%vreg14 > %vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2 > %vreg22<def> = IMPLICIT_DEF; R600_Reg128:%vreg22 > %vreg21<def,tied1> = INSERT_SUBREG %vreg22<tied0>, %vreg18<kill>, sel_x; R600_Reg128:%vreg21,%vreg22 R600_Reg32:%vreg18 > %vreg23<def,tied1> = INSERT_SUBREG %vreg19<tied0>, %vreg15, sel_y; R600_Reg128:%vreg23,%vreg19 R600_TReg32:%vreg15 > %vreg24<def,tied1> = INSERT_SUBREG %vreg21<tied0>, %vreg2, sel_y; R600_Reg128:%vreg24,%vreg21 R600_Reg32:%vreg2 > %vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25 > %vreg26<def,tied1> = INSERT_SUBREG %vreg23<tied0>, %vreg16, sel_z; R600_Reg128:%vreg26,%vreg23 R600_TReg32:%vreg16 > %vreg27<def,tied1> = INSERT_SUBREG %vreg24<tied0>, %vreg25<kill>, sel_z; R600_Reg128:%vreg27,%vreg24 R600_Reg32:%vreg25 > %vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28 > %vreg3<def,tied1> = INSERT_SUBREG %vreg27<tied0>, %vreg28<kill>, sel_w; R600_Reg128:%vreg3,%vreg27 R600_Reg32:%vreg28 > %vreg1<def,tied1> = INSERT_SUBREG %vreg26<tied0>, %vreg17, sel_w; R600_Reg128:%vreg1,%vreg26 R600_TReg32:%vreg17 > %vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13 > %vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0 > %vreg12<def> = IMPLICIT_DEF; R600_Reg32:%vreg12 > Successors according to CFG: BB#1 > > BB#1: derived from LLVM BB %25 > Predecessors according to CFG: BB#0 BB#3 > %vreg5<def> = PHI %vreg2, <BB#0>, %vreg9, <BB#3>; R600_Reg32:%vreg5,%vreg2,%vreg9 > %vreg6<def> = PHI %vreg3, <BB#0>, %vreg10, <BB#3>; R600_Reg128:%vreg6,%vreg3,%vreg10 > %vreg7<def> = PHI %vreg13, <BB#0>, %vreg11, <BB#3>; R600_Reg32:%vreg7,%vreg13,%vreg11 > %vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7 > %vreg30<def> = COPY %vreg29; GPRI32:%vreg30 R600_Reg32:%vreg29 > %PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16; GPRI32:%vreg30 > JUMP <BB#3>, pred:%PREDICATE_BIT<kill> > JUMP <BB#2>, pred:%noreg > Successors according to CFG: BB#2(4) BB#3(124) > > BB#2: derived from LLVM BB %31 > Predecessors according to CFG: BB#1 > %vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6 > %T2_X<def> = COPY %vreg39; R600_Reg32:%vreg39 > %vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6 > %T2_Y<def> = COPY %vreg40; R600_Reg32:%vreg40 > %vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6 > %T2_Z<def> = COPY %vreg41; R600_Reg32:%vreg41 > %vreg42<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg42 R600_Reg128:%vreg6 > %T2_W<def> = COPY %vreg42; R600_Reg32:%vreg42 > %vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1 > %T1_X<def> = COPY %vreg43; R600_Reg32:%vreg43 > %vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1 > %T1_Y<def> = COPY %vreg44; R600_Reg32:%vreg44 > %vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1 > %T1_Z<def> = COPY %vreg45; R600_Reg32:%vreg45 > %vreg46<def> = COPY %vreg1:sel_w; R600_Reg32:%vreg46 R600_Reg128:%vreg1 > %T1_W<def> = COPY %vreg46; R600_Reg32:%vreg46 > RETURN > > BB#3: derived from LLVM BB %41 > Predecessors according to CFG: BB#1 > %vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6 > %vreg33<def> = IMPLICIT_DEF; R600_Reg128:%vreg33 > %vreg32<def,tied1> = INSERT_SUBREG %vreg33<tied0>, %vreg31<kill>, sel_x; R600_Reg128:%vreg32,%vreg33 R600_Reg32:%vreg31 > %vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6 > %vreg35<def,tied1> = INSERT_SUBREG %vreg32<tied0>, %vreg34<kill>, sel_y; R600_Reg128:%vreg35,%vreg32 R600_Reg32:%vreg34 > %vreg36<def,tied1> = INSERT_SUBREG %vreg35<tied0>, %vreg5, sel_z; R600_Reg128:%vreg36,%vreg35 R600_Reg32:%vreg5 > %vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6 > %vreg10<def,tied1> = INSERT_SUBREG %vreg36<tied0>, %vreg37<kill>, sel_w; R600_Reg128:%vreg10,%vreg36 R600_Reg32:%vreg37 > %vreg9<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg6 > %vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38 > %vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7, 0, 0, 0, %vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg11,%vreg7,%vreg38 > %vreg8<def> = COPY %vreg5; R600_Reg32:%vreg8,%vreg5 > JUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Merge disjoint stack slots ***: > # Machine code for function main: SSA > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > 0BBB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > 16B%vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17 > 32B%vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16 > 48B%vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15 > 64B%vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14 > 80B%vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18 > 96B%vreg20<def> = IMPLICIT_DEF; R600_Reg128:%vreg20 > 112B%vreg19<def,tied1> = INSERT_SUBREG %vreg20<tied0>, %vreg14, sel_x; R600_Reg128:%vreg19,%vreg20 R600_TReg32:%vreg14 > 128B%vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2 > 144B%vreg22<def> = IMPLICIT_DEF; R600_Reg128:%vreg22 > 160B%vreg21<def,tied1> = INSERT_SUBREG %vreg22<tied0>, %vreg18<kill>, sel_x; R600_Reg128:%vreg21,%vreg22 R600_Reg32:%vreg18 > 176B%vreg23<def,tied1> = INSERT_SUBREG %vreg19<tied0>, %vreg15, sel_y; R600_Reg128:%vreg23,%vreg19 R600_TReg32:%vreg15 > 192B%vreg24<def,tied1> = INSERT_SUBREG %vreg21<tied0>, %vreg2, sel_y; R600_Reg128:%vreg24,%vreg21 R600_Reg32:%vreg2 > 208B%vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25 > 224B%vreg26<def,tied1> = INSERT_SUBREG %vreg23<tied0>, %vreg16, sel_z; R600_Reg128:%vreg26,%vreg23 R600_TReg32:%vreg16 > 240B%vreg27<def,tied1> = INSERT_SUBREG %vreg24<tied0>, %vreg25<kill>, sel_z; R600_Reg128:%vreg27,%vreg24 R600_Reg32:%vreg25 > 256B%vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28 > 272B%vreg3<def,tied1> = INSERT_SUBREG %vreg27<tied0>, %vreg28<kill>, sel_w; R600_Reg128:%vreg3,%vreg27 R600_Reg32:%vreg28 > 288B%vreg1<def,tied1> = INSERT_SUBREG %vreg26<tied0>, %vreg17, sel_w; R600_Reg128:%vreg1,%vreg26 R600_TReg32:%vreg17 > 304B%vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13 > 320B%vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0 > 336B%vreg12<def> = IMPLICIT_DEF; R600_Reg32:%vreg12 > Successors according to CFG: BB#1 > > 352BBB#1: derived from LLVM BB %25 > Predecessors according to CFG: BB#0 BB#3 > 368B%vreg5<def> = PHI %vreg2, <BB#0>, %vreg9, <BB#3>; R600_Reg32:%vreg5,%vreg2,%vreg9 > 384B%vreg6<def> = PHI %vreg3, <BB#0>, %vreg10, <BB#3>; R600_Reg128:%vreg6,%vreg3,%vreg10 > 400B%vreg7<def> = PHI %vreg13, <BB#0>, %vreg11, <BB#3>; R600_Reg32:%vreg7,%vreg13,%vreg11 > 416B%vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7 > 432B%vreg30<def> = COPY %vreg29; GPRI32:%vreg30 R600_Reg32:%vreg29 > 448B%PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16; GPRI32:%vreg30 > 464BJUMP <BB#3>, pred:%PREDICATE_BIT<kill> > 480BJUMP <BB#2>, pred:%noreg > Successors according to CFG: BB#2(4) BB#3(124) > > 496BBB#2: derived from LLVM BB %31 > Predecessors according to CFG: BB#1 > 512B%vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6 > 528B%T2_X<def> = COPY %vreg39; R600_Reg32:%vreg39 > 544B%vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6 > 560B%T2_Y<def> = COPY %vreg40; R600_Reg32:%vreg40 > 576B%vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6 > 592B%T2_Z<def> = COPY %vreg41; R600_Reg32:%vreg41 > 608B%vreg42<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg42 R600_Reg128:%vreg6 > 624B%T2_W<def> = COPY %vreg42; R600_Reg32:%vreg42 > 640B%vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1 > 656B%T1_X<def> = COPY %vreg43; R600_Reg32:%vreg43 > 672B%vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1 > 688B%T1_Y<def> = COPY %vreg44; R600_Reg32:%vreg44 > 704B%vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1 > 720B%T1_Z<def> = COPY %vreg45; R600_Reg32:%vreg45 > 736B%vreg46<def> = COPY %vreg1:sel_w; R600_Reg32:%vreg46 R600_Reg128:%vreg1 > 752B%T1_W<def> = COPY %vreg46; R600_Reg32:%vreg46 > 768BRETURN > > 784BBB#3: derived from LLVM BB %41 > Predecessors according to CFG: BB#1 > 800B%vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6 > 816B%vreg33<def> = IMPLICIT_DEF; R600_Reg128:%vreg33 > 832B%vreg32<def,tied1> = INSERT_SUBREG %vreg33<tied0>, %vreg31<kill>, sel_x; R600_Reg128:%vreg32,%vreg33 R600_Reg32:%vreg31 > 848B%vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6 > 864B%vreg35<def,tied1> = INSERT_SUBREG %vreg32<tied0>, %vreg34<kill>, sel_y; R600_Reg128:%vreg35,%vreg32 R600_Reg32:%vreg34 > 880B%vreg36<def,tied1> = INSERT_SUBREG %vreg35<tied0>, %vreg5, sel_z; R600_Reg128:%vreg36,%vreg35 R600_Reg32:%vreg5 > 896B%vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6 > 912B%vreg10<def,tied1> = INSERT_SUBREG %vreg36<tied0>, %vreg37<kill>, sel_w; R600_Reg128:%vreg10,%vreg36 R600_Reg32:%vreg37 > 928B%vreg9<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg6 > 944B%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38 > 960B%vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7, 0, 0, 0, %vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg11,%vreg7,%vreg38 > 976B%vreg8<def> = COPY %vreg5; R600_Reg32:%vreg8,%vreg5 > 992BJUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Local Stack Slot Allocation ***: > # Machine code for function main: SSA > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > BB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > %vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17 > %vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16 > %vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15 > %vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14 > %vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18 > %vreg20<def> = IMPLICIT_DEF; R600_Reg128:%vreg20 > %vreg19<def,tied1> = INSERT_SUBREG %vreg20<tied0>, %vreg14, sel_x; R600_Reg128:%vreg19,%vreg20 R600_TReg32:%vreg14 > %vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2 > %vreg22<def> = IMPLICIT_DEF; R600_Reg128:%vreg22 > %vreg21<def,tied1> = INSERT_SUBREG %vreg22<tied0>, %vreg18<kill>, sel_x; R600_Reg128:%vreg21,%vreg22 R600_Reg32:%vreg18 > %vreg23<def,tied1> = INSERT_SUBREG %vreg19<tied0>, %vreg15, sel_y; R600_Reg128:%vreg23,%vreg19 R600_TReg32:%vreg15 > %vreg24<def,tied1> = INSERT_SUBREG %vreg21<tied0>, %vreg2, sel_y; R600_Reg128:%vreg24,%vreg21 R600_Reg32:%vreg2 > %vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25 > %vreg26<def,tied1> = INSERT_SUBREG %vreg23<tied0>, %vreg16, sel_z; R600_Reg128:%vreg26,%vreg23 R600_TReg32:%vreg16 > %vreg27<def,tied1> = INSERT_SUBREG %vreg24<tied0>, %vreg25<kill>, sel_z; R600_Reg128:%vreg27,%vreg24 R600_Reg32:%vreg25 > %vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28 > %vreg3<def,tied1> = INSERT_SUBREG %vreg27<tied0>, %vreg28<kill>, sel_w; R600_Reg128:%vreg3,%vreg27 R600_Reg32:%vreg28 > %vreg1<def,tied1> = INSERT_SUBREG %vreg26<tied0>, %vreg17, sel_w; R600_Reg128:%vreg1,%vreg26 R600_TReg32:%vreg17 > %vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13 > %vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0 > %vreg12<def> = IMPLICIT_DEF; R600_Reg32:%vreg12 > Successors according to CFG: BB#1 > > BB#1: derived from LLVM BB %25 > Predecessors according to CFG: BB#0 BB#3 > %vreg5<def> = PHI %vreg2, <BB#0>, %vreg9, <BB#3>; R600_Reg32:%vreg5,%vreg2,%vreg9 > %vreg6<def> = PHI %vreg3, <BB#0>, %vreg10, <BB#3>; R600_Reg128:%vreg6,%vreg3,%vreg10 > %vreg7<def> = PHI %vreg13, <BB#0>, %vreg11, <BB#3>; R600_Reg32:%vreg7,%vreg13,%vreg11 > %vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7 > %vreg30<def> = COPY %vreg29; GPRI32:%vreg30 R600_Reg32:%vreg29 > %PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16; GPRI32:%vreg30 > JUMP <BB#3>, pred:%PREDICATE_BIT<kill> > JUMP <BB#2>, pred:%noreg > Successors according to CFG: BB#2(4) BB#3(124) > > BB#2: derived from LLVM BB %31 > Predecessors according to CFG: BB#1 > %vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6 > %T2_X<def> = COPY %vreg39; R600_Reg32:%vreg39 > %vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6 > %T2_Y<def> = COPY %vreg40; R600_Reg32:%vreg40 > %vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6 > %T2_Z<def> = COPY %vreg41; R600_Reg32:%vreg41 > %vreg42<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg42 R600_Reg128:%vreg6 > %T2_W<def> = COPY %vreg42; R600_Reg32:%vreg42 > %vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1 > %T1_X<def> = COPY %vreg43; R600_Reg32:%vreg43 > %vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1 > %T1_Y<def> = COPY %vreg44; R600_Reg32:%vreg44 > %vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1 > %T1_Z<def> = COPY %vreg45; R600_Reg32:%vreg45 > %vreg46<def> = COPY %vreg1:sel_w; R600_Reg32:%vreg46 R600_Reg128:%vreg1 > %T1_W<def> = COPY %vreg46; R600_Reg32:%vreg46 > RETURN > > BB#3: derived from LLVM BB %41 > Predecessors according to CFG: BB#1 > %vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6 > %vreg33<def> = IMPLICIT_DEF; R600_Reg128:%vreg33 > %vreg32<def,tied1> = INSERT_SUBREG %vreg33<tied0>, %vreg31<kill>, sel_x; R600_Reg128:%vreg32,%vreg33 R600_Reg32:%vreg31 > %vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6 > %vreg35<def,tied1> = INSERT_SUBREG %vreg32<tied0>, %vreg34<kill>, sel_y; R600_Reg128:%vreg35,%vreg32 R600_Reg32:%vreg34 > %vreg36<def,tied1> = INSERT_SUBREG %vreg35<tied0>, %vreg5, sel_z; R600_Reg128:%vreg36,%vreg35 R600_Reg32:%vreg5 > %vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6 > %vreg10<def,tied1> = INSERT_SUBREG %vreg36<tied0>, %vreg37<kill>, sel_w; R600_Reg128:%vreg10,%vreg36 R600_Reg32:%vreg37 > %vreg9<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg6 > %vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38 > %vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7, 0, 0, 0, %vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg11,%vreg7,%vreg38 > %vreg8<def> = COPY %vreg5; R600_Reg32:%vreg8,%vreg5 > JUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Remove dead machine instructions ***: > # Machine code for function main: SSA > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > BB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > %vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17 > %vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16 > %vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15 > %vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14 > %vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18 > %vreg20<def> = IMPLICIT_DEF; R600_Reg128:%vreg20 > %vreg19<def,tied1> = INSERT_SUBREG %vreg20<tied0>, %vreg14, sel_x; R600_Reg128:%vreg19,%vreg20 R600_TReg32:%vreg14 > %vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2 > %vreg22<def> = IMPLICIT_DEF; R600_Reg128:%vreg22 > %vreg21<def,tied1> = INSERT_SUBREG %vreg22<tied0>, %vreg18<kill>, sel_x; R600_Reg128:%vreg21,%vreg22 R600_Reg32:%vreg18 > %vreg23<def,tied1> = INSERT_SUBREG %vreg19<tied0>, %vreg15, sel_y; R600_Reg128:%vreg23,%vreg19 R600_TReg32:%vreg15 > %vreg24<def,tied1> = INSERT_SUBREG %vreg21<tied0>, %vreg2, sel_y; R600_Reg128:%vreg24,%vreg21 R600_Reg32:%vreg2 > %vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25 > %vreg26<def,tied1> = INSERT_SUBREG %vreg23<tied0>, %vreg16, sel_z; R600_Reg128:%vreg26,%vreg23 R600_TReg32:%vreg16 > %vreg27<def,tied1> = INSERT_SUBREG %vreg24<tied0>, %vreg25<kill>, sel_z; R600_Reg128:%vreg27,%vreg24 R600_Reg32:%vreg25 > %vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28 > %vreg3<def,tied1> = INSERT_SUBREG %vreg27<tied0>, %vreg28<kill>, sel_w; R600_Reg128:%vreg3,%vreg27 R600_Reg32:%vreg28 > %vreg1<def,tied1> = INSERT_SUBREG %vreg26<tied0>, %vreg17, sel_w; R600_Reg128:%vreg1,%vreg26 R600_TReg32:%vreg17 > %vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13 > %vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0 > %vreg12<def> = IMPLICIT_DEF; R600_Reg32:%vreg12 > Successors according to CFG: BB#1 > > BB#1: derived from LLVM BB %25 > Predecessors according to CFG: BB#0 BB#3 > %vreg5<def> = PHI %vreg2, <BB#0>, %vreg9, <BB#3>; R600_Reg32:%vreg5,%vreg2,%vreg9 > %vreg6<def> = PHI %vreg3, <BB#0>, %vreg10, <BB#3>; R600_Reg128:%vreg6,%vreg3,%vreg10 > %vreg7<def> = PHI %vreg13, <BB#0>, %vreg11, <BB#3>; R600_Reg32:%vreg7,%vreg13,%vreg11 > %vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7 > %vreg30<def> = COPY %vreg29; GPRI32:%vreg30 R600_Reg32:%vreg29 > %PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16; GPRI32:%vreg30 > JUMP <BB#3>, pred:%PREDICATE_BIT<kill> > JUMP <BB#2>, pred:%noreg > Successors according to CFG: BB#2(4) BB#3(124) > > BB#2: derived from LLVM BB %31 > Predecessors according to CFG: BB#1 > %vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6 > %T2_X<def> = COPY %vreg39; R600_Reg32:%vreg39 > %vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6 > %T2_Y<def> = COPY %vreg40; R600_Reg32:%vreg40 > %vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6 > %T2_Z<def> = COPY %vreg41; R600_Reg32:%vreg41 > %vreg42<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg42 R600_Reg128:%vreg6 > %T2_W<def> = COPY %vreg42; R600_Reg32:%vreg42 > %vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1 > %T1_X<def> = COPY %vreg43; R600_Reg32:%vreg43 > %vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1 > %T1_Y<def> = COPY %vreg44; R600_Reg32:%vreg44 > %vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1 > %T1_Z<def> = COPY %vreg45; R600_Reg32:%vreg45 > %vreg46<def> = COPY %vreg1:sel_w; R600_Reg32:%vreg46 R600_Reg128:%vreg1 > %T1_W<def> = COPY %vreg46; R600_Reg32:%vreg46 > RETURN > > BB#3: derived from LLVM BB %41 > Predecessors according to CFG: BB#1 > %vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6 > %vreg33<def> = IMPLICIT_DEF; R600_Reg128:%vreg33 > %vreg32<def,tied1> = INSERT_SUBREG %vreg33<tied0>, %vreg31<kill>, sel_x; R600_Reg128:%vreg32,%vreg33 R600_Reg32:%vreg31 > %vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6 > %vreg35<def,tied1> = INSERT_SUBREG %vreg32<tied0>, %vreg34<kill>, sel_y; R600_Reg128:%vreg35,%vreg32 R600_Reg32:%vreg34 > %vreg36<def,tied1> = INSERT_SUBREG %vreg35<tied0>, %vreg5, sel_z; R600_Reg128:%vreg36,%vreg35 R600_Reg32:%vreg5 > %vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6 > %vreg10<def,tied1> = INSERT_SUBREG %vreg36<tied0>, %vreg37<kill>, sel_w; R600_Reg128:%vreg10,%vreg36 R600_Reg32:%vreg37 > %vreg9<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg6 > %vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38 > %vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7, 0, 0, 0, %vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg11,%vreg7,%vreg38 > %vreg8<def> = COPY %vreg5; R600_Reg32:%vreg8,%vreg5 > JUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Machine Loop Invariant Code Motion ***: > # Machine code for function main: SSA > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > BB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > %vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17 > %vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16 > %vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15 > %vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14 > %vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18 > %vreg20<def> = IMPLICIT_DEF; R600_Reg128:%vreg20 > %vreg19<def,tied1> = INSERT_SUBREG %vreg20<tied0>, %vreg14, sel_x; R600_Reg128:%vreg19,%vreg20 R600_TReg32:%vreg14 > %vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2 > %vreg22<def> = IMPLICIT_DEF; R600_Reg128:%vreg22 > %vreg21<def,tied1> = INSERT_SUBREG %vreg22<tied0>, %vreg18<kill>, sel_x; R600_Reg128:%vreg21,%vreg22 R600_Reg32:%vreg18 > %vreg23<def,tied1> = INSERT_SUBREG %vreg19<tied0>, %vreg15, sel_y; R600_Reg128:%vreg23,%vreg19 R600_TReg32:%vreg15 > %vreg24<def,tied1> = INSERT_SUBREG %vreg21<tied0>, %vreg2, sel_y; R600_Reg128:%vreg24,%vreg21 R600_Reg32:%vreg2 > %vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25 > %vreg26<def,tied1> = INSERT_SUBREG %vreg23<tied0>, %vreg16, sel_z; R600_Reg128:%vreg26,%vreg23 R600_TReg32:%vreg16 > %vreg27<def,tied1> = INSERT_SUBREG %vreg24<tied0>, %vreg25<kill>, sel_z; R600_Reg128:%vreg27,%vreg24 R600_Reg32:%vreg25 > %vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28 > %vreg3<def,tied1> = INSERT_SUBREG %vreg27<tied0>, %vreg28<kill>, sel_w; R600_Reg128:%vreg3,%vreg27 R600_Reg32:%vreg28 > %vreg1<def,tied1> = INSERT_SUBREG %vreg26<tied0>, %vreg17, sel_w; R600_Reg128:%vreg1,%vreg26 R600_TReg32:%vreg17 > %vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13 > %vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0 > Successors according to CFG: BB#1 > > BB#1: derived from LLVM BB %25 > Predecessors according to CFG: BB#0 BB#3 > %vreg5<def> = PHI %vreg2, <BB#0>, %vreg9, <BB#3>; R600_Reg32:%vreg5,%vreg2,%vreg9 > %vreg6<def> = PHI %vreg3, <BB#0>, %vreg10, <BB#3>; R600_Reg128:%vreg6,%vreg3,%vreg10 > %vreg7<def> = PHI %vreg13, <BB#0>, %vreg11, <BB#3>; R600_Reg32:%vreg7,%vreg13,%vreg11 > %vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7 > %vreg30<def> = COPY %vreg29; GPRI32:%vreg30 R600_Reg32:%vreg29 > %PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16; GPRI32:%vreg30 > JUMP <BB#3>, pred:%PREDICATE_BIT<kill> > JUMP <BB#2>, pred:%noreg > Successors according to CFG: BB#2(4) BB#3(124) > > BB#2: derived from LLVM BB %31 > Predecessors according to CFG: BB#1 > %vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6 > %T2_X<def> = COPY %vreg39; R600_Reg32:%vreg39 > %vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6 > %T2_Y<def> = COPY %vreg40; R600_Reg32:%vreg40 > %vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6 > %T2_Z<def> = COPY %vreg41; R600_Reg32:%vreg41 > %vreg42<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg42 R600_Reg128:%vreg6 > %T2_W<def> = COPY %vreg42; R600_Reg32:%vreg42 > %vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1 > %T1_X<def> = COPY %vreg43; R600_Reg32:%vreg43 > %vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1 > %T1_Y<def> = COPY %vreg44; R600_Reg32:%vreg44 > %vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1 > %T1_Z<def> = COPY %vreg45; R600_Reg32:%vreg45 > %vreg46<def> = COPY %vreg1:sel_w; R600_Reg32:%vreg46 R600_Reg128:%vreg1 > %T1_W<def> = COPY %vreg46; R600_Reg32:%vreg46 > RETURN > > BB#3: derived from LLVM BB %41 > Predecessors according to CFG: BB#1 > %vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6 > %vreg33<def> = IMPLICIT_DEF; R600_Reg128:%vreg33 > %vreg32<def,tied1> = INSERT_SUBREG %vreg33<tied0>, %vreg31<kill>, sel_x; R600_Reg128:%vreg32,%vreg33 R600_Reg32:%vreg31 > %vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6 > %vreg35<def,tied1> = INSERT_SUBREG %vreg32<tied0>, %vreg34<kill>, sel_y; R600_Reg128:%vreg35,%vreg32 R600_Reg32:%vreg34 > %vreg36<def,tied1> = INSERT_SUBREG %vreg35<tied0>, %vreg5, sel_z; R600_Reg128:%vreg36,%vreg35 R600_Reg32:%vreg5 > %vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6 > %vreg10<def,tied1> = INSERT_SUBREG %vreg36<tied0>, %vreg37<kill>, sel_w; R600_Reg128:%vreg10,%vreg36 R600_Reg32:%vreg37 > %vreg9<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg6 > %vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38 > %vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7, 0, 0, 0, %vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg11,%vreg7,%vreg38 > JUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Machine Common Subexpression Elimination ***: > # Machine code for function main: SSA > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > BB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > %vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17 > %vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16 > %vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15 > %vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14 > %vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18 > %vreg20<def> = IMPLICIT_DEF; R600_Reg128:%vreg20 > %vreg19<def,tied1> = INSERT_SUBREG %vreg20<tied0>, %vreg14, sel_x; R600_Reg128:%vreg19,%vreg20 R600_TReg32:%vreg14 > %vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2 > %vreg22<def> = IMPLICIT_DEF; R600_Reg128:%vreg22 > %vreg21<def,tied1> = INSERT_SUBREG %vreg22<tied0>, %vreg18<kill>, sel_x; R600_Reg128:%vreg21,%vreg22 R600_Reg32:%vreg18 > %vreg23<def,tied1> = INSERT_SUBREG %vreg19<tied0>, %vreg15, sel_y; R600_Reg128:%vreg23,%vreg19 R600_TReg32:%vreg15 > %vreg24<def,tied1> = INSERT_SUBREG %vreg21<tied0>, %vreg2, sel_y; R600_Reg128:%vreg24,%vreg21 R600_Reg32:%vreg2 > %vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25 > %vreg26<def,tied1> = INSERT_SUBREG %vreg23<tied0>, %vreg16, sel_z; R600_Reg128:%vreg26,%vreg23 R600_TReg32:%vreg16 > %vreg27<def,tied1> = INSERT_SUBREG %vreg24<tied0>, %vreg25<kill>, sel_z; R600_Reg128:%vreg27,%vreg24 R600_Reg32:%vreg25 > %vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28 > %vreg3<def,tied1> = INSERT_SUBREG %vreg27<tied0>, %vreg28<kill>, sel_w; R600_Reg128:%vreg3,%vreg27 R600_Reg32:%vreg28 > %vreg1<def,tied1> = INSERT_SUBREG %vreg26<tied0>, %vreg17, sel_w; R600_Reg128:%vreg1,%vreg26 R600_TReg32:%vreg17 > %vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13 > %vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0 > %vreg33<def> = IMPLICIT_DEF; R600_Reg128:%vreg33 > Successors according to CFG: BB#1 > > BB#1: derived from LLVM BB %25 > Predecessors according to CFG: BB#0 BB#3 > %vreg5<def> = PHI %vreg2, <BB#0>, %vreg9, <BB#3>; R600_Reg32:%vreg5,%vreg2,%vreg9 > %vreg6<def> = PHI %vreg3, <BB#0>, %vreg10, <BB#3>; R600_Reg128:%vreg6,%vreg3,%vreg10 > %vreg7<def> = PHI %vreg13, <BB#0>, %vreg11, <BB#3>; R600_Reg32:%vreg7,%vreg13,%vreg11 > %vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7 > %vreg30<def> = COPY %vreg29; GPRI32:%vreg30 R600_Reg32:%vreg29 > %PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16; GPRI32:%vreg30 > JUMP <BB#3>, pred:%PREDICATE_BIT<kill> > JUMP <BB#2>, pred:%noreg > Successors according to CFG: BB#2(4) BB#3(124) > > BB#2: derived from LLVM BB %31 > Predecessors according to CFG: BB#1 > %vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6 > %T2_X<def> = COPY %vreg39; R600_Reg32:%vreg39 > %vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6 > %T2_Y<def> = COPY %vreg40; R600_Reg32:%vreg40 > %vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6 > %T2_Z<def> = COPY %vreg41; R600_Reg32:%vreg41 > %vreg42<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg42 R600_Reg128:%vreg6 > %T2_W<def> = COPY %vreg42; R600_Reg32:%vreg42 > %vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1 > %T1_X<def> = COPY %vreg43; R600_Reg32:%vreg43 > %vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1 > %T1_Y<def> = COPY %vreg44; R600_Reg32:%vreg44 > %vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1 > %T1_Z<def> = COPY %vreg45; R600_Reg32:%vreg45 > %vreg46<def> = COPY %vreg1:sel_w; R600_Reg32:%vreg46 R600_Reg128:%vreg1 > %T1_W<def> = COPY %vreg46; R600_Reg32:%vreg46 > RETURN > > BB#3: derived from LLVM BB %41 > Predecessors according to CFG: BB#1 > %vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6 > %vreg32<def,tied1> = INSERT_SUBREG %vreg33<tied0>, %vreg31<kill>, sel_x; R600_Reg128:%vreg32,%vreg33 R600_Reg32:%vreg31 > %vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6 > %vreg35<def,tied1> = INSERT_SUBREG %vreg32<tied0>, %vreg34<kill>, sel_y; R600_Reg128:%vreg35,%vreg32 R600_Reg32:%vreg34 > %vreg36<def,tied1> = INSERT_SUBREG %vreg35<tied0>, %vreg5, sel_z; R600_Reg128:%vreg36,%vreg35 R600_Reg32:%vreg5 > %vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6 > %vreg10<def,tied1> = INSERT_SUBREG %vreg36<tied0>, %vreg37<kill>, sel_w; R600_Reg128:%vreg10,%vreg36 R600_Reg32:%vreg37 > %vreg9<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg6 > %vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38 > %vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7, 0, 0, 0, %vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg11,%vreg7,%vreg38 > JUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Machine code sinking ***: > # Machine code for function main: SSA > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > BB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > %vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17 > %vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16 > %vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15 > %vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14 > %vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18 > %vreg20<def> = IMPLICIT_DEF; R600_Reg128:%vreg20 > %vreg19<def,tied1> = INSERT_SUBREG %vreg20<tied0>, %vreg14, sel_x; R600_Reg128:%vreg19,%vreg20 R600_TReg32:%vreg14 > %vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2 > %vreg22<def> = IMPLICIT_DEF; R600_Reg128:%vreg22 > %vreg21<def,tied1> = INSERT_SUBREG %vreg22<tied0>, %vreg18<kill>, sel_x; R600_Reg128:%vreg21,%vreg22 R600_Reg32:%vreg18 > %vreg23<def,tied1> = INSERT_SUBREG %vreg19<tied0>, %vreg15, sel_y; R600_Reg128:%vreg23,%vreg19 R600_TReg32:%vreg15 > %vreg24<def,tied1> = INSERT_SUBREG %vreg21<tied0>, %vreg2, sel_y; R600_Reg128:%vreg24,%vreg21 R600_Reg32:%vreg2 > %vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25 > %vreg26<def,tied1> = INSERT_SUBREG %vreg23<tied0>, %vreg16, sel_z; R600_Reg128:%vreg26,%vreg23 R600_TReg32:%vreg16 > %vreg27<def,tied1> = INSERT_SUBREG %vreg24<tied0>, %vreg25<kill>, sel_z; R600_Reg128:%vreg27,%vreg24 R600_Reg32:%vreg25 > %vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28 > %vreg3<def,tied1> = INSERT_SUBREG %vreg27<tied0>, %vreg28<kill>, sel_w; R600_Reg128:%vreg3,%vreg27 R600_Reg32:%vreg28 > %vreg1<def,tied1> = INSERT_SUBREG %vreg26<tied0>, %vreg17, sel_w; R600_Reg128:%vreg1,%vreg26 R600_TReg32:%vreg17 > %vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13 > %vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0 > %vreg33<def> = IMPLICIT_DEF; R600_Reg128:%vreg33 > Successors according to CFG: BB#1 > > BB#1: derived from LLVM BB %25 > Predecessors according to CFG: BB#0 BB#3 > %vreg5<def> = PHI %vreg2, <BB#0>, %vreg9, <BB#3>; R600_Reg32:%vreg5,%vreg2,%vreg9 > %vreg6<def> = PHI %vreg3, <BB#0>, %vreg10, <BB#3>; R600_Reg128:%vreg6,%vreg3,%vreg10 > %vreg7<def> = PHI %vreg13, <BB#0>, %vreg11, <BB#3>; R600_Reg32:%vreg7,%vreg13,%vreg11 > %vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7 > %vreg30<def> = COPY %vreg29; GPRI32:%vreg30 R600_Reg32:%vreg29 > %PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16; GPRI32:%vreg30 > JUMP <BB#3>, pred:%PREDICATE_BIT<kill> > JUMP <BB#2>, pred:%noreg > Successors according to CFG: BB#2(4) BB#3(124) > > BB#2: derived from LLVM BB %31 > Predecessors according to CFG: BB#1 > %vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6 > %T2_X<def> = COPY %vreg39; R600_Reg32:%vreg39 > %vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6 > %T2_Y<def> = COPY %vreg40; R600_Reg32:%vreg40 > %vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6 > %T2_Z<def> = COPY %vreg41; R600_Reg32:%vreg41 > %vreg42<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg42 R600_Reg128:%vreg6 > %T2_W<def> = COPY %vreg42; R600_Reg32:%vreg42 > %vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1 > %T1_X<def> = COPY %vreg43; R600_Reg32:%vreg43 > %vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1 > %T1_Y<def> = COPY %vreg44; R600_Reg32:%vreg44 > %vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1 > %T1_Z<def> = COPY %vreg45; R600_Reg32:%vreg45 > %vreg46<def> = COPY %vreg1:sel_w; R600_Reg32:%vreg46 R600_Reg128:%vreg1 > %T1_W<def> = COPY %vreg46; R600_Reg32:%vreg46 > RETURN > > BB#3: derived from LLVM BB %41 > Predecessors according to CFG: BB#1 > %vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6 > %vreg32<def,tied1> = INSERT_SUBREG %vreg33<tied0>, %vreg31<kill>, sel_x; R600_Reg128:%vreg32,%vreg33 R600_Reg32:%vreg31 > %vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6 > %vreg35<def,tied1> = INSERT_SUBREG %vreg32<tied0>, %vreg34<kill>, sel_y; R600_Reg128:%vreg35,%vreg32 R600_Reg32:%vreg34 > %vreg36<def,tied1> = INSERT_SUBREG %vreg35<tied0>, %vreg5, sel_z; R600_Reg128:%vreg36,%vreg35 R600_Reg32:%vreg5 > %vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6 > %vreg10<def,tied1> = INSERT_SUBREG %vreg36<tied0>, %vreg37<kill>, sel_w; R600_Reg128:%vreg10,%vreg36 R600_Reg32:%vreg37 > %vreg9<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg6 > %vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38 > %vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7, 0, 0, 0, %vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg11,%vreg7,%vreg38 > JUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Peephole Optimizations ***: > # Machine code for function main: SSA > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > BB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > %vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17 > %vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16 > %vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15 > %vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14 > %vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18 > %vreg20<def> = IMPLICIT_DEF; R600_Reg128:%vreg20 > %vreg19<def,tied1> = INSERT_SUBREG %vreg20<tied0>, %vreg14, sel_x; R600_Reg128:%vreg19,%vreg20 R600_TReg32:%vreg14 > %vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2 > %vreg22<def> = IMPLICIT_DEF; R600_Reg128:%vreg22 > %vreg21<def,tied1> = INSERT_SUBREG %vreg22<tied0>, %vreg18<kill>, sel_x; R600_Reg128:%vreg21,%vreg22 R600_Reg32:%vreg18 > %vreg23<def,tied1> = INSERT_SUBREG %vreg19<tied0>, %vreg15, sel_y; R600_Reg128:%vreg23,%vreg19 R600_TReg32:%vreg15 > %vreg24<def,tied1> = INSERT_SUBREG %vreg21<tied0>, %vreg2, sel_y; R600_Reg128:%vreg24,%vreg21 R600_Reg32:%vreg2 > %vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25 > %vreg26<def,tied1> = INSERT_SUBREG %vreg23<tied0>, %vreg16, sel_z; R600_Reg128:%vreg26,%vreg23 R600_TReg32:%vreg16 > %vreg27<def,tied1> = INSERT_SUBREG %vreg24<tied0>, %vreg25<kill>, sel_z; R600_Reg128:%vreg27,%vreg24 R600_Reg32:%vreg25 > %vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28 > %vreg3<def,tied1> = INSERT_SUBREG %vreg27<tied0>, %vreg28<kill>, sel_w; R600_Reg128:%vreg3,%vreg27 R600_Reg32:%vreg28 > %vreg1<def,tied1> = INSERT_SUBREG %vreg26<tied0>, %vreg17, sel_w; R600_Reg128:%vreg1,%vreg26 R600_TReg32:%vreg17 > %vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13 > %vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0 > %vreg33<def> = IMPLICIT_DEF; R600_Reg128:%vreg33 > Successors according to CFG: BB#1 > > BB#1: derived from LLVM BB %25 > Predecessors according to CFG: BB#0 BB#3 > %vreg5<def> = PHI %vreg2, <BB#0>, %vreg9, <BB#3>; R600_Reg32:%vreg5,%vreg2,%vreg9 > %vreg6<def> = PHI %vreg3, <BB#0>, %vreg10, <BB#3>; R600_Reg128:%vreg6,%vreg3,%vreg10 > %vreg7<def> = PHI %vreg13, <BB#0>, %vreg11, <BB#3>; R600_Reg32:%vreg7,%vreg13,%vreg11 > %vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7 > %vreg30<def> = COPY %vreg29; GPRI32:%vreg30 R600_Reg32:%vreg29 > %PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16; GPRI32:%vreg30 > JUMP <BB#3>, pred:%PREDICATE_BIT<kill> > JUMP <BB#2>, pred:%noreg > Successors according to CFG: BB#2(4) BB#3(124) > > BB#2: derived from LLVM BB %31 > Predecessors according to CFG: BB#1 > %vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6 > %T2_X<def> = COPY %vreg39; R600_Reg32:%vreg39 > %vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6 > %T2_Y<def> = COPY %vreg40; R600_Reg32:%vreg40 > %vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6 > %T2_Z<def> = COPY %vreg41; R600_Reg32:%vreg41 > %vreg42<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg42 R600_Reg128:%vreg6 > %T2_W<def> = COPY %vreg42; R600_Reg32:%vreg42 > %vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1 > %T1_X<def> = COPY %vreg43; R600_Reg32:%vreg43 > %vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1 > %T1_Y<def> = COPY %vreg44; R600_Reg32:%vreg44 > %vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1 > %T1_Z<def> = COPY %vreg45; R600_Reg32:%vreg45 > %vreg46<def> = COPY %vreg1:sel_w; R600_Reg32:%vreg46 R600_Reg128:%vreg1 > %T1_W<def> = COPY %vreg46; R600_Reg32:%vreg46 > RETURN > > BB#3: derived from LLVM BB %41 > Predecessors according to CFG: BB#1 > %vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6 > %vreg32<def,tied1> = INSERT_SUBREG %vreg33<tied0>, %vreg31<kill>, sel_x; R600_Reg128:%vreg32,%vreg33 R600_Reg32:%vreg31 > %vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6 > %vreg35<def,tied1> = INSERT_SUBREG %vreg32<tied0>, %vreg34<kill>, sel_y; R600_Reg128:%vreg35,%vreg32 R600_Reg32:%vreg34 > %vreg36<def,tied1> = INSERT_SUBREG %vreg35<tied0>, %vreg5, sel_z; R600_Reg128:%vreg36,%vreg35 R600_Reg32:%vreg5 > %vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6 > %vreg10<def,tied1> = INSERT_SUBREG %vreg36<tied0>, %vreg37<kill>, sel_w; R600_Reg128:%vreg10,%vreg36 R600_Reg32:%vreg37 > %vreg9<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg6 > %vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38 > %vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7, 0, 0, 0, %vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg11,%vreg7,%vreg38 > JUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Process Implicit Definitions ***: > # Machine code for function main: SSA > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > BB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > %vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17 > %vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16 > %vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15 > %vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14 > %vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18 > %vreg20<def> = IMPLICIT_DEF; R600_Reg128:%vreg20 > %vreg19<def,tied1> = INSERT_SUBREG %vreg20<tied0>, %vreg14, sel_x; R600_Reg128:%vreg19,%vreg20 R600_TReg32:%vreg14 > %vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2 > %vreg22<def> = IMPLICIT_DEF; R600_Reg128:%vreg22 > %vreg21<def,tied1> = INSERT_SUBREG %vreg22<tied0>, %vreg18<kill>, sel_x; R600_Reg128:%vreg21,%vreg22 R600_Reg32:%vreg18 > %vreg23<def,tied1> = INSERT_SUBREG %vreg19<tied0>, %vreg15, sel_y; R600_Reg128:%vreg23,%vreg19 R600_TReg32:%vreg15 > %vreg24<def,tied1> = INSERT_SUBREG %vreg21<tied0>, %vreg2, sel_y; R600_Reg128:%vreg24,%vreg21 R600_Reg32:%vreg2 > %vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25 > %vreg26<def,tied1> = INSERT_SUBREG %vreg23<tied0>, %vreg16, sel_z; R600_Reg128:%vreg26,%vreg23 R600_TReg32:%vreg16 > %vreg27<def,tied1> = INSERT_SUBREG %vreg24<tied0>, %vreg25<kill>, sel_z; R600_Reg128:%vreg27,%vreg24 R600_Reg32:%vreg25 > %vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28 > %vreg3<def,tied1> = INSERT_SUBREG %vreg27<tied0>, %vreg28<kill>, sel_w; R600_Reg128:%vreg3,%vreg27 R600_Reg32:%vreg28 > %vreg1<def,tied1> = INSERT_SUBREG %vreg26<tied0>, %vreg17, sel_w; R600_Reg128:%vreg1,%vreg26 R600_TReg32:%vreg17 > %vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13 > %vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0 > %vreg33<def> = IMPLICIT_DEF; R600_Reg128:%vreg33 > Successors according to CFG: BB#1 > > BB#1: derived from LLVM BB %25 > Predecessors according to CFG: BB#0 BB#3 > %vreg5<def> = PHI %vreg2, <BB#0>, %vreg9, <BB#3>; R600_Reg32:%vreg5,%vreg2,%vreg9 > %vreg6<def> = PHI %vreg3, <BB#0>, %vreg10, <BB#3>; R600_Reg128:%vreg6,%vreg3,%vreg10 > %vreg7<def> = PHI %vreg13, <BB#0>, %vreg11, <BB#3>; R600_Reg32:%vreg7,%vreg13,%vreg11 > %vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7 > %vreg30<def> = COPY %vreg29; R600_Reg32:%vreg30,%vreg29 > %PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16; R600_Reg32:%vreg30 > JUMP <BB#3>, pred:%PREDICATE_BIT<kill> > JUMP <BB#2>, pred:%noreg > Successors according to CFG: BB#2(4) BB#3(124) > > BB#2: derived from LLVM BB %31 > Predecessors according to CFG: BB#1 > %vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6 > %T2_X<def> = COPY %vreg39; R600_Reg32:%vreg39 > %vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6 > %T2_Y<def> = COPY %vreg40; R600_Reg32:%vreg40 > %vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6 > %T2_Z<def> = COPY %vreg41; R600_Reg32:%vreg41 > %vreg42<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg42 R600_Reg128:%vreg6 > %T2_W<def> = COPY %vreg42; R600_Reg32:%vreg42 > %vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1 > %T1_X<def> = COPY %vreg43; R600_Reg32:%vreg43 > %vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1 > %T1_Y<def> = COPY %vreg44; R600_Reg32:%vreg44 > %vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1 > %T1_Z<def> = COPY %vreg45; R600_Reg32:%vreg45 > %vreg46<def> = COPY %vreg1:sel_w; R600_Reg32:%vreg46 R600_Reg128:%vreg1 > %T1_W<def> = COPY %vreg46; R600_Reg32:%vreg46 > RETURN > > BB#3: derived from LLVM BB %41 > Predecessors according to CFG: BB#1 > %vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6 > %vreg32<def,tied1> = INSERT_SUBREG %vreg33<tied0>, %vreg31<kill>, sel_x; R600_Reg128:%vreg32,%vreg33 R600_Reg32:%vreg31 > %vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6 > %vreg35<def,tied1> = INSERT_SUBREG %vreg32<tied0>, %vreg34<kill>, sel_y; R600_Reg128:%vreg35,%vreg32 R600_Reg32:%vreg34 > %vreg36<def,tied1> = INSERT_SUBREG %vreg35<tied0>, %vreg5, sel_z; R600_Reg128:%vreg36,%vreg35 R600_Reg32:%vreg5 > %vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6 > %vreg10<def,tied1> = INSERT_SUBREG %vreg36<tied0>, %vreg37<kill>, sel_w; R600_Reg128:%vreg10,%vreg36 R600_Reg32:%vreg37 > %vreg9<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg6 > %vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38 > %vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7, 0, 0, 0, %vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg11,%vreg7,%vreg38 > JUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Remove unreachable machine basic blocks ***: > # Machine code for function main: SSA > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > BB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > %vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17 > %vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16 > %vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15 > %vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14 > %vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18 > %vreg19<def,tied1> = INSERT_SUBREG %vreg20<undef,tied0>, %vreg14, sel_x; R600_Reg128:%vreg19,%vreg20 R600_TReg32:%vreg14 > %vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2 > %vreg21<def,tied1> = INSERT_SUBREG %vreg22<undef,tied0>, %vreg18<kill>, sel_x; R600_Reg128:%vreg21,%vreg22 R600_Reg32:%vreg18 > %vreg23<def,tied1> = INSERT_SUBREG %vreg19<tied0>, %vreg15, sel_y; R600_Reg128:%vreg23,%vreg19 R600_TReg32:%vreg15 > %vreg24<def,tied1> = INSERT_SUBREG %vreg21<tied0>, %vreg2, sel_y; R600_Reg128:%vreg24,%vreg21 R600_Reg32:%vreg2 > %vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25 > %vreg26<def,tied1> = INSERT_SUBREG %vreg23<tied0>, %vreg16, sel_z; R600_Reg128:%vreg26,%vreg23 R600_TReg32:%vreg16 > %vreg27<def,tied1> = INSERT_SUBREG %vreg24<tied0>, %vreg25<kill>, sel_z; R600_Reg128:%vreg27,%vreg24 R600_Reg32:%vreg25 > %vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28 > %vreg3<def,tied1> = INSERT_SUBREG %vreg27<tied0>, %vreg28<kill>, sel_w; R600_Reg128:%vreg3,%vreg27 R600_Reg32:%vreg28 > %vreg1<def,tied1> = INSERT_SUBREG %vreg26<tied0>, %vreg17, sel_w; R600_Reg128:%vreg1,%vreg26 R600_TReg32:%vreg17 > %vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13 > %vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0 > Successors according to CFG: BB#1 > > BB#1: derived from LLVM BB %25 > Predecessors according to CFG: BB#0 BB#3 > %vreg5<def> = PHI %vreg2, <BB#0>, %vreg9, <BB#3>; R600_Reg32:%vreg5,%vreg2,%vreg9 > %vreg6<def> = PHI %vreg3, <BB#0>, %vreg10, <BB#3>; R600_Reg128:%vreg6,%vreg3,%vreg10 > %vreg7<def> = PHI %vreg13, <BB#0>, %vreg11, <BB#3>; R600_Reg32:%vreg7,%vreg13,%vreg11 > %vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7 > %vreg30<def> = COPY %vreg29; R600_Reg32:%vreg30,%vreg29 > %PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16; R600_Reg32:%vreg30 > JUMP <BB#3>, pred:%PREDICATE_BIT<kill> > JUMP <BB#2>, pred:%noreg > Successors according to CFG: BB#2(4) BB#3(124) > > BB#2: derived from LLVM BB %31 > Predecessors according to CFG: BB#1 > %vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6 > %T2_X<def> = COPY %vreg39; R600_Reg32:%vreg39 > %vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6 > %T2_Y<def> = COPY %vreg40; R600_Reg32:%vreg40 > %vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6 > %T2_Z<def> = COPY %vreg41; R600_Reg32:%vreg41 > %vreg42<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg42 R600_Reg128:%vreg6 > %T2_W<def> = COPY %vreg42; R600_Reg32:%vreg42 > %vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1 > %T1_X<def> = COPY %vreg43; R600_Reg32:%vreg43 > %vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1 > %T1_Y<def> = COPY %vreg44; R600_Reg32:%vreg44 > %vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1 > %T1_Z<def> = COPY %vreg45; R600_Reg32:%vreg45 > %vreg46<def> = COPY %vreg1:sel_w; R600_Reg32:%vreg46 R600_Reg128:%vreg1 > %T1_W<def> = COPY %vreg46; R600_Reg32:%vreg46 > RETURN > > BB#3: derived from LLVM BB %41 > Predecessors according to CFG: BB#1 > %vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6 > %vreg32<def,tied1> = INSERT_SUBREG %vreg33<undef,tied0>, %vreg31<kill>, sel_x; R600_Reg128:%vreg32,%vreg33 R600_Reg32:%vreg31 > %vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6 > %vreg35<def,tied1> = INSERT_SUBREG %vreg32<tied0>, %vreg34<kill>, sel_y; R600_Reg128:%vreg35,%vreg32 R600_Reg32:%vreg34 > %vreg36<def,tied1> = INSERT_SUBREG %vreg35<tied0>, %vreg5, sel_z; R600_Reg128:%vreg36,%vreg35 R600_Reg32:%vreg5 > %vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6 > %vreg10<def,tied1> = INSERT_SUBREG %vreg36<tied0>, %vreg37<kill>, sel_w; R600_Reg128:%vreg10,%vreg36 R600_Reg32:%vreg37 > %vreg9<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg6 > %vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38 > %vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7, 0, 0, 0, %vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg11,%vreg7,%vreg38 > JUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Live Variable Analysis ***: > # Machine code for function main: SSA > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > BB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > %vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17 > %vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16 > %vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15 > %vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14 > %vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18 > %vreg19<def,tied1> = INSERT_SUBREG %vreg20<undef,tied0>, %vreg14, sel_x; R600_Reg128:%vreg19,%vreg20 R600_TReg32:%vreg14 > %vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2 > %vreg21<def,tied1> = INSERT_SUBREG %vreg22<undef,tied0>, %vreg18<kill>, sel_x; R600_Reg128:%vreg21,%vreg22 R600_Reg32:%vreg18 > %vreg23<def,tied1> = INSERT_SUBREG %vreg19<tied0>, %vreg15, sel_y; R600_Reg128:%vreg23,%vreg19 R600_TReg32:%vreg15 > %vreg24<def,tied1> = INSERT_SUBREG %vreg21<tied0>, %vreg2, sel_y; R600_Reg128:%vreg24,%vreg21 R600_Reg32:%vreg2 > %vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25 > %vreg26<def,tied1> = INSERT_SUBREG %vreg23<tied0>, %vreg16, sel_z; R600_Reg128:%vreg26,%vreg23 R600_TReg32:%vreg16 > %vreg27<def,tied1> = INSERT_SUBREG %vreg24<tied0>, %vreg25<kill>, sel_z; R600_Reg128:%vreg27,%vreg24 R600_Reg32:%vreg25 > %vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28 > %vreg3<def,tied1> = INSERT_SUBREG %vreg27<tied0>, %vreg28<kill>, sel_w; R600_Reg128:%vreg3,%vreg27 R600_Reg32:%vreg28 > %vreg1<def,tied1> = INSERT_SUBREG %vreg26<tied0>, %vreg17, sel_w; R600_Reg128:%vreg1,%vreg26 R600_TReg32:%vreg17 > %vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13 > %vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0 > Successors according to CFG: BB#1 > > BB#1: derived from LLVM BB %25 > Predecessors according to CFG: BB#0 BB#3 > %vreg5<def> = PHI %vreg2, <BB#0>, %vreg9, <BB#3>; R600_Reg32:%vreg5,%vreg2,%vreg9 > %vreg6<def> = PHI %vreg3, <BB#0>, %vreg10, <BB#3>; R600_Reg128:%vreg6,%vreg3,%vreg10 > %vreg7<def> = PHI %vreg13, <BB#0>, %vreg11, <BB#3>; R600_Reg32:%vreg7,%vreg13,%vreg11 > %vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7 > %vreg30<def> = COPY %vreg29; R600_Reg32:%vreg30,%vreg29 > %PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16; R600_Reg32:%vreg30 > JUMP <BB#3>, pred:%PREDICATE_BIT<kill> > JUMP <BB#2>, pred:%noreg > Successors according to CFG: BB#2(4) BB#3(124) > > BB#2: derived from LLVM BB %31 > Predecessors according to CFG: BB#1 > %vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6 > %T2_X<def> = COPY %vreg39; R600_Reg32:%vreg39 > %vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6 > %T2_Y<def> = COPY %vreg40; R600_Reg32:%vreg40 > %vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6 > %T2_Z<def> = COPY %vreg41; R600_Reg32:%vreg41 > %vreg42<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg42 R600_Reg128:%vreg6 > %T2_W<def> = COPY %vreg42; R600_Reg32:%vreg42 > %vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1 > %T1_X<def> = COPY %vreg43; R600_Reg32:%vreg43 > %vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1 > %T1_Y<def> = COPY %vreg44; R600_Reg32:%vreg44 > %vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1 > %T1_Z<def> = COPY %vreg45; R600_Reg32:%vreg45 > %vreg46<def> = COPY %vreg1:sel_w; R600_Reg32:%vreg46 R600_Reg128:%vreg1 > %T1_W<def> = COPY %vreg46; R600_Reg32:%vreg46 > RETURN > > BB#3: derived from LLVM BB %41 > Predecessors according to CFG: BB#1 > %vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6 > %vreg32<def,tied1> = INSERT_SUBREG %vreg33<undef,tied0>, %vreg31<kill>, sel_x; R600_Reg128:%vreg32,%vreg33 R600_Reg32:%vreg31 > %vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6 > %vreg35<def,tied1> = INSERT_SUBREG %vreg32<tied0>, %vreg34<kill>, sel_y; R600_Reg128:%vreg35,%vreg32 R600_Reg32:%vreg34 > %vreg36<def,tied1> = INSERT_SUBREG %vreg35<tied0>, %vreg5, sel_z; R600_Reg128:%vreg36,%vreg35 R600_Reg32:%vreg5 > %vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6 > %vreg10<def,tied1> = INSERT_SUBREG %vreg36<tied0>, %vreg37<kill>, sel_w; R600_Reg128:%vreg10,%vreg36 R600_Reg32:%vreg37 > %vreg9<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg6 > %vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38 > %vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7, 0, 0, 0, %vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg11,%vreg7,%vreg38 > JUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Eliminate PHI nodes for register allocation ***: > # Machine code for function main: SSA > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > BB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > %vreg17<def> = COPY %T1_W<kill>; R600_TReg32:%vreg17 > %vreg16<def> = COPY %T1_Z<kill>; R600_TReg32:%vreg16 > %vreg15<def> = COPY %T1_Y<kill>; R600_TReg32:%vreg15 > %vreg14<def> = COPY %T1_X<kill>; R600_TReg32:%vreg14 > %vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18 > %vreg19<def,tied1> = INSERT_SUBREG %vreg20<undef,tied0>, %vreg14<kill>, sel_x; R600_Reg128:%vreg19,%vreg20 R600_TReg32:%vreg14 > %vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2 > %vreg21<def,tied1> = INSERT_SUBREG %vreg22<undef,tied0>, %vreg18<kill>, sel_x; R600_Reg128:%vreg21,%vreg22 R600_Reg32:%vreg18 > %vreg23<def,tied1> = INSERT_SUBREG %vreg19<kill,tied0>, %vreg15<kill>, sel_y; R600_Reg128:%vreg23,%vreg19 R600_TReg32:%vreg15 > %vreg24<def,tied1> = INSERT_SUBREG %vreg21<kill,tied0>, %vreg2, sel_y; R600_Reg128:%vreg24,%vreg21 R600_Reg32:%vreg2 > %vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25 > %vreg26<def,tied1> = INSERT_SUBREG %vreg23<kill,tied0>, %vreg16<kill>, sel_z; R600_Reg128:%vreg26,%vreg23 R600_TReg32:%vreg16 > %vreg27<def,tied1> = INSERT_SUBREG %vreg24<kill,tied0>, %vreg25<kill>, sel_z; R600_Reg128:%vreg27,%vreg24 R600_Reg32:%vreg25 > %vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28 > %vreg3<def,tied1> = INSERT_SUBREG %vreg27<kill,tied0>, %vreg28<kill>, sel_w; R600_Reg128:%vreg3,%vreg27 R600_Reg32:%vreg28 > %vreg1<def,tied1> = INSERT_SUBREG %vreg26<kill,tied0>, %vreg17<kill>, sel_w; R600_Reg128:%vreg1,%vreg26 R600_TReg32:%vreg17 > %vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13 > %vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0 > Successors according to CFG: BB#1 > > BB#1: derived from LLVM BB %25 > Predecessors according to CFG: BB#0 BB#3 > %vreg5<def> = PHI %vreg2, <BB#0>, %vreg9, <BB#3>; R600_Reg32:%vreg5,%vreg2,%vreg9 > %vreg6<def> = PHI %vreg3, <BB#0>, %vreg10, <BB#3>; R600_Reg128:%vreg6,%vreg3,%vreg10 > %vreg7<def> = PHI %vreg13, <BB#0>, %vreg11, <BB#3>; R600_Reg32:%vreg7,%vreg13,%vreg11 > %vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7 > %vreg30<def> = COPY %vreg29<kill>; R600_Reg32:%vreg30,%vreg29 > %PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16; R600_Reg32:%vreg30 > JUMP <BB#3>, pred:%PREDICATE_BIT > JUMP <BB#2>, pred:%noreg > Successors according to CFG: BB#2(4) BB#3(124) > > BB#2: derived from LLVM BB %31 > Predecessors according to CFG: BB#1 > %vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6 > %T2_X<def> = COPY %vreg39<kill>; R600_Reg32:%vreg39 > %vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6 > %T2_Y<def> = COPY %vreg40<kill>; R600_Reg32:%vreg40 > %vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6 > %T2_Z<def> = COPY %vreg41<kill>; R600_Reg32:%vreg41 > %vreg42<def> = COPY %vreg6:sel_w<kill>; R600_Reg32:%vreg42 R600_Reg128:%vreg6 > %T2_W<def> = COPY %vreg42<kill>; R600_Reg32:%vreg42 > %vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1 > %T1_X<def> = COPY %vreg43<kill>; R600_Reg32:%vreg43 > %vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1 > %T1_Y<def> = COPY %vreg44<kill>; R600_Reg32:%vreg44 > %vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1 > %T1_Z<def> = COPY %vreg45<kill>; R600_Reg32:%vreg45 > %vreg46<def> = COPY %vreg1:sel_w<kill>; R600_Reg32:%vreg46 R600_Reg128:%vreg1 > %T1_W<def> = COPY %vreg46<kill>; R600_Reg32:%vreg46 > RETURN %T1_W<imp-use,kill>, %T1_Z<imp-use,kill>, %T1_Y<imp-use,kill>, %T1_X<imp-use,kill>, %T2_W<imp-use,kill>, %T2_Z<imp-use,kill>, %T2_Y<imp-use,kill>, %T2_X<imp-use,kill> > > BB#3: derived from LLVM BB %41 > Predecessors according to CFG: BB#1 > %vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6 > %vreg32<def,tied1> = INSERT_SUBREG %vreg33<undef,tied0>, %vreg31<kill>, sel_x; R600_Reg128:%vreg32,%vreg33 R600_Reg32:%vreg31 > %vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6 > %vreg35<def,tied1> = INSERT_SUBREG %vreg32<kill,tied0>, %vreg34<kill>, sel_y; R600_Reg128:%vreg35,%vreg32 R600_Reg32:%vreg34 > %vreg36<def,tied1> = INSERT_SUBREG %vreg35<kill,tied0>, %vreg5<kill>, sel_z; R600_Reg128:%vreg36,%vreg35 R600_Reg32:%vreg5 > %vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6 > %vreg10<def,tied1> = INSERT_SUBREG %vreg36<kill,tied0>, %vreg37<kill>, sel_w; R600_Reg128:%vreg10,%vreg36 R600_Reg32:%vreg37 > %vreg9<def> = COPY %vreg6:sel_z<kill>; R600_Reg32:%vreg9 R600_Reg128:%vreg6 > %vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38 > %vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7<kill>, 0, 0, 0, %vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg11,%vreg7,%vreg38 > JUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Two-Address instruction pass ***: > # Machine code for function main: Post SSA > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > BB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > %vreg17<def> = COPY %T1_W<kill>; R600_TReg32:%vreg17 > %vreg16<def> = COPY %T1_Z<kill>; R600_TReg32:%vreg16 > %vreg15<def> = COPY %T1_Y<kill>; R600_TReg32:%vreg15 > %vreg14<def> = COPY %T1_X<kill>; R600_TReg32:%vreg14 > %vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18 > %vreg19<def,tied1> = INSERT_SUBREG %vreg20<undef,tied0>, %vreg14<kill>, sel_x; R600_Reg128:%vreg19,%vreg20 R600_TReg32:%vreg14 > %vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2 > %vreg21<def,tied1> = INSERT_SUBREG %vreg22<undef,tied0>, %vreg18<kill>, sel_x; R600_Reg128:%vreg21,%vreg22 R600_Reg32:%vreg18 > %vreg23<def,tied1> = INSERT_SUBREG %vreg19<kill,tied0>, %vreg15<kill>, sel_y; R600_Reg128:%vreg23,%vreg19 R600_TReg32:%vreg15 > %vreg24<def,tied1> = INSERT_SUBREG %vreg21<kill,tied0>, %vreg2, sel_y; R600_Reg128:%vreg24,%vreg21 R600_Reg32:%vreg2 > %vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25 > %vreg26<def,tied1> = INSERT_SUBREG %vreg23<kill,tied0>, %vreg16<kill>, sel_z; R600_Reg128:%vreg26,%vreg23 R600_TReg32:%vreg16 > %vreg27<def,tied1> = INSERT_SUBREG %vreg24<kill,tied0>, %vreg25<kill>, sel_z; R600_Reg128:%vreg27,%vreg24 R600_Reg32:%vreg25 > %vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28 > %vreg3<def,tied1> = INSERT_SUBREG %vreg27<kill,tied0>, %vreg28<kill>, sel_w; R600_Reg128:%vreg3,%vreg27 R600_Reg32:%vreg28 > %vreg1<def,tied1> = INSERT_SUBREG %vreg26<kill,tied0>, %vreg17<kill>, sel_w; R600_Reg128:%vreg1,%vreg26 R600_TReg32:%vreg17 > %vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13 > %vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0 > %vreg47<def> = COPY %vreg2<kill>; R600_Reg32:%vreg47,%vreg2 > %vreg48<def> = COPY %vreg3<kill>; R600_Reg128:%vreg48,%vreg3 > %vreg49<def> = COPY %vreg13<kill>; R600_Reg32:%vreg49,%vreg13 > Successors according to CFG: BB#1 > > BB#1: derived from LLVM BB %25 > Predecessors according to CFG: BB#0 BB#3 > %vreg5<def> = COPY %vreg47<kill>; R600_Reg32:%vreg5,%vreg47 > %vreg6<def> = COPY %vreg48<kill>; R600_Reg128:%vreg6,%vreg48 > %vreg7<def> = COPY %vreg49<kill>; R600_Reg32:%vreg7,%vreg49 > %vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7 > %vreg30<def> = COPY %vreg29<kill>; R600_Reg32:%vreg30,%vreg29 > %PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16; R600_Reg32:%vreg30 > JUMP <BB#3>, pred:%PREDICATE_BIT > JUMP <BB#2>, pred:%noreg > Successors according to CFG: BB#2(4) BB#3(124) > > BB#2: derived from LLVM BB %31 > Predecessors according to CFG: BB#1 > %vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6 > %T2_X<def> = COPY %vreg39<kill>; R600_Reg32:%vreg39 > %vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6 > %T2_Y<def> = COPY %vreg40<kill>; R600_Reg32:%vreg40 > %vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6 > %T2_Z<def> = COPY %vreg41<kill>; R600_Reg32:%vreg41 > %vreg42<def> = COPY %vreg6:sel_w<kill>; R600_Reg32:%vreg42 R600_Reg128:%vreg6 > %T2_W<def> = COPY %vreg42<kill>; R600_Reg32:%vreg42 > %vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1 > %T1_X<def> = COPY %vreg43<kill>; R600_Reg32:%vreg43 > %vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1 > %T1_Y<def> = COPY %vreg44<kill>; R600_Reg32:%vreg44 > %vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1 > %T1_Z<def> = COPY %vreg45<kill>; R600_Reg32:%vreg45 > %vreg46<def> = COPY %vreg1:sel_w<kill>; R600_Reg32:%vreg46 R600_Reg128:%vreg1 > %T1_W<def> = COPY %vreg46<kill>; R600_Reg32:%vreg46 > RETURN %T1_W<imp-use,kill>, %T1_Z<imp-use,kill>, %T1_Y<imp-use,kill>, %T1_X<imp-use,kill>, %T2_W<imp-use,kill>, %T2_Z<imp-use,kill>, %T2_Y<imp-use,kill>, %T2_X<imp-use,kill> > > BB#3: derived from LLVM BB %41 > Predecessors according to CFG: BB#1 > %vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6 > %vreg32<def,tied1> = INSERT_SUBREG %vreg33<undef,tied0>, %vreg31<kill>, sel_x; R600_Reg128:%vreg32,%vreg33 R600_Reg32:%vreg31 > %vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6 > %vreg35<def,tied1> = INSERT_SUBREG %vreg32<kill,tied0>, %vreg34<kill>, sel_y; R600_Reg128:%vreg35,%vreg32 R600_Reg32:%vreg34 > %vreg36<def,tied1> = INSERT_SUBREG %vreg35<kill,tied0>, %vreg5<kill>, sel_z; R600_Reg128:%vreg36,%vreg35 R600_Reg32:%vreg5 > %vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6 > %vreg10<def,tied1> = INSERT_SUBREG %vreg36<kill,tied0>, %vreg37<kill>, sel_w; R600_Reg128:%vreg10,%vreg36 R600_Reg32:%vreg37 > %vreg9<def> = COPY %vreg6:sel_z<kill>; R600_Reg32:%vreg9 R600_Reg128:%vreg6 > %vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38 > %vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7<kill>, 0, 0, 0, %vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg11,%vreg7,%vreg38 > %vreg47<def> = COPY %vreg9<kill>; R600_Reg32:%vreg47,%vreg9 > %vreg48<def> = COPY %vreg10<kill>; R600_Reg128:%vreg48,%vreg10 > %vreg49<def> = COPY %vreg11<kill>; R600_Reg32:%vreg49,%vreg11 > JUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Slot index numbering ***: > # Machine code for function main: Post SSA > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > BB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > %vreg17<def> = COPY %T1_W<kill>; R600_TReg32:%vreg17 > %vreg16<def> = COPY %T1_Z<kill>; R600_TReg32:%vreg16 > %vreg15<def> = COPY %T1_Y<kill>; R600_TReg32:%vreg15 > %vreg14<def> = COPY %T1_X<kill>; R600_TReg32:%vreg14 > %vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18 > %vreg19:sel_x<def,read-undef> = COPY %vreg14<kill>; R600_Reg128:%vreg19 R600_TReg32:%vreg14 > %vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2 > %vreg21:sel_x<def,read-undef> = COPY %vreg18<kill>; R600_Reg128:%vreg21 R600_Reg32:%vreg18 > %vreg23<def> = COPY %vreg19<kill>; R600_Reg128:%vreg23,%vreg19 > %vreg23:sel_y<def> = COPY %vreg15<kill>; R600_Reg128:%vreg23 R600_TReg32:%vreg15 > %vreg24<def> = COPY %vreg21<kill>; R600_Reg128:%vreg24,%vreg21 > %vreg24:sel_y<def> = COPY %vreg2; R600_Reg128:%vreg24 R600_Reg32:%vreg2 > %vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25 > %vreg26<def> = COPY %vreg23<kill>; R600_Reg128:%vreg26,%vreg23 > %vreg26:sel_z<def> = COPY %vreg16<kill>; R600_Reg128:%vreg26 R600_TReg32:%vreg16 > %vreg27<def> = COPY %vreg24<kill>; R600_Reg128:%vreg27,%vreg24 > %vreg27:sel_z<def> = COPY %vreg25<kill>; R600_Reg128:%vreg27 R600_Reg32:%vreg25 > %vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28 > %vreg3<def> = COPY %vreg27<kill>; R600_Reg128:%vreg3,%vreg27 > %vreg3:sel_w<def> = COPY %vreg28<kill>; R600_Reg128:%vreg3 R600_Reg32:%vreg28 > %vreg1<def> = COPY %vreg26<kill>; R600_Reg128:%vreg1,%vreg26 > %vreg1:sel_w<def> = COPY %vreg17<kill>; R600_Reg128:%vreg1 R600_TReg32:%vreg17 > %vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13 > %vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0 > %vreg47<def> = COPY %vreg2<kill>; R600_Reg32:%vreg47,%vreg2 > %vreg48<def> = COPY %vreg3<kill>; R600_Reg128:%vreg48,%vreg3 > %vreg49<def> = COPY %vreg13<kill>; R600_Reg32:%vreg49,%vreg13 > Successors according to CFG: BB#1 > > BB#1: derived from LLVM BB %25 > Predecessors according to CFG: BB#0 BB#3 > %vreg5<def> = COPY %vreg47<kill>; R600_Reg32:%vreg5,%vreg47 > %vreg6<def> = COPY %vreg48<kill>; R600_Reg128:%vreg6,%vreg48 > %vreg7<def> = COPY %vreg49<kill>; R600_Reg32:%vreg7,%vreg49 > %vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7 > %vreg30<def> = COPY %vreg29<kill>; R600_Reg32:%vreg30,%vreg29 > %PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16; R600_Reg32:%vreg30 > JUMP <BB#3>, pred:%PREDICATE_BIT > JUMP <BB#2>, pred:%noreg > Successors according to CFG: BB#2(4) BB#3(124) > > BB#2: derived from LLVM BB %31 > Predecessors according to CFG: BB#1 > %vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6 > %T2_X<def> = COPY %vreg39<kill>; R600_Reg32:%vreg39 > %vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6 > %T2_Y<def> = COPY %vreg40<kill>; R600_Reg32:%vreg40 > %vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6 > %T2_Z<def> = COPY %vreg41<kill>; R600_Reg32:%vreg41 > %vreg42<def> = COPY %vreg6:sel_w<kill>; R600_Reg32:%vreg42 R600_Reg128:%vreg6 > %T2_W<def> = COPY %vreg42<kill>; R600_Reg32:%vreg42 > %vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1 > %T1_X<def> = COPY %vreg43<kill>; R600_Reg32:%vreg43 > %vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1 > %T1_Y<def> = COPY %vreg44<kill>; R600_Reg32:%vreg44 > %vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1 > %T1_Z<def> = COPY %vreg45<kill>; R600_Reg32:%vreg45 > %vreg46<def> = COPY %vreg1:sel_w<kill>; R600_Reg32:%vreg46 R600_Reg128:%vreg1 > %T1_W<def> = COPY %vreg46<kill>; R600_Reg32:%vreg46 > RETURN %T1_W<imp-use,kill>, %T1_Z<imp-use,kill>, %T1_Y<imp-use,kill>, %T1_X<imp-use,kill>, %T2_W<imp-use,kill>, %T2_Z<imp-use,kill>, %T2_Y<imp-use,kill>, %T2_X<imp-use,kill> > > BB#3: derived from LLVM BB %41 > Predecessors according to CFG: BB#1 > %vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6 > %vreg32:sel_x<def,read-undef> = COPY %vreg31<kill>; R600_Reg128:%vreg32 R600_Reg32:%vreg31 > %vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6 > %vreg35<def> = COPY %vreg32<kill>; R600_Reg128:%vreg35,%vreg32 > %vreg35:sel_y<def> = COPY %vreg34<kill>; R600_Reg128:%vreg35 R600_Reg32:%vreg34 > %vreg36<def> = COPY %vreg35<kill>; R600_Reg128:%vreg36,%vreg35 > %vreg36:sel_z<def> = COPY %vreg5<kill>; R600_Reg128:%vreg36 R600_Reg32:%vreg5 > %vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6 > %vreg10<def> = COPY %vreg36<kill>; R600_Reg128:%vreg10,%vreg36 > %vreg10:sel_w<def> = COPY %vreg37<kill>; R600_Reg128:%vreg10 R600_Reg32:%vreg37 > %vreg9<def> = COPY %vreg6:sel_z<kill>; R600_Reg32:%vreg9 R600_Reg128:%vreg6 > %vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38 > %vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7<kill>, 0, 0, 0, %vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg11,%vreg7,%vreg38 > %vreg47<def> = COPY %vreg9<kill>; R600_Reg32:%vreg47,%vreg9 > %vreg48<def> = COPY %vreg10<kill>; R600_Reg128:%vreg48,%vreg10 > %vreg49<def> = COPY %vreg11<kill>; R600_Reg32:%vreg49,%vreg11 > JUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Live Interval Analysis ***: > # Machine code for function main: Post SSA > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > 0BBB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > 16B%vreg17<def> = COPY %T1_W<kill>; R600_TReg32:%vreg17 > 32B%vreg16<def> = COPY %T1_Z<kill>; R600_TReg32:%vreg16 > 48B%vreg15<def> = COPY %T1_Y<kill>; R600_TReg32:%vreg15 > 64B%vreg14<def> = COPY %T1_X<kill>; R600_TReg32:%vreg14 > 80B%vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18 > 96B%vreg19:sel_x<def,read-undef> = COPY %vreg14<kill>; R600_Reg128:%vreg19 R600_TReg32:%vreg14 > 112B%vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2 > 128B%vreg21:sel_x<def,read-undef> = COPY %vreg18<kill>; R600_Reg128:%vreg21 R600_Reg32:%vreg18 > 144B%vreg23<def> = COPY %vreg19<kill>; R600_Reg128:%vreg23,%vreg19 > 160B%vreg23:sel_y<def> = COPY %vreg15<kill>; R600_Reg128:%vreg23 R600_TReg32:%vreg15 > 176B%vreg24<def> = COPY %vreg21<kill>; R600_Reg128:%vreg24,%vreg21 > 192B%vreg24:sel_y<def> = COPY %vreg2; R600_Reg128:%vreg24 R600_Reg32:%vreg2 > 208B%vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25 > 224B%vreg26<def> = COPY %vreg23<kill>; R600_Reg128:%vreg26,%vreg23 > 240B%vreg26:sel_z<def> = COPY %vreg16<kill>; R600_Reg128:%vreg26 R600_TReg32:%vreg16 > 256B%vreg27<def> = COPY %vreg24<kill>; R600_Reg128:%vreg27,%vreg24 > 272B%vreg27:sel_z<def> = COPY %vreg25<kill>; R600_Reg128:%vreg27 R600_Reg32:%vreg25 > 288B%vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28 > 304B%vreg3<def> = COPY %vreg27<kill>; R600_Reg128:%vreg3,%vreg27 > 320B%vreg3:sel_w<def> = COPY %vreg28<kill>; R600_Reg128:%vreg3 R600_Reg32:%vreg28 > 336B%vreg1<def> = COPY %vreg26<kill>; R600_Reg128:%vreg1,%vreg26 > 352B%vreg1:sel_w<def> = COPY %vreg17<kill>; R600_Reg128:%vreg1 R600_TReg32:%vreg17 > 368B%vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13 > 384B%vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0 > 400B%vreg47<def> = COPY %vreg2<kill>; R600_Reg32:%vreg47,%vreg2 > 416B%vreg48<def> = COPY %vreg3<kill>; R600_Reg128:%vreg48,%vreg3 > 432B%vreg49<def> = COPY %vreg13<kill>; R600_Reg32:%vreg49,%vreg13 > Successors according to CFG: BB#1 > > 448BBB#1: derived from LLVM BB %25 > Predecessors according to CFG: BB#0 BB#3 > 464B%vreg5<def> = COPY %vreg47<kill>; R600_Reg32:%vreg5,%vreg47 > 480B%vreg6<def> = COPY %vreg48<kill>; R600_Reg128:%vreg6,%vreg48 > 496B%vreg7<def> = COPY %vreg49<kill>; R600_Reg32:%vreg7,%vreg49 > 512B%vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7 > 528B%vreg30<def> = COPY %vreg29<kill>; R600_Reg32:%vreg30,%vreg29 > 544B%PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16; R600_Reg32:%vreg30 > 560BJUMP <BB#3>, pred:%PREDICATE_BIT > 576BJUMP <BB#2>, pred:%noreg > Successors according to CFG: BB#2(4) BB#3(124) > > 592BBB#2: derived from LLVM BB %31 > Predecessors according to CFG: BB#1 > 608B%vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6 > 624B%T2_X<def> = COPY %vreg39<kill>; R600_Reg32:%vreg39 > 640B%vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6 > 656B%T2_Y<def> = COPY %vreg40<kill>; R600_Reg32:%vreg40 > 672B%vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6 > 688B%T2_Z<def> = COPY %vreg41<kill>; R600_Reg32:%vreg41 > 704B%vreg42<def> = COPY %vreg6:sel_w<kill>; R600_Reg32:%vreg42 R600_Reg128:%vreg6 > 720B%T2_W<def> = COPY %vreg42<kill>; R600_Reg32:%vreg42 > 736B%vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1 > 752B%T1_X<def> = COPY %vreg43<kill>; R600_Reg32:%vreg43 > 768B%vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1 > 784B%T1_Y<def> = COPY %vreg44<kill>; R600_Reg32:%vreg44 > 800B%vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1 > 816B%T1_Z<def> = COPY %vreg45<kill>; R600_Reg32:%vreg45 > 832B%vreg46<def> = COPY %vreg1:sel_w<kill>; R600_Reg32:%vreg46 R600_Reg128:%vreg1 > 848B%T1_W<def> = COPY %vreg46<kill>; R600_Reg32:%vreg46 > 864BRETURN %T1_W<imp-use,kill>, %T1_Z<imp-use,kill>, %T1_Y<imp-use,kill>, %T1_X<imp-use,kill>, %T2_W<imp-use,kill>, %T2_Z<imp-use,kill>, %T2_Y<imp-use,kill>, %T2_X<imp-use,kill> > > 880BBB#3: derived from LLVM BB %41 > Predecessors according to CFG: BB#1 > 896B%vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6 > 912B%vreg32:sel_x<def,read-undef> = COPY %vreg31<kill>; R600_Reg128:%vreg32 R600_Reg32:%vreg31 > 928B%vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6 > 944B%vreg35<def> = COPY %vreg32<kill>; R600_Reg128:%vreg35,%vreg32 > 960B%vreg35:sel_y<def> = COPY %vreg34<kill>; R600_Reg128:%vreg35 R600_Reg32:%vreg34 > 976B%vreg36<def> = COPY %vreg35<kill>; R600_Reg128:%vreg36,%vreg35 > 992B%vreg36:sel_z<def> = COPY %vreg5<kill>; R600_Reg128:%vreg36 R600_Reg32:%vreg5 > 1008B%vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6 > 1024B%vreg10<def> = COPY %vreg36<kill>; R600_Reg128:%vreg10,%vreg36 > 1040B%vreg10:sel_w<def> = COPY %vreg37<kill>; R600_Reg128:%vreg10 R600_Reg32:%vreg37 > 1056B%vreg9<def> = COPY %vreg6:sel_z<kill>; R600_Reg32:%vreg9 R600_Reg128:%vreg6 > 1072B%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38 > 1088B%vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7<kill>, 0, 0, 0, %vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg11,%vreg7,%vreg38 > 1104B%vreg47<def> = COPY %vreg9<kill>; R600_Reg32:%vreg47,%vreg9 > 1120B%vreg48<def> = COPY %vreg10<kill>; R600_Reg128:%vreg48,%vreg10 > 1136B%vreg49<def> = COPY %vreg11<kill>; R600_Reg32:%vreg49,%vreg11 > 1152BJUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Debug Variable Analysis ***: > # Machine code for function main: Post SSA > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > 0BBB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > 16B%vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17 > 32B%vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16 > 48B%vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15 > 64B%vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14 > 80B%vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18 > 96B%vreg19:sel_x<def,read-undef> = COPY %vreg14<kill>; R600_Reg128:%vreg19 R600_TReg32:%vreg14 > 112B%vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2 > 128B%vreg21:sel_x<def,read-undef> = COPY %vreg18<kill>; R600_Reg128:%vreg21 R600_Reg32:%vreg18 > 144B%vreg23<def> = COPY %vreg19<kill>; R600_Reg128:%vreg23,%vreg19 > 160B%vreg23:sel_y<def> = COPY %vreg15<kill>; R600_Reg128:%vreg23 R600_TReg32:%vreg15 > 176B%vreg24<def> = COPY %vreg21<kill>; R600_Reg128:%vreg24,%vreg21 > 192B%vreg24:sel_y<def> = COPY %vreg2; R600_Reg128:%vreg24 R600_Reg32:%vreg2 > 208B%vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25 > 224B%vreg26<def> = COPY %vreg23<kill>; R600_Reg128:%vreg26,%vreg23 > 240B%vreg26:sel_z<def> = COPY %vreg16<kill>; R600_Reg128:%vreg26 R600_TReg32:%vreg16 > 256B%vreg27<def> = COPY %vreg24<kill>; R600_Reg128:%vreg27,%vreg24 > 272B%vreg27:sel_z<def> = COPY %vreg25<kill>; R600_Reg128:%vreg27 R600_Reg32:%vreg25 > 288B%vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28 > 304B%vreg3<def> = COPY %vreg27<kill>; R600_Reg128:%vreg3,%vreg27 > 320B%vreg3:sel_w<def> = COPY %vreg28<kill>; R600_Reg128:%vreg3 R600_Reg32:%vreg28 > 336B%vreg1<def> = COPY %vreg26<kill>; R600_Reg128:%vreg1,%vreg26 > 352B%vreg1:sel_w<def> = COPY %vreg17<kill>; R600_Reg128:%vreg1 R600_TReg32:%vreg17 > 368B%vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13 > 384B%vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0 > 400B%vreg47<def> = COPY %vreg2<kill>; R600_Reg32:%vreg47,%vreg2 > 416B%vreg48<def> = COPY %vreg3<kill>; R600_Reg128:%vreg48,%vreg3 > 432B%vreg49<def> = COPY %vreg13<kill>; R600_Reg32:%vreg49,%vreg13 > Successors according to CFG: BB#1 > > 448BBB#1: derived from LLVM BB %25 > Predecessors according to CFG: BB#0 BB#3 > 464B%vreg5<def> = COPY %vreg47<kill>; R600_Reg32:%vreg5,%vreg47 > 480B%vreg6<def> = COPY %vreg48<kill>; R600_Reg128:%vreg6,%vreg48 > 496B%vreg7<def> = COPY %vreg49<kill>; R600_Reg32:%vreg7,%vreg49 > 512B%vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7 > 528B%vreg30<def> = COPY %vreg29<kill>; R600_Reg32:%vreg30,%vreg29 > 544B%PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16; R600_Reg32:%vreg30 > 560BJUMP <BB#3>, pred:%PREDICATE_BIT > 576BJUMP <BB#2>, pred:%noreg > Successors according to CFG: BB#2(4) BB#3(124) > > 592BBB#2: derived from LLVM BB %31 > Predecessors according to CFG: BB#1 > 608B%vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6 > 624B%T2_X<def> = COPY %vreg39<kill>; R600_Reg32:%vreg39 > 640B%vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6 > 656B%T2_Y<def> = COPY %vreg40<kill>; R600_Reg32:%vreg40 > 672B%vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6 > 688B%T2_Z<def> = COPY %vreg41<kill>; R600_Reg32:%vreg41 > 704B%vreg42<def> = COPY %vreg6:sel_w<kill>; R600_Reg32:%vreg42 R600_Reg128:%vreg6 > 720B%T2_W<def> = COPY %vreg42<kill>; R600_Reg32:%vreg42 > 736B%vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1 > 752B%T1_X<def> = COPY %vreg43<kill>; R600_Reg32:%vreg43 > 768B%vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1 > 784B%T1_Y<def> = COPY %vreg44<kill>; R600_Reg32:%vreg44 > 800B%vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1 > 816B%T1_Z<def> = COPY %vreg45<kill>; R600_Reg32:%vreg45 > 832B%vreg46<def> = COPY %vreg1:sel_w<kill>; R600_Reg32:%vreg46 R600_Reg128:%vreg1 > 848B%T1_W<def> = COPY %vreg46<kill>; R600_Reg32:%vreg46 > 864BRETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>, %T1_X<imp-use>, %T2_W<imp-use,kill>, %T2_Z<imp-use,kill>, %T2_Y<imp-use,kill>, %T2_X<imp-use,kill> > > 880BBB#3: derived from LLVM BB %41 > Predecessors according to CFG: BB#1 > 896B%vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6 > 912B%vreg32:sel_x<def,read-undef> = COPY %vreg31<kill>; R600_Reg128:%vreg32 R600_Reg32:%vreg31 > 928B%vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6 > 944B%vreg35<def> = COPY %vreg32<kill>; R600_Reg128:%vreg35,%vreg32 > 960B%vreg35:sel_y<def> = COPY %vreg34<kill>; R600_Reg128:%vreg35 R600_Reg32:%vreg34 > 976B%vreg36<def> = COPY %vreg35<kill>; R600_Reg128:%vreg36,%vreg35 > 992B%vreg36:sel_z<def> = COPY %vreg5<kill>; R600_Reg128:%vreg36 R600_Reg32:%vreg5 > 1008B%vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6 > 1024B%vreg10<def> = COPY %vreg36<kill>; R600_Reg128:%vreg10,%vreg36 > 1040B%vreg10:sel_w<def> = COPY %vreg37<kill>; R600_Reg128:%vreg10 R600_Reg32:%vreg37 > 1056B%vreg9<def> = COPY %vreg6:sel_z<kill>; R600_Reg32:%vreg9 R600_Reg128:%vreg6 > 1072B%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38 > 1088B%vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7<kill>, 0, 0, 0, %vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg11,%vreg7,%vreg38 > 1104B%vreg47<def> = COPY %vreg9<kill>; R600_Reg32:%vreg47,%vreg9 > 1120B%vreg48<def> = COPY %vreg10<kill>; R600_Reg128:%vreg48,%vreg10 > 1136B%vreg49<def> = COPY %vreg11<kill>; R600_Reg32:%vreg49,%vreg11 > 1152BJUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Simple Register Coalescing ***: > # Machine code for function main: Post SSA > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > 0BBB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > 16B%vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17 > 32B%vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16 > 48B%vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15 > 64B%vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14 > 80B%vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18 > 96B%vreg19:sel_x<def,read-undef> = COPY %vreg14<kill>; R600_Reg128:%vreg19 R600_TReg32:%vreg14 > 112B%vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2 > 128B%vreg21:sel_x<def,read-undef> = COPY %vreg18<kill>; R600_Reg128:%vreg21 R600_Reg32:%vreg18 > 144B%vreg23<def> = COPY %vreg19<kill>; R600_Reg128:%vreg23,%vreg19 > 160B%vreg23:sel_y<def> = COPY %vreg15<kill>; R600_Reg128:%vreg23 R600_TReg32:%vreg15 > 176B%vreg24<def> = COPY %vreg21<kill>; R600_Reg128:%vreg24,%vreg21 > 192B%vreg24:sel_y<def> = COPY %vreg2; R600_Reg128:%vreg24 R600_Reg32:%vreg2 > 208B%vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25 > 224B%vreg26<def> = COPY %vreg23<kill>; R600_Reg128:%vreg26,%vreg23 > 240B%vreg26:sel_z<def> = COPY %vreg16<kill>; R600_Reg128:%vreg26 R600_TReg32:%vreg16 > 256B%vreg27<def> = COPY %vreg24<kill>; R600_Reg128:%vreg27,%vreg24 > 272B%vreg27:sel_z<def> = COPY %vreg25<kill>; R600_Reg128:%vreg27 R600_Reg32:%vreg25 > 288B%vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28 > 304B%vreg3<def> = COPY %vreg27<kill>; R600_Reg128:%vreg3,%vreg27 > 320B%vreg3:sel_w<def> = COPY %vreg28<kill>; R600_Reg128:%vreg3 R600_Reg32:%vreg28 > 336B%vreg1<def> = COPY %vreg26<kill>; R600_Reg128:%vreg1,%vreg26 > 352B%vreg1:sel_w<def> = COPY %vreg17<kill>; R600_Reg128:%vreg1 R600_TReg32:%vreg17 > 368B%vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13 > 384B%vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0 > 400B%vreg47<def> = COPY %vreg2<kill>; R600_Reg32:%vreg47,%vreg2 > 416B%vreg48<def> = COPY %vreg3<kill>; R600_Reg128:%vreg48,%vreg3 > 432B%vreg49<def> = COPY %vreg13<kill>; R600_Reg32:%vreg49,%vreg13 > Successors according to CFG: BB#1 > > 448BBB#1: derived from LLVM BB %25 > Predecessors according to CFG: BB#0 BB#3 > 464B%vreg5<def> = COPY %vreg47<kill>; R600_Reg32:%vreg5,%vreg47 > 480B%vreg6<def> = COPY %vreg48<kill>; R600_Reg128:%vreg6,%vreg48 > 496B%vreg7<def> = COPY %vreg49<kill>; R600_Reg32:%vreg7,%vreg49 > 512B%vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7 > 528B%vreg30<def> = COPY %vreg29<kill>; R600_Reg32:%vreg30,%vreg29 > 544B%PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16; R600_Reg32:%vreg30 > 560BJUMP <BB#3>, pred:%PREDICATE_BIT > 576BJUMP <BB#2>, pred:%noreg > Successors according to CFG: BB#2(4) BB#3(124) > > 592BBB#2: derived from LLVM BB %31 > Predecessors according to CFG: BB#1 > 608B%vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6 > 624B%T2_X<def> = COPY %vreg39<kill>; R600_Reg32:%vreg39 > 640B%vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6 > 656B%T2_Y<def> = COPY %vreg40<kill>; R600_Reg32:%vreg40 > 672B%vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6 > 688B%T2_Z<def> = COPY %vreg41<kill>; R600_Reg32:%vreg41 > 704B%vreg42<def> = COPY %vreg6:sel_w<kill>; R600_Reg32:%vreg42 R600_Reg128:%vreg6 > 720B%T2_W<def> = COPY %vreg42<kill>; R600_Reg32:%vreg42 > 736B%vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1 > 752B%T1_X<def> = COPY %vreg43<kill>; R600_Reg32:%vreg43 > 768B%vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1 > 784B%T1_Y<def> = COPY %vreg44<kill>; R600_Reg32:%vreg44 > 800B%vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1 > 816B%T1_Z<def> = COPY %vreg45<kill>; R600_Reg32:%vreg45 > 832B%vreg46<def> = COPY %vreg1:sel_w<kill>; R600_Reg32:%vreg46 R600_Reg128:%vreg1 > 848B%T1_W<def> = COPY %vreg46<kill>; R600_Reg32:%vreg46 > 864BRETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>, %T1_X<imp-use>, %T2_W<imp-use,kill>, %T2_Z<imp-use,kill>, %T2_Y<imp-use,kill>, %T2_X<imp-use,kill> > > 880BBB#3: derived from LLVM BB %41 > Predecessors according to CFG: BB#1 > 896B%vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6 > 912B%vreg32:sel_x<def,read-undef> = COPY %vreg31<kill>; R600_Reg128:%vreg32 R600_Reg32:%vreg31 > 928B%vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6 > 944B%vreg35<def> = COPY %vreg32<kill>; R600_Reg128:%vreg35,%vreg32 > 960B%vreg35:sel_y<def> = COPY %vreg34<kill>; R600_Reg128:%vreg35 R600_Reg32:%vreg34 > 976B%vreg36<def> = COPY %vreg35<kill>; R600_Reg128:%vreg36,%vreg35 > 992B%vreg36:sel_z<def> = COPY %vreg5<kill>; R600_Reg128:%vreg36 R600_Reg32:%vreg5 > 1008B%vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6 > 1024B%vreg10<def> = COPY %vreg36<kill>; R600_Reg128:%vreg10,%vreg36 > 1040B%vreg10:sel_w<def> = COPY %vreg37<kill>; R600_Reg128:%vreg10 R600_Reg32:%vreg37 > 1056B%vreg9<def> = COPY %vreg6:sel_z<kill>; R600_Reg32:%vreg9 R600_Reg128:%vreg6 > 1072B%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38 > 1088B%vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7<kill>, 0, 0, 0, %vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg11,%vreg7,%vreg38 > 1104B%vreg47<def> = COPY %vreg9<kill>; R600_Reg32:%vreg47,%vreg9 > 1120B%vreg48<def> = COPY %vreg10<kill>; R600_Reg128:%vreg48,%vreg10 > 1136B%vreg49<def> = COPY %vreg11<kill>; R600_Reg32:%vreg49,%vreg11 > 1152BJUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Live Stack Slot Analysis ***: > # Machine code for function main: Post SSA > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > 0BBB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > 16B%vreg1:sel_w<def,read-undef> = COPY %T1_W; R600_Reg128:%vreg1 > 32B%vreg1:sel_z<def> = COPY %T1_Z; R600_Reg128:%vreg1 > 48B%vreg1:sel_y<def> = COPY %T1_Y; R600_Reg128:%vreg1 > 64B%vreg1:sel_x<def> = COPY %T1_X; R600_Reg128:%vreg1 > 128B%vreg27:sel_x<def,read-undef> = COPY %C1_X; R600_Reg128:%vreg27 > 192B%vreg27:sel_y<def> = COPY %C1_Y; R600_Reg128:%vreg27 > 272B%vreg27:sel_z<def> = COPY %C1_Z; R600_Reg128:%vreg27 > 320B%vreg27:sel_w<def> = COPY %C1_W; R600_Reg128:%vreg27 > 368B%vreg49<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg49 > Successors according to CFG: BB#1 > > 448BBB#1: derived from LLVM BB %25 > Predecessors according to CFG: BB#0 BB#3 > 512B%vreg30<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %vreg49, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg30,%vreg49 > 544B%PREDICATE_BIT<def> = PRED_X %vreg30, 152, 16; R600_Reg32:%vreg30 > 560BJUMP <BB#3>, pred:%PREDICATE_BIT > 576BJUMP <BB#2>, pred:%noreg > Successors according to CFG: BB#2(4) BB#3(124) > > 592BBB#2: derived from LLVM BB %31 > Predecessors according to CFG: BB#1 > 624B%T2_X<def> = COPY %vreg27:sel_x; R600_Reg128:%vreg27 > 656B%T2_Y<def> = COPY %vreg27:sel_y; R600_Reg128:%vreg27 > 688B%T2_Z<def> = COPY %vreg27:sel_z; R600_Reg128:%vreg27 > 720B%T2_W<def> = COPY %vreg27:sel_w; R600_Reg128:%vreg27 > 752B%T1_X<def> = COPY %vreg1:sel_x; R600_Reg128:%vreg1 > 784B%T1_Y<def> = COPY %vreg1:sel_y; R600_Reg128:%vreg1 > 816B%T1_Z<def> = COPY %vreg1:sel_z; R600_Reg128:%vreg1 > 848B%T1_W<def> = COPY %vreg1:sel_w; R600_Reg128:%vreg1 > 864BRETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>, %T1_X<imp-use>, %T2_W<imp-use,kill>, %T2_Z<imp-use,kill>, %T2_Y<imp-use,kill>, %T2_X<imp-use,kill> > > 880BBB#3: derived from LLVM BB %41 > Predecessors according to CFG: BB#1 > 1072B%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38 > 1088B%vreg49<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg49, 0, 0, 0, %vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg49,%vreg38 > 1152BJUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Calculate spill weights ***: > # Machine code for function main: Post SSA > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > 0BBB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > 16B%vreg1:sel_w<def,read-undef> = COPY %T1_W; R600_Reg128:%vreg1 > 32B%vreg1:sel_z<def> = COPY %T1_Z; R600_Reg128:%vreg1 > 48B%vreg1:sel_y<def> = COPY %T1_Y; R600_Reg128:%vreg1 > 64B%vreg1:sel_x<def> = COPY %T1_X; R600_Reg128:%vreg1 > 128B%vreg27:sel_x<def,read-undef> = COPY %C1_X; R600_Reg128:%vreg27 > 192B%vreg27:sel_y<def> = COPY %C1_Y; R600_Reg128:%vreg27 > 272B%vreg27:sel_z<def> = COPY %C1_Z; R600_Reg128:%vreg27 > 320B%vreg27:sel_w<def> = COPY %C1_W; R600_Reg128:%vreg27 > 368B%vreg49<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg49 > Successors according to CFG: BB#1 > > 448BBB#1: derived from LLVM BB %25 > Predecessors according to CFG: BB#0 BB#3 > 512B%vreg30<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %vreg49, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg30,%vreg49 > 544B%PREDICATE_BIT<def> = PRED_X %vreg30, 152, 16; R600_Reg32:%vreg30 > 560BJUMP <BB#3>, pred:%PREDICATE_BIT > 576BJUMP <BB#2>, pred:%noreg > Successors according to CFG: BB#2(4) BB#3(124) > > 592BBB#2: derived from LLVM BB %31 > Predecessors according to CFG: BB#1 > 624B%T2_X<def> = COPY %vreg27:sel_x; R600_Reg128:%vreg27 > 656B%T2_Y<def> = COPY %vreg27:sel_y; R600_Reg128:%vreg27 > 688B%T2_Z<def> = COPY %vreg27:sel_z; R600_Reg128:%vreg27 > 720B%T2_W<def> = COPY %vreg27:sel_w; R600_Reg128:%vreg27 > 752B%T1_X<def> = COPY %vreg1:sel_x; R600_Reg128:%vreg1 > 784B%T1_Y<def> = COPY %vreg1:sel_y; R600_Reg128:%vreg1 > 816B%T1_Z<def> = COPY %vreg1:sel_z; R600_Reg128:%vreg1 > 848B%T1_W<def> = COPY %vreg1:sel_w; R600_Reg128:%vreg1 > 864BRETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>, %T1_X<imp-use>, %T2_W<imp-use,kill>, %T2_Z<imp-use,kill>, %T2_Y<imp-use,kill>, %T2_X<imp-use,kill> > > 880BBB#3: derived from LLVM BB %41 > Predecessors according to CFG: BB#1 > 1072B%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38 > 1088B%vreg49<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg49, 0, 0, 0, %vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg49,%vreg38 > 1152BJUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Virtual Register Map ***: > # Machine code for function main: Post SSA > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > 0BBB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > 16B%vreg1:sel_w<def,read-undef> = COPY %T1_W; R600_Reg128:%vreg1 > 32B%vreg1:sel_z<def> = COPY %T1_Z; R600_Reg128:%vreg1 > 48B%vreg1:sel_y<def> = COPY %T1_Y; R600_Reg128:%vreg1 > 64B%vreg1:sel_x<def> = COPY %T1_X; R600_Reg128:%vreg1 > 128B%vreg27:sel_x<def,read-undef> = COPY %C1_X; R600_Reg128:%vreg27 > 192B%vreg27:sel_y<def> = COPY %C1_Y; R600_Reg128:%vreg27 > 272B%vreg27:sel_z<def> = COPY %C1_Z; R600_Reg128:%vreg27 > 320B%vreg27:sel_w<def> = COPY %C1_W; R600_Reg128:%vreg27 > 368B%vreg49<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg49 > Successors according to CFG: BB#1 > > 448BBB#1: derived from LLVM BB %25 > Predecessors according to CFG: BB#0 BB#3 > 512B%vreg30<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %vreg49, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg30,%vreg49 > 544B%PREDICATE_BIT<def> = PRED_X %vreg30, 152, 16; R600_Reg32:%vreg30 > 560BJUMP <BB#3>, pred:%PREDICATE_BIT > 576BJUMP <BB#2>, pred:%noreg > Successors according to CFG: BB#2(4) BB#3(124) > > 592BBB#2: derived from LLVM BB %31 > Predecessors according to CFG: BB#1 > 624B%T2_X<def> = COPY %vreg27:sel_x; R600_Reg128:%vreg27 > 656B%T2_Y<def> = COPY %vreg27:sel_y; R600_Reg128:%vreg27 > 688B%T2_Z<def> = COPY %vreg27:sel_z; R600_Reg128:%vreg27 > 720B%T2_W<def> = COPY %vreg27:sel_w; R600_Reg128:%vreg27 > 752B%T1_X<def> = COPY %vreg1:sel_x; R600_Reg128:%vreg1 > 784B%T1_Y<def> = COPY %vreg1:sel_y; R600_Reg128:%vreg1 > 816B%T1_Z<def> = COPY %vreg1:sel_z; R600_Reg128:%vreg1 > 848B%T1_W<def> = COPY %vreg1:sel_w; R600_Reg128:%vreg1 > 864BRETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>, %T1_X<imp-use>, %T2_W<imp-use,kill>, %T2_Z<imp-use,kill>, %T2_Y<imp-use,kill>, %T2_X<imp-use,kill> > > 880BBB#3: derived from LLVM BB %41 > Predecessors according to CFG: BB#1 > 1072B%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38 > 1088B%vreg49<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg49, 0, 0, 0, %vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg49,%vreg38 > 1152BJUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Live Register Matrix ***: > # Machine code for function main: Post SSA > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > 0BBB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > 16B%vreg1:sel_w<def,read-undef> = COPY %T1_W; R600_Reg128:%vreg1 > 32B%vreg1:sel_z<def> = COPY %T1_Z; R600_Reg128:%vreg1 > 48B%vreg1:sel_y<def> = COPY %T1_Y; R600_Reg128:%vreg1 > 64B%vreg1:sel_x<def> = COPY %T1_X; R600_Reg128:%vreg1 > 128B%vreg27:sel_x<def,read-undef> = COPY %C1_X; R600_Reg128:%vreg27 > 192B%vreg27:sel_y<def> = COPY %C1_Y; R600_Reg128:%vreg27 > 272B%vreg27:sel_z<def> = COPY %C1_Z; R600_Reg128:%vreg27 > 320B%vreg27:sel_w<def> = COPY %C1_W; R600_Reg128:%vreg27 > 368B%vreg49<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg49 > Successors according to CFG: BB#1 > > 448BBB#1: derived from LLVM BB %25 > Predecessors according to CFG: BB#0 BB#3 > 512B%vreg30<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %vreg49, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg30,%vreg49 > 544B%PREDICATE_BIT<def> = PRED_X %vreg30, 152, 16; R600_Reg32:%vreg30 > 560BJUMP <BB#3>, pred:%PREDICATE_BIT > 576BJUMP <BB#2>, pred:%noreg > Successors according to CFG: BB#2(4) BB#3(124) > > 592BBB#2: derived from LLVM BB %31 > Predecessors according to CFG: BB#1 > 624B%T2_X<def> = COPY %vreg27:sel_x; R600_Reg128:%vreg27 > 656B%T2_Y<def> = COPY %vreg27:sel_y; R600_Reg128:%vreg27 > 688B%T2_Z<def> = COPY %vreg27:sel_z; R600_Reg128:%vreg27 > 720B%T2_W<def> = COPY %vreg27:sel_w; R600_Reg128:%vreg27 > 752B%T1_X<def> = COPY %vreg1:sel_x; R600_Reg128:%vreg1 > 784B%T1_Y<def> = COPY %vreg1:sel_y; R600_Reg128:%vreg1 > 816B%T1_Z<def> = COPY %vreg1:sel_z; R600_Reg128:%vreg1 > 848B%T1_W<def> = COPY %vreg1:sel_w; R600_Reg128:%vreg1 > 864BRETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>, %T1_X<imp-use>, %T2_W<imp-use,kill>, %T2_Z<imp-use,kill>, %T2_Y<imp-use,kill>, %T2_X<imp-use,kill> > > 880BBB#3: derived from LLVM BB %41 > Predecessors according to CFG: BB#1 > 1072B%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38 > 1088B%vreg49<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg49, 0, 0, 0, %vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg49,%vreg38 > 1152BJUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Virtual Register Rewriter ***: > # Machine code for function main: Post SSA > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > 0BBB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > 16B%vreg1:sel_w<def,read-undef> = COPY %T1_W; R600_Reg128:%vreg1 > 32B%vreg1:sel_z<def> = COPY %T1_Z; R600_Reg128:%vreg1 > 48B%vreg1:sel_y<def> = COPY %T1_Y; R600_Reg128:%vreg1 > 64B%vreg1:sel_x<def> = COPY %T1_X; R600_Reg128:%vreg1 > 128B%vreg27:sel_x<def,read-undef> = COPY %C1_X; R600_Reg128:%vreg27 > 192B%vreg27:sel_y<def> = COPY %C1_Y; R600_Reg128:%vreg27 > 272B%vreg27:sel_z<def> = COPY %C1_Z; R600_Reg128:%vreg27 > 320B%vreg27:sel_w<def> = COPY %C1_W; R600_Reg128:%vreg27 > 368B%vreg49<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg49 > Successors according to CFG: BB#1 > > 448BBB#1: derived from LLVM BB %25 > Predecessors according to CFG: BB#0 BB#3 > 512B%vreg30<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %vreg49, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg30,%vreg49 > 544B%PREDICATE_BIT<def> = PRED_X %vreg30, 152, 16; R600_Reg32:%vreg30 > 560BJUMP <BB#3>, pred:%PREDICATE_BIT > 576BJUMP <BB#2>, pred:%noreg > Successors according to CFG: BB#2(4) BB#3(124) > > 592BBB#2: derived from LLVM BB %31 > Predecessors according to CFG: BB#1 > 624B%T2_X<def> = COPY %vreg27:sel_x; R600_Reg128:%vreg27 > 656B%T2_Y<def> = COPY %vreg27:sel_y; R600_Reg128:%vreg27 > 688B%T2_Z<def> = COPY %vreg27:sel_z; R600_Reg128:%vreg27 > 720B%T2_W<def> = COPY %vreg27:sel_w; R600_Reg128:%vreg27 > 752B%T1_X<def> = COPY %vreg1:sel_x; R600_Reg128:%vreg1 > 784B%T1_Y<def> = COPY %vreg1:sel_y; R600_Reg128:%vreg1 > 816B%T1_Z<def> = COPY %vreg1:sel_z; R600_Reg128:%vreg1 > 848B%T1_W<def> = COPY %vreg1:sel_w; R600_Reg128:%vreg1 > 864BRETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>, %T1_X<imp-use>, %T2_W<imp-use>, %T2_Z<imp-use>, %T2_Y<imp-use>, %T2_X<imp-use> > > 880BBB#3: derived from LLVM BB %41 > Predecessors according to CFG: BB#1 > 1072B%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38 > 1088B%vreg49<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg49, 0, 0, 0, %vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg49,%vreg38 > 1152BJUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Stack Slot Coloring ***: > # Machine code for function main: Post SSA > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > 0BBB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > 16B%T1_W<def> = KILL %T1_W, %T1_XYZW<imp-def> > 32B%T1_Z<def> = KILL %T1_Z, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > 48B%T1_Y<def> = KILL %T1_Y, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > 64B%T1_X<def> = KILL %T1_X, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > 128B%T2_X<def> = COPY %C1_X, %T2_XYZW<imp-def> > 192B%T2_Y<def> = COPY %C1_Y, %T2_XYZW<imp-use,kill>, %T2_XYZW<imp-def> > 272B%T2_Z<def> = COPY %C1_Z, %T2_XYZW<imp-use,kill>, %T2_XYZW<imp-def> > 320B%T2_W<def> = COPY %C1_W, %T2_XYZW<imp-use,kill>, %T2_XYZW<imp-def> > 368B%T3_X<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > Successors according to CFG: BB#1 > > 448BBB#1: derived from LLVM BB %25 > Live Ins: %T1_XYZW %T2_XYZW %T3_X > Predecessors according to CFG: BB#0 BB#3 > 512B%T3_Y<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %T3_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > 544B%PREDICATE_BIT<def> = PRED_X %T3_Y<kill>, 152, 16 > 560BJUMP <BB#3>, pred:%PREDICATE_BIT > 576BJUMP <BB#2>, pred:%noreg > Successors according to CFG: BB#2(4) BB#3(124) > > 592BBB#2: derived from LLVM BB %31 > Live Ins: %T1_XYZW %T2_XYZW > Predecessors according to CFG: BB#1 > 864BRETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>, %T1_X<imp-use>, %T2_W<imp-use>, %T2_Z<imp-use>, %T2_Y<imp-use>, %T2_X<imp-use> > > 880BBB#3: derived from LLVM BB %41 > Live Ins: %T1_XYZW %T2_XYZW %T3_X > Predecessors according to CFG: BB#1 > 1072B%T3_Y<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1 > 1088B%T3_X<def> = ADD_INT 0, 0, 1, 0, 0, 0, %T3_X<kill>, 0, 0, 0, %T3_Y<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > 1152BJUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Machine Loop Invariant Code Motion ***: > # Machine code for function main: Post SSA > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > BB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > %T1_W<def> = KILL %T1_W, %T1_XYZW<imp-def> > %T1_Z<def> = KILL %T1_Z, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > %T1_Y<def> = KILL %T1_Y, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > %T1_X<def> = KILL %T1_X, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > %T2_X<def> = COPY %C1_X, %T2_XYZW<imp-def> > %T2_Y<def> = COPY %C1_Y, %T2_XYZW<imp-use,kill>, %T2_XYZW<imp-def> > %T2_Z<def> = COPY %C1_Z, %T2_XYZW<imp-use,kill>, %T2_XYZW<imp-def> > %T2_W<def> = COPY %C1_W, %T2_XYZW<imp-use,kill>, %T2_XYZW<imp-def> > %T3_X<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > Successors according to CFG: BB#1 > > BB#1: derived from LLVM BB %25 > Live Ins: %T1_XYZW %T2_XYZW %T3_X > Predecessors according to CFG: BB#0 BB#3 > %T3_Y<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %T3_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > %PREDICATE_BIT<def> = PRED_X %T3_Y<kill>, 152, 16 > JUMP <BB#3>, pred:%PREDICATE_BIT > JUMP <BB#2>, pred:%noreg > Successors according to CFG: BB#2(4) BB#3(124) > > BB#2: derived from LLVM BB %31 > Live Ins: %T1_XYZW %T2_XYZW > Predecessors according to CFG: BB#1 > RETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>, %T1_X<imp-use>, %T2_W<imp-use>, %T2_Z<imp-use>, %T2_Y<imp-use>, %T2_X<imp-use> > > BB#3: derived from LLVM BB %41 > Live Ins: %T1_XYZW %T2_XYZW %T3_X > Predecessors according to CFG: BB#1 > %T3_Y<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1 > %T3_X<def> = ADD_INT 0, 0, 1, 0, 0, 0, %T3_X<kill>, 0, 0, 0, %T3_Y<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > JUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Prologue/Epilogue Insertion & Frame Finalization ***: > # Machine code for function main: Post SSA > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > BB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > %T1_W<def> = KILL %T1_W, %T1_XYZW<imp-def> > %T1_Z<def> = KILL %T1_Z, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > %T1_Y<def> = KILL %T1_Y, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > %T1_X<def> = KILL %T1_X, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > %T2_X<def> = COPY %C1_X, %T2_XYZW<imp-def> > %T2_Y<def> = COPY %C1_Y, %T2_XYZW<imp-use,kill>, %T2_XYZW<imp-def> > %T2_Z<def> = COPY %C1_Z, %T2_XYZW<imp-use,kill>, %T2_XYZW<imp-def> > %T2_W<def> = COPY %C1_W, %T2_XYZW<imp-use,kill>, %T2_XYZW<imp-def> > %T3_X<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > Successors according to CFG: BB#1 > > BB#1: derived from LLVM BB %25 > Live Ins: %T1_XYZW %T2_XYZW %T3_X > Predecessors according to CFG: BB#0 BB#3 > %T3_Y<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %T3_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > %PREDICATE_BIT<def> = PRED_X %T3_Y<kill>, 152, 16 > JUMP <BB#3>, pred:%PREDICATE_BIT > JUMP <BB#2>, pred:%noreg > Successors according to CFG: BB#2(4) BB#3(124) > > BB#2: derived from LLVM BB %31 > Live Ins: %T1_XYZW %T2_XYZW > Predecessors according to CFG: BB#1 > RETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>, %T1_X<imp-use>, %T2_W<imp-use>, %T2_Z<imp-use>, %T2_Y<imp-use>, %T2_X<imp-use> > > BB#3: derived from LLVM BB %41 > Live Ins: %T1_XYZW %T2_XYZW %T3_X > Predecessors according to CFG: BB#1 > %T3_Y<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1 > %T3_X<def> = ADD_INT 0, 0, 1, 0, 0, 0, %T3_X<kill>, 0, 0, 0, %T3_Y<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > JUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Control Flow Optimizer ***: > # Machine code for function main: Post SSA > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > BB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > %T1_W<def> = KILL %T1_W, %T1_XYZW<imp-def> > %T1_Z<def> = KILL %T1_Z, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > %T1_Y<def> = KILL %T1_Y, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > %T1_X<def> = KILL %T1_X, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > %T2_X<def> = COPY %C1_X, %T2_XYZW<imp-def> > %T2_Y<def> = COPY %C1_Y, %T2_XYZW<imp-use,kill>, %T2_XYZW<imp-def> > %T2_Z<def> = COPY %C1_Z, %T2_XYZW<imp-use,kill>, %T2_XYZW<imp-def> > %T2_W<def> = COPY %C1_W, %T2_XYZW<imp-use,kill>, %T2_XYZW<imp-def> > %T3_X<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > Successors according to CFG: BB#1 > > BB#1: derived from LLVM BB %25 > Live Ins: %T1_XYZW %T2_XYZW %T3_X > Predecessors according to CFG: BB#0 BB#3 > %T3_Y<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %T3_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > %PREDICATE_BIT<def> = PRED_X %T3_Y<kill>, 152, 16 > JUMP <BB#3>, pred:%PREDICATE_BIT > JUMP <BB#2>, pred:%noreg > Successors according to CFG: BB#2(4) BB#3(124) > > BB#2: derived from LLVM BB %31 > Live Ins: %T1_XYZW %T2_XYZW > Predecessors according to CFG: BB#1 > RETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>, %T1_X<imp-use>, %T2_W<imp-use>, %T2_Z<imp-use>, %T2_Y<imp-use>, %T2_X<imp-use> > > BB#3: derived from LLVM BB %41 > Live Ins: %T1_XYZW %T2_XYZW %T3_X > Predecessors according to CFG: BB#1 > %T3_Y<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1 > %T3_X<def> = ADD_INT 0, 0, 1, 0, 0, 0, %T3_X<kill>, 0, 0, 0, %T3_Y<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > JUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Tail Duplication ***: > # Machine code for function main: Post SSA, not tracking liveness > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > BB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > %T1_W<def> = KILL %T1_W, %T1_XYZW<imp-def> > %T1_Z<def> = KILL %T1_Z, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > %T1_Y<def> = KILL %T1_Y, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > %T1_X<def> = KILL %T1_X, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > %T2_X<def> = COPY %C1_X, %T2_XYZW<imp-def> > %T2_Y<def> = COPY %C1_Y, %T2_XYZW<imp-use,kill>, %T2_XYZW<imp-def> > %T2_Z<def> = COPY %C1_Z, %T2_XYZW<imp-use,kill>, %T2_XYZW<imp-def> > %T2_W<def> = COPY %C1_W, %T2_XYZW<imp-use,kill>, %T2_XYZW<imp-def> > %T3_X<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > Successors according to CFG: BB#1 > > BB#1: derived from LLVM BB %25 > Live Ins: %T1_XYZW %T2_XYZW %T3_X > Predecessors according to CFG: BB#0 BB#3 > %T3_Y<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %T3_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > %PREDICATE_BIT<def> = PRED_X %T3_Y<kill>, 152, 16 > JUMP <BB#3>, pred:%PREDICATE_BIT<kill> > Successors according to CFG: BB#2(4) BB#3(124) > > BB#2: derived from LLVM BB %31 > Live Ins: %T1_XYZW %T2_XYZW > Predecessors according to CFG: BB#1 > RETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>, %T1_X<imp-use>, %T2_W<imp-use>, %T2_Z<imp-use>, %T2_Y<imp-use>, %T2_X<imp-use> > > BB#3: derived from LLVM BB %41 > Live Ins: %T1_XYZW %T2_XYZW %T3_X > Predecessors according to CFG: BB#1 > %T3_Y<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1 > %T3_X<def> = ADD_INT 0, 0, 1, 0, 0, 0, %T3_X<kill>, 0, 0, 0, %T3_Y<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > JUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Machine Copy Propagation Pass ***: > # Machine code for function main: Post SSA, not tracking liveness > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > BB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > %T1_W<def> = KILL %T1_W, %T1_XYZW<imp-def> > %T1_Z<def> = KILL %T1_Z, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > %T1_Y<def> = KILL %T1_Y, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > %T1_X<def> = KILL %T1_X, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > %T2_X<def> = COPY %C1_X, %T2_XYZW<imp-def> > %T2_Y<def> = COPY %C1_Y, %T2_XYZW<imp-use,kill>, %T2_XYZW<imp-def> > %T2_Z<def> = COPY %C1_Z, %T2_XYZW<imp-use,kill>, %T2_XYZW<imp-def> > %T2_W<def> = COPY %C1_W, %T2_XYZW<imp-use,kill>, %T2_XYZW<imp-def> > %T3_X<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > Successors according to CFG: BB#1 > > BB#1: derived from LLVM BB %25 > Live Ins: %T1_XYZW %T2_XYZW %T3_X > Predecessors according to CFG: BB#0 BB#3 > %T3_Y<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %T3_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > %PREDICATE_BIT<def> = PRED_X %T3_Y<kill>, 152, 16 > JUMP <BB#3>, pred:%PREDICATE_BIT<kill> > Successors according to CFG: BB#2(4) BB#3(124) > > BB#2: derived from LLVM BB %31 > Live Ins: %T1_XYZW %T2_XYZW > Predecessors according to CFG: BB#1 > RETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>, %T1_X<imp-use>, %T2_W<imp-use>, %T2_Z<imp-use>, %T2_Y<imp-use>, %T2_X<imp-use> > > BB#3: derived from LLVM BB %41 > Live Ins: %T1_XYZW %T2_XYZW %T3_X > Predecessors according to CFG: BB#1 > %T3_Y<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1 > %T3_X<def> = ADD_INT 0, 0, 1, 0, 0, 0, %T3_X<kill>, 0, 0, 0, %T3_Y<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > JUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Post-RA pseudo instruction expansion pass ***: > # Machine code for function main: Post SSA, not tracking liveness > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > BB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > %T1_W<def> = KILL %T1_W, %T1_XYZW<imp-def> > %T1_Z<def> = KILL %T1_Z, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > %T1_Y<def> = KILL %T1_Y, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > %T1_X<def> = KILL %T1_X, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > %T2_X<def> = COPY %C1_X, %T2_XYZW<imp-def> > %T2_Y<def> = COPY %C1_Y, %T2_XYZW<imp-use,kill>, %T2_XYZW<imp-def> > %T2_Z<def> = COPY %C1_Z, %T2_XYZW<imp-use,kill>, %T2_XYZW<imp-def> > %T2_W<def> = COPY %C1_W, %T2_XYZW<imp-use,kill>, %T2_XYZW<imp-def> > %T3_X<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > Successors according to CFG: BB#1 > > BB#1: derived from LLVM BB %25 > Live Ins: %T1_XYZW %T2_XYZW %T3_X > Predecessors according to CFG: BB#0 BB#3 > %T3_Y<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %T3_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > %PREDICATE_BIT<def> = PRED_X %T3_Y<kill>, 152, 16 > JUMP <BB#3>, pred:%PREDICATE_BIT<kill> > Successors according to CFG: BB#2(4) BB#3(124) > > BB#2: derived from LLVM BB %31 > Live Ins: %T1_XYZW %T2_XYZW > Predecessors according to CFG: BB#1 > RETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>, %T1_X<imp-use>, %T2_W<imp-use>, %T2_Z<imp-use>, %T2_Y<imp-use>, %T2_X<imp-use> > > BB#3: derived from LLVM BB %41 > Live Ins: %T1_XYZW %T2_XYZW %T3_X > Predecessors according to CFG: BB#1 > %T3_Y<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1 > %T3_X<def> = ADD_INT 0, 0, 1, 0, 0, 0, %T3_X<kill>, 0, 0, 0, %T3_Y<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > JUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before If Converter ***: > # Machine code for function main: Post SSA, not tracking liveness > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > BB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > %T1_W<def> = KILL %T1_W, %T1_XYZW<imp-def> > %T1_Z<def> = KILL %T1_Z, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > %T1_Y<def> = KILL %T1_Y, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > %T1_X<def> = KILL %T1_X, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > %T2_X<def> = MOV 1, 0, 0, 0, %C1_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T2_XYZW<imp-def> > %T2_Y<def> = MOV 1, 0, 0, 0, %C1_Y, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T2_XYZW<imp-def> > %T2_Z<def> = MOV 1, 0, 0, 0, %C1_Z, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T2_XYZW<imp-def> > %T2_W<def> = MOV 1, 0, 0, 0, %C1_W, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T2_XYZW<imp-def> > %T3_X<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > Successors according to CFG: BB#1 > > BB#1: derived from LLVM BB %25 > Live Ins: %T1_XYZW %T2_XYZW %T3_X > Predecessors according to CFG: BB#0 BB#3 > %T3_Y<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %T3_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > %PREDICATE_BIT<def> = PRED_X %T3_Y<kill>, 152, 16 > JUMP <BB#3>, pred:%PREDICATE_BIT<kill> > Successors according to CFG: BB#2(4) BB#3(124) > > BB#2: derived from LLVM BB %31 > Live Ins: %T1_XYZW %T2_XYZW > Predecessors according to CFG: BB#1 > RETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>, %T1_X<imp-use>, %T2_W<imp-use>, %T2_Z<imp-use>, %T2_Y<imp-use>, %T2_X<imp-use> > > BB#3: derived from LLVM BB %41 > Live Ins: %T1_XYZW %T2_XYZW %T3_X > Predecessors according to CFG: BB#1 > %T3_Y<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1 > %T3_X<def> = ADD_INT 0, 0, 1, 0, 0, 0, %T3_X<kill>, 0, 0, 0, %T3_Y<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > JUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Post RA top-down list latency scheduler ***: > # Machine code for function main: Post SSA, not tracking liveness > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > BB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > %T1_W<def> = KILL %T1_W, %T1_XYZW<imp-def> > %T1_Z<def> = KILL %T1_Z, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > %T1_Y<def> = KILL %T1_Y, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > %T1_X<def> = KILL %T1_X, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > %T2_X<def> = MOV 1, 0, 0, 0, %C1_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T2_XYZW<imp-def> > %T2_Y<def> = MOV 1, 0, 0, 0, %C1_Y, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T2_XYZW<imp-def> > %T2_Z<def> = MOV 1, 0, 0, 0, %C1_Z, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T2_XYZW<imp-def> > %T2_W<def> = MOV 1, 0, 0, 0, %C1_W, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T2_XYZW<imp-def> > %T3_X<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > Successors according to CFG: BB#1 > > BB#1: derived from LLVM BB %25 > Live Ins: %T1_XYZW %T2_XYZW %T3_X > Predecessors according to CFG: BB#0 BB#3 > %T3_Y<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %T3_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > %PREDICATE_BIT<def> = PRED_X %T3_Y<kill>, 152, 16 > JUMP <BB#3>, pred:%PREDICATE_BIT<kill> > Successors according to CFG: BB#2(4) BB#3(124) > > BB#2: derived from LLVM BB %31 > Live Ins: %T1_XYZW %T2_XYZW > Predecessors according to CFG: BB#1 > RETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>, %T1_X<imp-use>, %T2_W<imp-use>, %T2_Z<imp-use>, %T2_Y<imp-use>, %T2_X<imp-use> > > BB#3: derived from LLVM BB %41 > Live Ins: %T1_XYZW %T2_XYZW %T3_X > Predecessors according to CFG: BB#1 > %T3_Y<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1 > %T3_X<def> = ADD_INT 0, 0, 1, 0, 0, 0, %T3_X<kill>, 0, 0, 0, %T3_Y<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > JUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Analyze Machine Code For Garbage Collection ***: > # Machine code for function main: Post SSA, not tracking liveness > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > BB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > %T1_W<def> = KILL %T1_W, %T1_XYZW<imp-def> > %T1_Z<def> = KILL %T1_Z, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > %T1_Y<def> = KILL %T1_Y, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > %T1_X<def> = KILL %T1_X, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > %T2_X<def> = MOV 1, 0, 0, 0, %C1_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T2_XYZW<imp-def> > %T2_Y<def> = MOV 1, 0, 0, 0, %C1_Y, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T2_XYZW<imp-def> > %T2_Z<def> = MOV 1, 0, 0, 0, %C1_Z, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T2_XYZW<imp-def> > %T2_W<def> = MOV 1, 0, 0, 0, %C1_W, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T2_XYZW<imp-def> > %T3_X<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > Successors according to CFG: BB#1 > > BB#1: derived from LLVM BB %25 > Live Ins: %T1_XYZW %T2_XYZW %T3_X > Predecessors according to CFG: BB#0 BB#3 > %T3_Y<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %T3_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > %PREDICATE_BIT<def> = PRED_X %T3_Y<kill>, 152, 16 > JUMP <BB#3>, pred:%PREDICATE_BIT<kill> > Successors according to CFG: BB#2(4) BB#3(124) > > BB#2: derived from LLVM BB %31 > Live Ins: %T1_XYZW %T2_XYZW > Predecessors according to CFG: BB#1 > RETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>, %T1_X<imp-use>, %T2_W<imp-use>, %T2_Z<imp-use>, %T2_Y<imp-use>, %T2_X<imp-use> > > BB#3: derived from LLVM BB %41 > Live Ins: %T1_XYZW %T2_XYZW %T3_X > Predecessors according to CFG: BB#1 > %T3_Y<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1 > %T3_X<def> = ADD_INT 0, 0, 1, 0, 0, 0, %T3_X<kill>, 0, 0, 0, %T3_Y<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > JUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Branch Probability Basic Block Placement ***: > # Machine code for function main: Post SSA, not tracking liveness > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > BB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > %T1_W<def> = KILL %T1_W, %T1_XYZW<imp-def> > %T1_Z<def> = KILL %T1_Z, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > %T1_Y<def> = KILL %T1_Y, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > %T1_X<def> = KILL %T1_X, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > %T2_X<def> = MOV 1, 0, 0, 0, %C1_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T2_XYZW<imp-def> > %T2_Y<def> = MOV 1, 0, 0, 0, %C1_Y, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T2_XYZW<imp-def> > %T2_Z<def> = MOV 1, 0, 0, 0, %C1_Z, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T2_XYZW<imp-def> > %T2_W<def> = MOV 1, 0, 0, 0, %C1_W, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T2_XYZW<imp-def> > %T3_X<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > Successors according to CFG: BB#1 > > BB#1: derived from LLVM BB %25 > Live Ins: %T1_XYZW %T2_XYZW %T3_X > Predecessors according to CFG: BB#0 BB#3 > %T3_Y<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %T3_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > %PREDICATE_BIT<def> = PRED_X %T3_Y<kill>, 152, 16 > JUMP <BB#3>, pred:%PREDICATE_BIT<kill> > Successors according to CFG: BB#2(4) BB#3(124) > > BB#2: derived from LLVM BB %31 > Live Ins: %T1_XYZW %T2_XYZW > Predecessors according to CFG: BB#1 > RETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>, %T1_X<imp-use>, %T2_W<imp-use>, %T2_Z<imp-use>, %T2_Y<imp-use>, %T2_X<imp-use> > > BB#3: derived from LLVM BB %41 > Live Ins: %T1_XYZW %T2_XYZW %T3_X > Predecessors according to CFG: BB#1 > %T3_Y<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1 > %T3_X<def> = ADD_INT 0, 0, 1, 0, 0, 0, %T3_X<kill>, 0, 0, 0, %T3_Y<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > JUMP <BB#1>, pred:%noreg > Successors according to CFG: BB#1 > > # End machine code for function main. > > # *** IR Dump Before Finalize machine instruction bundles ***: > # Machine code for function main: Post SSA, not tracking liveness > Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 > Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X > > BB#0: derived from LLVM BB %0 > Live Ins: %T1_X %T1_Y %T1_Z %T1_W > %T1_W<def> = KILL %T1_W, %T1_XYZW<imp-def> > %T1_Z<def> = KILL %T1_Z, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > %T1_Y<def> = KILL %T1_Y, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > %T1_X<def> = KILL %T1_X, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def> > %T2_X<def> = MOV 1, 0, 0, 0, %C1_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T2_XYZW<imp-def> > %T2_Y<def> = MOV 1, 0, 0, 0, %C1_Y, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T2_XYZW<imp-def> > %T2_Z<def> = MOV 1, 0, 0, 0, %C1_Z, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T2_XYZW<imp-def> > %T2_W<def> = MOV 1, 0, 0, 0, %C1_W, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T2_XYZW<imp-def> > %T3_X<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > WHILELOOP > %T3_Y<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %T3_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > %PREDICATE_BIT<def> = PRED_SETE_INT 1, 0, 0, 0, 0, 0, %T3_Y, 0, 0, 0, %ZERO, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > BREAK_LOGICALZ_i32 %PREDICATE_BIT > %T3_Y<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1 > %T3_X<def> = ADD_INT 0, 0, 1, 0, 0, 0, %T3_X<kill>, 0, 0, 0, %T3_Y<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > ENDLOOP > RETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>, %T1_X<imp-use>, %T2_W<imp-use>, %T2_Z<imp-use>, %T2_Y<imp-use>, %T2_X<imp-use> > > # End machine code for function main. > > > _______________________________________________ > LLVM Developers mailing list > LLVMdev at cs.uiuc.edu http://llvm.cs.uiuc.edu > http://lists.cs.uiuc.edu/mailman/listinfo/llvmdev
Vincent Lejeune
2012-Oct-25 15:35 UTC
[LLVMdev] RegisterCoalescing Pass seems to ignore part of CFG.
Thank for your answer. If I set EnableJoining to false (ie moreless disable the regcoalescer pass), my shader is correct (but with many uneeded MOV) : BB#0: derived from LLVM BB %0 Live Ins: %T1_X %T1_Y %T1_Z %T1_W %T2_Y<def> = MOV 1, 0, 0, 0, %C1_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 %T3_X<def> = MOV 1, 0, 0, 0, %T1_X<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T3_XYZW<imp-def> %T2_X<def> = MOV 1, 0, 0, 0, %C1_Y, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 %T4_X<def> = MOV 1, 0, 0, 0, %T2_Y<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T4_XYZW<imp-def> %T3_Y<def> = MOV 1, 0, 0, 0, %T1_Y<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T3_XYZW<imp-def> %T4_Y<def> = MOV 1, 0, 0, 0, %T2_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T4_XYZW<imp-def> %T1_X<def> = MOV 1, 0, 0, 0, %C1_Z, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 %T3_Z<def> = MOV 1, 0, 0, 0, %T1_Z<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T3_XYZW<imp-def> %T4_Z<def> = MOV 1, 0, 0, 0, %T1_X<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T4_XYZW<imp-def> %T1_X<def> = MOV 1, 0, 0, 0, %C1_W, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 %T4_W<def> = MOV 1, 0, 0, 0, %T1_X<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T4_XYZW<imp-def> %T3_W<def> = MOV 1, 0, 0, 0, %T1_W<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T3_XYZW<imp-def> %T1_W<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 %T1_X<def> = MOV 1, 0, 0, 0, %C0_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 %T1_Y<def> = MOV 1, 0, 0, 0, %T2_X<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 %T2_X<def> = MOV 1, 0, 0, 0, %T4_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T2_XYZW<imp-def> %T2_Y<def> = MOV 1, 0, 0, 0, %T4_Y, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T2_XYZW<imp-def> %T2_Z<def> = MOV 1, 0, 0, 0, %T4_Z, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T2_XYZW<imp-def> %T2_W<def> = MOV 1, 0, 0, 0, %T4_W, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T2_XYZW<imp-def> WHILELOOP %T1_Z<def> = MOV 1, 0, 0, 0, %T1_Y<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 %T4_X<def> = MOV 1, 0, 0, 0, %T2_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T4_XYZW<imp-def> %T4_Y<def> = MOV 1, 0, 0, 0, %T2_Y, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T4_XYZW<imp-def> %T4_Z<def> = MOV 1, 0, 0, 0, %T2_Z, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T4_XYZW<imp-def> %T4_W<def> = MOV 1, 0, 0, 0, %T2_W, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T4_XYZW<imp-def> %T1_Y<def> = MOV 1, 0, 0, 0, %T1_W<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 %T1_W<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %T1_X, 0, 0, 0, %T1_Y, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 %PREDICATE_BIT<def> = PRED_SETE_INT 1, 0, 0, 0, 0, 0, %T1_W, 0, 0, 0, %ZERO, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 BREAK_LOGICALZ_i32 %PREDICATE_BIT %T1_W<def> = MOV 1, 0, 0, 0, %T4_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 %T2_X<def> = MOV 1, 0, 0, 0, %T1_W<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T2_XYZW<imp-def> %T1_W<def> = MOV 1, 0, 0, 0, %T4_Y, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 %T2_Y<def> = MOV 1, 0, 0, 0, %T1_W<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T2_XYZW<imp-def> %T2_Z<def> = MOV 1, 0, 0, 0, %T1_Z<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T2_XYZW<imp-def> %T1_Z<def> = MOV 1, 0, 0, 0, %T4_W, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 %T2_W<def> = MOV 1, 0, 0, 0, %T1_Z<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0, %T2_XYZW<imp-def> %T1_Z<def> = MOV 1, 0, 0, 0, %T4_Z, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 %T1_W<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1 %T1_W<def> = ADD_INT 0, 0, 1, 0, 0, 0, %T1_Y<kill>, 0, 0, 0, %T1_W<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 %T1_Y<def> = MOV 1, 0, 0, 0, %T1_Z<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 ENDLOOP %T2_X<def> = MOV 1, 0, 0, 0, %T4_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 %T2_Y<def> = MOV 1, 0, 0, 0, %T4_Y, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 %T2_Z<def> = MOV 1, 0, 0, 0, %T4_Z, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 %T2_W<def> = MOV 1, 0, 0, 0, %T4_W, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 %T1_X<def> = MOV 1, 0, 0, 0, %T3_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 %T1_Y<def> = MOV 1, 0, 0, 0, %T3_Y, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 %T1_Z<def> = MOV 1, 0, 0, 0, %T3_Z, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 %T1_W<def> = MOV 1, 0, 0, 0, %T3_W, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 RETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>, %T1_X<imp-use>, %T2_W<imp-use>, %T2_Z<imp-use>, %T2_Y<imp-use>, %T2_X<imp-use> This makes me think that the bug is inside llvm. If I understand your point, it might be inside the phielim pass ? I don't know if I can disable it to track down what's happening (I'm not sure following pass can handle phi properly) Vincent>> >> >> Apparently, the pass assumed that it's still in SSA mode, and join > vreg6 with vreg27, thus ignoring the body block that can modify vreg48 value, > and thus vreg6 value. >> I don't know if I should manually tell the pass that it's not in > SSA mode (I assume that previous pass like 2 address simplification pass does > it), if I miss something in my LLVM IR, >> or if it's a bug. > > PHIElim and TwoAddress passes leave SSA form. > May be a missed something in your code but %vreg48 seems to be there > after PHI elimination. PHIElim tags those kind of registers as being > PHIJoin regs, updating LiveVariables pass, so the regcoalescer is aware > of them (some SSA info is still alive but the reg coalescer will > invalidate that information after joining intervals). PHIJoin regs > doesn't get modified by any other instruction than copies. > Anyway, IMHO if your code is faulty there should be a bug somewhere else. > > Ivan > >>
Vincent Lejeune
2012-Oct-25 15:54 UTC
[LLVMdev] RegisterCoalescing Pass seems to ignore part of CFG.
> > PHIElim and TwoAddress passes leave SSA form. > May be a missed something in your code but %vreg48 seems to be there > after PHI elimination. PHIElim tags those kind of registers as being > PHIJoin regs, updating LiveVariables pass, so the regcoalescer is aware > of them (some SSA info is still alive but the reg coalescer will > invalidate that information after joining intervals). PHIJoin regs > doesn't get modified by any other instruction than copies. > Anyway, IMHO if your code is faulty there should be a bug somewhere else. >It seems the PhiElim is working correctly, the output of --debug-only=regalloc shows that %vreg48 is a phi-join register, and intervals looks correct to me : ********** COMPUTING LIVE INTERVALS ********** ********** Function: main BB#0:# derived from 16B%vreg17<def> = COPY %T1_W<kill>; R600_TReg32:%vreg17 register: %vreg17 +[16r,352r:0) 32B%vreg16<def> = COPY %T1_Z<kill>; R600_TReg32:%vreg16 register: %vreg16 +[32r,240r:0) 48B%vreg15<def> = COPY %T1_Y<kill>; R600_TReg32:%vreg15 register: %vreg15 +[48r,160r:0) 64B%vreg14<def> = COPY %T1_X<kill>; R600_TReg32:%vreg14 register: %vreg14 +[64r,96r:0) 80B%vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18 register: %vreg18 +[80r,128r:0) 96B%vreg19:sel_x<def,read-undef> = COPY %vreg14<kill>; R600_Reg128:%vreg19 R600_TReg32:%vreg14 register: %vreg19 +[96r,144r:0) 112B%vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2 register: %vreg2 +[112r,400r:0) 128B%vreg21:sel_x<def,read-undef> = COPY %vreg18<kill>; R600_Reg128:%vreg21 R600_Reg32:%vreg18 register: %vreg21 +[128r,176r:0) 144B%vreg23<def> = COPY %vreg19<kill>; R600_Reg128:%vreg23,%vreg19 register: %vreg23 +[144r,224r:0) 160B%vreg23:sel_y<def> = COPY %vreg15<kill>; R600_Reg128:%vreg23 R600_TReg32:%vreg15 register: %vreg23 replace range with [144r,160r:1) RESULT: [144r,160r:1)[160r,224r:0) 0 at 160r 1 at 144r 176B%vreg24<def> = COPY %vreg21<kill>; R600_Reg128:%vreg24,%vreg21 register: %vreg24 +[176r,256r:0) 192B%vreg24:sel_y<def> = COPY %vreg2; R600_Reg128:%vreg24 R600_Reg32:%vreg2 register: %vreg24 replace range with [176r,192r:1) RESULT: [176r,192r:1)[192r,256r:0) 0 at 192r 1 at 176r 208B%vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25 register: %vreg25 +[208r,272r:0) 224B%vreg26<def> = COPY %vreg23<kill>; R600_Reg128:%vreg26,%vreg23 register: %vreg26 +[224r,336r:0) 240B%vreg26:sel_z<def> = COPY %vreg16<kill>; R600_Reg128:%vreg26 R600_TReg32:%vreg16 register: %vreg26 replace range with [224r,240r:1) RESULT: [224r,240r:1)[240r,336r:0) 0 at 240r 1 at 224r 256B%vreg27<def> = COPY %vreg24<kill>; R600_Reg128:%vreg27,%vreg24 register: %vreg27 +[256r,304r:0) 272B%vreg27:sel_z<def> = COPY %vreg25<kill>; R600_Reg128:%vreg27 R600_Reg32:%vreg25 register: %vreg27 replace range with [256r,272r:1) RESULT: [256r,272r:1)[272r,304r:0) 0 at 272r 1 at 256r 288B%vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28 register: %vreg28 +[288r,320r:0) 304B%vreg3<def> = COPY %vreg27<kill>; R600_Reg128:%vreg3,%vreg27 register: %vreg3 +[304r,416r:0) 320B%vreg3:sel_w<def> = COPY %vreg28<kill>; R600_Reg128:%vreg3 R600_Reg32:%vreg28 register: %vreg3 replace range with [304r,320r:1) RESULT: [304r,320r:1)[320r,416r:0) 0 at 320r 1 at 304r 336B%vreg1<def> = COPY %vreg26<kill>; R600_Reg128:%vreg1,%vreg26 register: %vreg1 +[336r,448B:0) +[448B,592B:0) +[880B,1168B:0) +[592B,832r:0) 352B%vreg1:sel_w<def> = COPY %vreg17<kill>; R600_Reg128:%vreg1 R600_TReg32:%vreg17 register: %vreg1 replace range with [336r,352r:1) RESULT: [336r,352r:1)[352r,832r:0)[880B,1168B:0) 0 at 352r 1 at 336r 368B%vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13 register: %vreg13 +[368r,432r:0) 384B%vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0 register: %vreg0 +[384r,448B:0) +[448B,592B:0) +[880B,1168B:0) 400B%vreg47<def> = COPY %vreg2<kill>; R600_Reg32:%vreg47,%vreg2 register: %vreg47 +[400r,448B:0) phi-join +[448B,464r:1) 416B%vreg48<def> = COPY %vreg3<kill>; R600_Reg128:%vreg48,%vreg3 register: %vreg48 +[416r,448B:0) phi-join +[448B,480r:1) 432B%vreg49<def> = COPY %vreg13<kill>; R600_Reg32:%vreg49,%vreg13 register: %vreg49 +[432r,448B:0) phi-join +[448B,496r:1) BB#1:# derived from 464B%vreg5<def> = COPY %vreg47<kill>; R600_Reg32:%vreg5,%vreg47 register: %vreg5 +[464r,592B:0) +[880B,992r:0) 480B%vreg6<def> = COPY %vreg48<kill>; R600_Reg128:%vreg6,%vreg48 register: %vreg6 +[480r,592B:0) +[592B,704r:0) +[880B,1056r:0) 496B%vreg7<def> = COPY %vreg49<kill>; R600_Reg32:%vreg7,%vreg49 register: %vreg7 +[496r,592B:0) +[880B,1088r:0) 512B%vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7 register: %vreg29 +[512r,528r:0) 528B%vreg30<def> = COPY %vreg29<kill>; R600_Reg32:%vreg30,%vreg29 register: %vreg30 +[528r,544r:0) 544B%PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16; R600_Reg32:%vreg30 560BJUMP <BB#3>, pred:%PREDICATE_BIT 576BJUMP <BB#2>, pred:%noreg BB#2:# derived from 608B%vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6 register: %vreg39 +[608r,624r:0) 624B%T2_X<def> = COPY %vreg39<kill>; R600_Reg32:%vreg39 640B%vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6 register: %vreg40 +[640r,656r:0) 656B%T2_Y<def> = COPY %vreg40<kill>; R600_Reg32:%vreg40 672B%vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6 register: %vreg41 +[672r,688r:0) 688B%T2_Z<def> = COPY %vreg41<kill>; R600_Reg32:%vreg41 704B%vreg42<def> = COPY %vreg6:sel_w<kill>; R600_Reg32:%vreg42 R600_Reg128:%vreg6 register: %vreg42 +[704r,720r:0) 720B%T2_W<def> = COPY %vreg42<kill>; R600_Reg32:%vreg42 736B%vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1 register: %vreg43 +[736r,752r:0) 752B%T1_X<def> = COPY %vreg43<kill>; R600_Reg32:%vreg43 768B%vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1 register: %vreg44 +[768r,784r:0) 784B%T1_Y<def> = COPY %vreg44<kill>; R600_Reg32:%vreg44 800B%vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1 register: %vreg45 +[800r,816r:0) 816B%T1_Z<def> = COPY %vreg45<kill>; R600_Reg32:%vreg45 832B%vreg46<def> = COPY %vreg1:sel_w<kill>; R600_Reg32:%vreg46 R600_Reg128:%vreg1 register: %vreg46 +[832r,848r:0) 848B%T1_W<def> = COPY %vreg46<kill>; R600_Reg32:%vreg46 864BRETURN %T1_W<imp-use,kill>, %T1_Z<imp-use,kill>, %T1_Y<imp-use,kill>, %T1_X<imp-use,kill>, %T2_W<imp-use,kill>, %T2_Z<imp-use,kill>, %T2_Y<imp-use,kill>, %T2_X<imp-use,kill> BB#3:# derived from 896B%vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6 register: %vreg31 +[896r,912r:0) 912B%vreg32:sel_x<def,read-undef> = COPY %vreg31<kill>; R600_Reg128:%vreg32 R600_Reg32:%vreg31 register: %vreg32 +[912r,944r:0) 928B%vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6 register: %vreg34 +[928r,960r:0) 944B%vreg35<def> = COPY %vreg32<kill>; R600_Reg128:%vreg35,%vreg32 register: %vreg35 +[944r,976r:0) 960B%vreg35:sel_y<def> = COPY %vreg34<kill>; R600_Reg128:%vreg35 R600_Reg32:%vreg34 register: %vreg35 replace range with [944r,960r:1) RESULT: [944r,960r:1)[960r,976r:0) 0 at 960r 1 at 944r 976B%vreg36<def> = COPY %vreg35<kill>; R600_Reg128:%vreg36,%vreg35 register: %vreg36 +[976r,1024r:0) 992B%vreg36:sel_z<def> = COPY %vreg5<kill>; R600_Reg128:%vreg36 R600_Reg32:%vreg5 register: %vreg36 replace range with [976r,992r:1) RESULT: [976r,992r:1)[992r,1024r:0) 0 at 992r 1 at 976r 1008B%vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6 register: %vreg37 +[1008r,1040r:0) 1024B%vreg10<def> = COPY %vreg36<kill>; R600_Reg128:%vreg10,%vreg36 register: %vreg10 +[1024r,1120r:0) 1040B%vreg10:sel_w<def> = COPY %vreg37<kill>; R600_Reg128:%vreg10 R600_Reg32:%vreg37 register: %vreg10 replace range with [1024r,1040r:1) RESULT: [1024r,1040r:1)[1040r,1120r:0) 0 at 1040r 1 at 1024r 1056B%vreg9<def> = COPY %vreg6:sel_z<kill>; R600_Reg32:%vreg9 R600_Reg128:%vreg6 register: %vreg9 +[1056r,1104r:0) 1072B%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38 register: %vreg38 +[1072r,1088r:0) 1088B%vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7<kill>, 0, 0, 0, %vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg11,%vreg7,%vreg38 register: %vreg11 +[1088r,1136r:0) 1104B%vreg47<def> = COPY %vreg9<kill>; R600_Reg32:%vreg47,%vreg9 register: %vreg47 phi-join +[1104r,1168B:2) 1120B%vreg48<def> = COPY %vreg10<kill>; R600_Reg128:%vreg48,%vreg10 register: %vreg48 phi-join +[1120r,1168B:2) 1136B%vreg49<def> = COPY %vreg11<kill>; R600_Reg32:%vreg49,%vreg11 register: %vreg49 phi-join +[1136r,1168B:2) 1152BJUMP <BB#1>, pred:%noreg Computing live-in reg-units in ABI blocks. 0BBB#0 T1_X#0 T1_Y#0 T1_Z#0 T1_W#0 Created 4 new intervals. ********** INTERVALS ********** T1_W = [0B,16r:0)[848r,864r:1) 0 at 0B-phi 1 at 848r T1_X = [0B,64r:0)[752r,864r:1) 0 at 0B-phi 1 at 752r T1_Y = [0B,48r:0)[784r,864r:1) 0 at 0B-phi 1 at 784r T1_Z = [0B,32r:0)[816r,864r:1) 0 at 0B-phi 1 at 816r %vreg0 = [384r,592B:0)[880B,1168B:0) 0 at 384r %vreg1 = [336r,352r:1)[352r,832r:0)[880B,1168B:0) 0 at 352r 1 at 336r %vreg2 = [112r,400r:0) 0 at 112r %vreg3 = [304r,320r:1)[320r,416r:0) 0 at 320r 1 at 304r %vreg5 = [464r,592B:0)[880B,992r:0) 0 at 464r %vreg6 = [480r,704r:0)[880B,1056r:0) 0 at 480r %vreg7 = [496r,592B:0)[880B,1088r:0) 0 at 496r %vreg9 = [1056r,1104r:0) 0 at 1056r %vreg10 = [1024r,1040r:1)[1040r,1120r:0) 0 at 1040r 1 at 1024r %vreg11 = [1088r,1136r:0) 0 at 1088r %vreg13 = [368r,432r:0) 0 at 368r %vreg14 = [64r,96r:0) 0 at 64r %vreg15 = [48r,160r:0) 0 at 48r %vreg16 = [32r,240r:0) 0 at 32r %vreg17 = [16r,352r:0) 0 at 16r %vreg18 = [80r,128r:0) 0 at 80r %vreg19 = [96r,144r:0) 0 at 96r %vreg21 = [128r,176r:0) 0 at 128r %vreg23 = [144r,160r:1)[160r,224r:0) 0 at 160r 1 at 144r %vreg24 = [176r,192r:1)[192r,256r:0) 0 at 192r 1 at 176r %vreg25 = [208r,272r:0) 0 at 208r %vreg26 = [224r,240r:1)[240r,336r:0) 0 at 240r 1 at 224r %vreg27 = [256r,272r:1)[272r,304r:0) 0 at 272r 1 at 256r %vreg28 = [288r,320r:0) 0 at 288r %vreg29 = [512r,528r:0) 0 at 512r %vreg30 = [528r,544r:0) 0 at 528r %vreg31 = [896r,912r:0) 0 at 896r %vreg32 = [912r,944r:0) 0 at 912r %vreg34 = [928r,960r:0) 0 at 928r %vreg35 = [944r,960r:1)[960r,976r:0) 0 at 960r 1 at 944r %vreg36 = [976r,992r:1)[992r,1024r:0) 0 at 992r 1 at 976r %vreg37 = [1008r,1040r:0) 0 at 1008r %vreg38 = [1072r,1088r:0) 0 at 1072r %vreg39 = [608r,624r:0) 0 at 608r %vreg40 = [640r,656r:0) 0 at 640r %vreg41 = [672r,688r:0) 0 at 672r %vreg42 = [704r,720r:0) 0 at 704r %vreg43 = [736r,752r:0) 0 at 736r %vreg44 = [768r,784r:0) 0 at 768r %vreg45 = [800r,816r:0) 0 at 800r %vreg46 = [832r,848r:0) 0 at 832r %vreg47 = [400r,448B:0)[448B,464r:1)[1104r,1168B:2) 0 at 400r 1 at 448B-phi 2 at 1104r %vreg48 = [416r,448B:0)[448B,480r:1)[1120r,1168B:2) 0 at 416r 1 at 448B-phi 2 at 1120r %vreg49 = [432r,448B:0)[448B,496r:1)[1136r,1168B:2) 0 at 432r 1 at 448B-phi 2 at 1136r ********** MACHINEINSTRS ********** # Machine code for function main: Post SSA Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X 0BBB#0: derived from LLVM BB %0 Live Ins: %T1_X %T1_Y %T1_Z %T1_W 16B%vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17 32B%vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16 48B%vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15 64B%vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14 80B%vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18 96B%vreg19:sel_x<def,read-undef> = COPY %vreg14<kill>; R600_Reg128:%vreg19 R600_TReg32:%vreg14 112B%vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2 128B%vreg21:sel_x<def,read-undef> = COPY %vreg18<kill>; R600_Reg128:%vreg21 R600_Reg32:%vreg18 144B%vreg23<def> = COPY %vreg19<kill>; R600_Reg128:%vreg23,%vreg19 160B%vreg23:sel_y<def> = COPY %vreg15<kill>; R600_Reg128:%vreg23 R600_TReg32:%vreg15 176B%vreg24<def> = COPY %vreg21<kill>; R600_Reg128:%vreg24,%vreg21 192B%vreg24:sel_y<def> = COPY %vreg2; R600_Reg128:%vreg24 R600_Reg32:%vreg2 208B%vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25 224B%vreg26<def> = COPY %vreg23<kill>; R600_Reg128:%vreg26,%vreg23 240B%vreg26:sel_z<def> = COPY %vreg16<kill>; R600_Reg128:%vreg26 R600_TReg32:%vreg16 256B%vreg27<def> = COPY %vreg24<kill>; R600_Reg128:%vreg27,%vreg24 272B%vreg27:sel_z<def> = COPY %vreg25<kill>; R600_Reg128:%vreg27 R600_Reg32:%vreg25 288B%vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28 304B%vreg3<def> = COPY %vreg27<kill>; R600_Reg128:%vreg3,%vreg27 320B%vreg3:sel_w<def> = COPY %vreg28<kill>; R600_Reg128:%vreg3 R600_Reg32:%vreg28 336B%vreg1<def> = COPY %vreg26<kill>; R600_Reg128:%vreg1,%vreg26 352B%vreg1:sel_w<def> = COPY %vreg17<kill>; R600_Reg128:%vreg1 R600_TReg32:%vreg17 368B%vreg13<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg13 384B%vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0 400B%vreg47<def> = COPY %vreg2<kill>; R600_Reg32:%vreg47,%vreg2 416B%vreg48<def> = COPY %vreg3<kill>; R600_Reg128:%vreg48,%vreg3 432B%vreg49<def> = COPY %vreg13<kill>; R600_Reg32:%vreg49,%vreg13 Successors according to CFG: BB#1 448BBB#1: derived from LLVM BB %25 Predecessors according to CFG: BB#0 BB#3 464B%vreg5<def> = COPY %vreg47<kill>; R600_Reg32:%vreg5,%vreg47 480B%vreg6<def> = COPY %vreg48<kill>; R600_Reg128:%vreg6,%vreg48 496B%vreg7<def> = COPY %vreg49<kill>; R600_Reg32:%vreg7,%vreg49 512B%vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg7, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg7 528B%vreg30<def> = COPY %vreg29<kill>; R600_Reg32:%vreg30,%vreg29 544B%PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16; R600_Reg32:%vreg30 560BJUMP <BB#3>, pred:%PREDICATE_BIT 576BJUMP <BB#2>, pred:%noreg Successors according to CFG: BB#2(4) BB#3(124) 592BBB#2: derived from LLVM BB %31 Predecessors according to CFG: BB#1 608B%vreg39<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg6 624B%T2_X<def> = COPY %vreg39<kill>; R600_Reg32:%vreg39 640B%vreg40<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg6 656B%T2_Y<def> = COPY %vreg40<kill>; R600_Reg32:%vreg40 672B%vreg41<def> = COPY %vreg6:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg6 688B%T2_Z<def> = COPY %vreg41<kill>; R600_Reg32:%vreg41 704B%vreg42<def> = COPY %vreg6:sel_w<kill>; R600_Reg32:%vreg42 R600_Reg128:%vreg6 720B%T2_W<def> = COPY %vreg42<kill>; R600_Reg32:%vreg42 736B%vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1 752B%T1_X<def> = COPY %vreg43<kill>; R600_Reg32:%vreg43 768B%vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1 784B%T1_Y<def> = COPY %vreg44<kill>; R600_Reg32:%vreg44 800B%vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1 816B%T1_Z<def> = COPY %vreg45<kill>; R600_Reg32:%vreg45 832B%vreg46<def> = COPY %vreg1:sel_w<kill>; R600_Reg32:%vreg46 R600_Reg128:%vreg1 848B%T1_W<def> = COPY %vreg46<kill>; R600_Reg32:%vreg46 864BRETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>, %T1_X<imp-use>, %T2_W<imp-use,kill>, %T2_Z<imp-use,kill>, %T2_Y<imp-use,kill>, %T2_X<imp-use,kill> 880BBB#3: derived from LLVM BB %41 Predecessors according to CFG: BB#1 896B%vreg31<def> = COPY %vreg6:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg6 912B%vreg32:sel_x<def,read-undef> = COPY %vreg31<kill>; R600_Reg128:%vreg32 R600_Reg32:%vreg31 928B%vreg34<def> = COPY %vreg6:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg6 944B%vreg35<def> = COPY %vreg32<kill>; R600_Reg128:%vreg35,%vreg32 960B%vreg35:sel_y<def> = COPY %vreg34<kill>; R600_Reg128:%vreg35 R600_Reg32:%vreg34 976B%vreg36<def> = COPY %vreg35<kill>; R600_Reg128:%vreg36,%vreg35 992B%vreg36:sel_z<def> = COPY %vreg5<kill>; R600_Reg128:%vreg36 R600_Reg32:%vreg5 1008B%vreg37<def> = COPY %vreg6:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg6 1024B%vreg10<def> = COPY %vreg36<kill>; R600_Reg128:%vreg10,%vreg36 1040B%vreg10:sel_w<def> = COPY %vreg37<kill>; R600_Reg128:%vreg10 R600_Reg32:%vreg37 1056B%vreg9<def> = COPY %vreg6:sel_z<kill>; R600_Reg32:%vreg9 R600_Reg128:%vreg6 1072B%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38 1088B%vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg7<kill>, 0, 0, 0, %vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg11,%vreg7,%vreg38 1104B%vreg47<def> = COPY %vreg9<kill>; R600_Reg32:%vreg47,%vreg9 1120B%vreg48<def> = COPY %vreg10<kill>; R600_Reg128:%vreg48,%vreg10 1136B%vreg49<def> = COPY %vreg11<kill>; R600_Reg32:%vreg49,%vreg11 1152BJUMP <BB#1>, pred:%noreg Successors according to CFG: BB#1 # End machine code for function main. ********** SIMPLE REGISTER COALESCING ********** ********** Function: main ********** JOINING INTERVALS *********** : 464B%vreg5<def> = COPY %vreg47<kill>; R600_Reg32:%vreg5,%vreg47 Considering merging to R600_Reg32 with %vreg47 in %vreg5 RHS = %vreg5 [464r,592B:0)[880B,992r:0) 0 at 464r LHS = %vreg47 [400r,448B:0)[448B,464r:1)[1104r,1168B:2) 0 at 400r 1 at 448B-phi 2 at 1104r merge %vreg5:0 at 464r into %vreg47:1 at 448B --> @448B erased:464r%vreg5<def> = COPY %vreg47<kill>; R600_Reg32:%vreg5,%vreg47 AllocationOrder(R600_Reg32) = [ %T0_X %T0_Y %T0_Z %T0_W %T1_X %T1_Y %T1_Z %T1_W %T2_X %T2_Y %T2_Z %T2_W %T3_X %T3_Y %T3_Z %T3_W %T4_X %T4_Y %T4_Z %T4_W %T5_X %T5_Y %T5_Z %T5_W %T6_X %T6_Y %T6_Z %T6_W %T7_X %T7_Y %T7_Z %T7_W %T8_X %T8_Y %T8_Z %T8_W %T9_X %T9_Y %T9_Z %T9_W %T10_X %T10_Y %T10_Z %T10_W %T11_X %T11_Y %T11_Z %T11_W %T12_X %T12_Y %T12_Z %T12_W %T13_X %T13_Y %T13_Z %T13_W %T14_X %T14_Y %T14_Z %T14_W %T15_X %T15_Y %T15_Z %T15_W %T16_X %T16_Y %T16_Z %T16_W %T17_X %T17_Y %T17_Z %T17_W %T18_X %T18_Y %T18_Z %T18_W %T19_X %T19_Y %T19_Z %T19_W %T20_X %T20_Y %T20_Z %T20_W %T21_X %T21_Y %T21_Z %T21_W %T22_X %T22_Y %T22_Z %T22_W %T23_X %T23_Y %T23_Z %T23_W %T24_X %T24_Y %T24_Z %T24_W %T25_X %T25_Y %T25_Z %T25_W %T26_X %T26_Y %T26_Z %T26_W %T27_X %T27_Y %T27_Z %T27_W %T28_X %T28_Y %T28_Z %T28_W %T29_X %T29_Y %T29_Z %T29_W %T30_X %T30_Y %T30_Z %T30_W %T31_X %T31_Y %T31_Z %T31_W %T32_X %T32_Y %T32_Z %T32_W %T33_X %T33_Y %T33_Z %T33_W %T34_X %T34_Y %T34_Z %T34_W %T35_X %T35_Y %T35_Z %T35_W %T36_X %T36_Y %T36_Z %T36_W %T37_X %T37_Y %T37_Z %T37_W %T38_X %T38_Y %T38_Z %T38_W %T39_X %T39_Y %T39_Z %T39_W %T40_X %T40_Y %T40_Z %T40_W %T41_X %T41_Y %T41_Z %T41_W %T42_X %T42_Y %T42_Z %T42_W %T43_X %T43_Y %T43_Z %T43_W %T44_X %T44_Y %T44_Z %T44_W %T45_X %T45_Y %T45_Z %T45_W %T46_X %T46_Y %T46_Z %T46_W %T47_X %T47_Y %T47_Z %T47_W %T48_X %T48_Y %T48_Z %T48_W %T49_X %T49_Y %T49_Z %T49_W %T50_X %T50_Y %T50_Z %T50_W %T51_X %T51_Y %T51_Z %T51_W %T52_X %T52_Y %T52_Z %T52_W %T53_X %T53_Y %T53_Z %T53_W %T54_X %T54_Y %T54_Z %T54_W %T55_X %T55_Y %T55_Z %T55_W %T56_X %T56_Y %T56_Z %T56_W %T57_X %T57_Y %T57_Z %T57_W %T58_X %T58_Y %T58_Z %T58_W %T59_X %T59_Y %T59_Z %T59_W %T60_X %T60_Y %T60_Z %T60_W %T61_X %T61_Y %T61_Z %T61_W %T62_X %T62_Y %T62_Z %T62_W %T63_X %T63_Y %T63_Z %T63_W %T64_X %T64_Y %T64_Z %T64_W %T65_X %T65_Y %T65_Z %T65_W %T66_X %T66_Y %T66_Z %T66_W %T67_X %T67_Y %T67_Z %T67_W %T68_X %T68_Y %T68_Z %T68_W %T69_X %T69_Y %T69_Z %T69_W %T70_X %T70_Y %T70_Z %T70_W %T71_X %T71_Y %T71_Z %T71_W %T72_X %T72_Y %T72_Z %T72_W %T73_X %T73_Y %T73_Z %T73_W %T74_X %T74_Y %T74_Z %T74_W %T75_X %T75_Y %T75_Z %T75_W %T76_X %T76_Y %T76_Z %T76_W %T77_X %T77_Y %T77_Z %T77_W %T78_X %T78_Y %T78_Z %T78_W %T79_X %T79_Y %T79_Z %T79_W %T80_X %T80_Y %T80_Z %T80_W %T81_X %T81_Y %T81_Z %T81_W %T82_X %T82_Y %T82_Z %T82_W %T83_X %T83_Y %T83_Z %T83_W %T84_X %T84_Y %T84_Z %T84_W %T85_X %T85_Y %T85_Z %T85_W %T86_X %T86_Y %T86_Z %T86_W %T87_X %T87_Y %T87_Z %T87_W %T88_X %T88_Y %T88_Z %T88_W %T89_X %T89_Y %T89_Z %T89_W %T90_X %T90_Y %T90_Z %T90_W %T91_X %T91_Y %T91_Z %T91_W %T92_X %T92_Y %T92_Z %T92_W %T93_X %T93_Y %T93_Z %T93_W %T94_X %T94_Y %T94_Z %T94_W %T95_X %T95_Y %T95_Z %T95_W %T96_X %T96_Y %T96_Z %T96_W %T97_X %T97_Y %T97_Z %T97_W %T98_X %T98_Y %T98_Z %T98_W %T99_X %T99_Y %T99_Z %T99_W %T100_X %T100_Y %T100_Z %T100_W %T101_X %T101_Y %T101_Z %T101_W %T102_X %T102_Y %T102_Z %T102_W %T103_X %T103_Y %T103_Z %T103_W %T104_X %T104_Y %T104_Z %T104_W %T105_X %T105_Y %T105_Z %T105_W %T106_X %T106_Y %T106_Z %T106_W %T107_X %T107_Y %T107_Z %T107_W %T108_X %T108_Y %T108_Z %T108_W %T109_X %T109_Y %T109_Z %T109_W %T110_X %T110_Y %T110_Z %T110_W %T111_X %T111_Y %T111_Z %T111_W %T112_X %T112_Y %T112_Z %T112_W %T113_X %T113_Y %T113_Z %T113_W %T114_X %T114_Y %T114_Z %T114_W %T115_X %T115_Y %T115_Z %T115_W %T116_X %T116_Y %T116_Z %T116_W %T117_X %T117_Y %T117_Z %T117_W %T118_X %T118_Y %T118_Z %T118_W %T119_X %T119_Y %T119_Z %T119_W %T120_X %T120_Y %T120_Z %T120_W %T121_X %T121_Y %T121_Z %T121_W %T122_X %T122_Y %T122_Z %T122_W %T123_X %T123_Y %T123_Z %T123_W %T124_X %T124_Y %T124_Z %T124_W %T125_X %T125_Y %T125_Z %T125_W %T126_X %T126_Y %T126_Z %T126_W %T127_X %T127_Y %T127_Z %T127_W %ArrayBase448 %ArrayBase449 %ArrayBase450 %ArrayBase451 %ArrayBase452 %ArrayBase453 %ArrayBase454 %ArrayBase455 %ArrayBase456 %ArrayBase457 %ArrayBase458 %ArrayBase459 %ArrayBase460 %ArrayBase461 %ArrayBase462 %ArrayBase463 %ArrayBase464 ] updated: 992B%vreg36:sel_z<def> = COPY %vreg47; R600_Reg128:%vreg36 R600_Reg32:%vreg47 Joined. Result = %vreg47[400r,448B:0)[448B,592B:1)[880B,992r:1)[1104r,1168B:2) 0 at 400r 1 at 448B-phi 2 at 1104r 480B%vreg6<def> = COPY %vreg48<kill>; R600_Reg128:%vreg6,%vreg48 Considering merging to R600_Reg128 with %vreg48 in %vreg6 RHS = %vreg6 [480r,704r:0)[880B,1056r:0) 0 at 480r LHS = %vreg48 [416r,448B:0)[448B,480r:1)[1120r,1168B:2) 0 at 416r 1 at 448B-phi 2 at 1120r merge %vreg6:0 at 480r into %vreg48:1 at 448B --> @448B erased:480r%vreg6<def> = COPY %vreg48<kill>; R600_Reg128:%vreg6,%vreg48 AllocationOrder(R600_Reg128) = [ %T0_XYZW %T1_XYZW %T2_XYZW %T3_XYZW %T4_XYZW %T5_XYZW %T6_XYZW %T7_XYZW %T8_XYZW %T9_XYZW %T10_XYZW %T11_XYZW %T12_XYZW %T13_XYZW %T14_XYZW %T15_XYZW %T16_XYZW %T17_XYZW %T18_XYZW %T19_XYZW %T20_XYZW %T21_XYZW %T22_XYZW %T23_XYZW %T24_XYZW %T25_XYZW %T26_XYZW %T27_XYZW %T28_XYZW %T29_XYZW %T30_XYZW %T31_XYZW %T32_XYZW %T33_XYZW %T34_XYZW %T35_XYZW %T36_XYZW %T37_XYZW %T38_XYZW %T39_XYZW %T40_XYZW %T41_XYZW %T42_XYZW %T43_XYZW %T44_XYZW %T45_XYZW %T46_XYZW %T47_XYZW %T48_XYZW %T49_XYZW %T50_XYZW %T51_XYZW %T52_XYZW %T53_XYZW %T54_XYZW %T55_XYZW %T56_XYZW %T57_XYZW %T58_XYZW %T59_XYZW %T60_XYZW %T61_XYZW %T62_XYZW %T63_XYZW %T64_XYZW %T65_XYZW %T66_XYZW %T67_XYZW %T68_XYZW %T69_XYZW %T70_XYZW %T71_XYZW %T72_XYZW %T73_XYZW %T74_XYZW %T75_XYZW %T76_XYZW %T77_XYZW %T78_XYZW %T79_XYZW %T80_XYZW %T81_XYZW %T82_XYZW %T83_XYZW %T84_XYZW %T85_XYZW %T86_XYZW %T87_XYZW %T88_XYZW %T89_XYZW %T90_XYZW %T91_XYZW %T92_XYZW %T93_XYZW %T94_XYZW %T95_XYZW %T96_XYZW %T97_XYZW %T98_XYZW %T99_XYZW %T100_XYZW %T101_XYZW %T102_XYZW %T103_XYZW %T104_XYZW %T105_XYZW %T106_XYZW %T107_XYZW %T108_XYZW %T109_XYZW %T110_XYZW %T111_XYZW %T112_XYZW %T113_XYZW %T114_XYZW %T115_XYZW %T116_XYZW %T117_XYZW %T118_XYZW %T119_XYZW %T120_XYZW %T121_XYZW %T122_XYZW %T123_XYZW %T124_XYZW %T125_XYZW %T126_XYZW %T127_XYZW ] updated: 896B%vreg31<def> = COPY %vreg48:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg48 updated: 928B%vreg34<def> = COPY %vreg48:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg48 updated: 1008B%vreg37<def> = COPY %vreg48:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg48 updated: 1056B%vreg9<def> = COPY %vreg48:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg48 updated: 608B%vreg39<def> = COPY %vreg48:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg48 updated: 640B%vreg40<def> = COPY %vreg48:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg48 updated: 672B%vreg41<def> = COPY %vreg48:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg48 updated: 704B%vreg42<def> = COPY %vreg48:sel_w; R600_Reg32:%vreg42 R600_Reg128:%vreg48 Joined. Result = %vreg48[416r,448B:0)[448B,704r:1)[880B,1056r:1)[1120r,1168B:2) 0 at 416r 1 at 448B-phi 2 at 1120r 496B%vreg7<def> = COPY %vreg49<kill>; R600_Reg32:%vreg7,%vreg49 Considering merging to R600_Reg32 with %vreg49 in %vreg7 RHS = %vreg7 [496r,592B:0)[880B,1088r:0) 0 at 496r LHS = %vreg49 [432r,448B:0)[448B,496r:1)[1136r,1168B:2) 0 at 432r 1 at 448B-phi 2 at 1136r merge %vreg7:0 at 496r into %vreg49:1 at 448B --> @448B erased:496r%vreg7<def> = COPY %vreg49<kill>; R600_Reg32:%vreg7,%vreg49 updated: 512B%vreg29<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg49, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg29,%vreg0,%vreg49 updated: 1088B%vreg11<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg49, 0, 0, 0, %vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg11,%vreg49,%vreg38 Joined. Result = %vreg49[432r,448B:0)[448B,592B:1)[880B,1088r:1)[1136r,1168B:2) 0 at 432r 1 at 448B-phi 2 at 1136r 528B%vreg30<def> = COPY %vreg29<kill>; R600_Reg32:%vreg30,%vreg29 Considering merging to R600_Reg32 with %vreg29 in %vreg30 RHS = %vreg29 [512r,528r:0) 0 at 512r LHS = %vreg30 [528r,544r:0) 0 at 528r merge %vreg30:0 at 528r into %vreg29:0 at 512r --> @512r erased:528r%vreg30<def> = COPY %vreg29<kill>; R600_Reg32:%vreg30,%vreg29 updated: 512B%vreg30<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %vreg0, 0, 0, 0, %vreg49, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg30,%vreg0,%vreg49 Joined. Result = %vreg30[512r,544r:0) 0 at 512r : 896B%vreg31<def> = COPY %vreg48:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg48 Considering merging to R600_Reg128 with %vreg31 in %vreg48:sel_x RHS = %vreg31 [896r,912r:0) 0 at 896r LHS = %vreg48 [416r,448B:0)[448B,704r:1)[880B,1056r:1)[1120r,1168B:2) 0 at 416r 1 at 448B-phi 2 at 1120r merge %vreg31:0 at 896r into %vreg48:1 at 448B --> @448B erased:896r%vreg31<def> = COPY %vreg48:sel_x; R600_Reg32:%vreg31 R600_Reg128:%vreg48 updated: 912B%vreg32:sel_x<def,read-undef> = COPY %vreg48:sel_x; R600_Reg128:%vreg32,%vreg48 Joined. Result = %vreg48[416r,448B:0)[448B,704r:1)[880B,1056r:1)[1120r,1168B:2) 0 at 416r 1 at 448B-phi 2 at 1120r 912B%vreg32:sel_x<def,read-undef> = COPY %vreg48:sel_x; R600_Reg128:%vreg32,%vreg48 Considering merging to R600_Reg128 with %vreg48 in %vreg32 RHS = %vreg48 [416r,448B:0)[448B,704r:1)[880B,1056r:1)[1120r,1168B:2) 0 at 416r 1 at 448B-phi 2 at 1120r LHS = %vreg32 [912r,944r:0) 0 at 912r merge %vreg32:0 at 912r into %vreg48:1 at 448B --> @448B erased:912r%vreg32:sel_x<def,read-undef> = COPY %vreg48:sel_x; R600_Reg128:%vreg32,%vreg48 updated: 416B%vreg32<def> = COPY %vreg3<kill>; R600_Reg128:%vreg32,%vreg3 updated: 1120B%vreg32<def> = COPY %vreg10<kill>; R600_Reg128:%vreg32,%vreg10 updated: 928B%vreg34<def> = COPY %vreg32:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg32 updated: 1008B%vreg37<def> = COPY %vreg32:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg32 updated: 1056B%vreg9<def> = COPY %vreg32:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg32 updated: 608B%vreg39<def> = COPY %vreg32:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg32 updated: 640B%vreg40<def> = COPY %vreg32:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg32 updated: 672B%vreg41<def> = COPY %vreg32:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg32 updated: 704B%vreg42<def> = COPY %vreg32:sel_w; R600_Reg32:%vreg42 R600_Reg128:%vreg32 Joined. Result = %vreg32[416r,448B:1)[448B,704r:0)[880B,1056r:0)[1120r,1168B:2) 0 at 448B-phi 1 at 416r 2 at 1120r 928B%vreg34<def> = COPY %vreg32:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg32 Considering merging to R600_Reg128 with %vreg34 in %vreg32:sel_y RHS = %vreg34 [928r,960r:0) 0 at 928r LHS = %vreg32 [416r,448B:1)[448B,704r:0)[880B,1056r:0)[1120r,1168B:2) 0 at 448B-phi 1 at 416r 2 at 1120r merge %vreg34:0 at 928r into %vreg32:0 at 448B --> @448B erased:928r%vreg34<def> = COPY %vreg32:sel_y; R600_Reg32:%vreg34 R600_Reg128:%vreg32 updated: 960B%vreg35:sel_y<def> = COPY %vreg32:sel_y; R600_Reg128:%vreg35,%vreg32 Joined. Result = %vreg32[416r,448B:1)[448B,704r:0)[880B,1056r:0)[1120r,1168B:2) 0 at 448B-phi 1 at 416r 2 at 1120r 944B%vreg35<def> = COPY %vreg32; R600_Reg128:%vreg35,%vreg32 Considering merging to R600_Reg128 with %vreg32 in %vreg35 RHS = %vreg35 [944r,960r:1)[960r,976r:0) 0 at 960r 1 at 944r LHS = %vreg32 [416r,448B:1)[448B,704r:0)[880B,1056r:0)[1120r,1168B:2) 0 at 448B-phi 1 at 416r 2 at 1120r merge %vreg35:1 at 944r into %vreg32:0 at 448B --> @448B merge %vreg35:0 at 960r into %vreg32:0 at 448B --> @448B erased:960r%vreg35:sel_y<def> = COPY %vreg32:sel_y; R600_Reg128:%vreg35,%vreg32 erased:944r%vreg35<def> = COPY %vreg32; R600_Reg128:%vreg35,%vreg32 updated: 976B%vreg36<def> = COPY %vreg32; R600_Reg128:%vreg36,%vreg32 Joined. Result = %vreg32[416r,448B:1)[448B,704r:0)[880B,1056r:0)[1120r,1168B:2) 0 at 448B-phi 1 at 416r 2 at 1120r 976B%vreg36<def> = COPY %vreg32; R600_Reg128:%vreg36,%vreg32 Considering merging to R600_Reg128 with %vreg32 in %vreg36 RHS = %vreg36 [976r,992r:1)[992r,1024r:0) 0 at 992r 1 at 976r LHS = %vreg32 [416r,448B:1)[448B,704r:0)[880B,1056r:0)[1120r,1168B:2) 0 at 448B-phi 1 at 416r 2 at 1120r merge %vreg36:1 at 976r into %vreg32:0 at 448B --> @448B conflict at %vreg36:0 at 992r taints local %vreg32:0 at 880B to 1056r tainted lanes used by: %vreg9<def> = COPY %vreg32:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg32 Interference! 992B%vreg36:sel_z<def> = COPY %vreg47; R600_Reg128:%vreg36 R600_Reg32:%vreg47 Considering merging to R600_Reg128 with %vreg47 in %vreg36:sel_z RHS = %vreg47 [400r,448B:0)[448B,592B:1)[880B,992r:1)[1104r,1168B:2) 0 at 400r 1 at 448B-phi 2 at 1104r LHS = %vreg36 [976r,992r:1)[992r,1024r:0) 0 at 992r 1 at 976r merge %vreg36:0 at 992r into %vreg47:1 at 448B --> @448B interference at %vreg36:1 at 976r Interference! 1008B%vreg37<def> = COPY %vreg32:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg32 Considering merging to R600_Reg128 with %vreg37 in %vreg32:sel_w RHS = %vreg37 [1008r,1040r:0) 0 at 1008r LHS = %vreg32 [416r,448B:1)[448B,704r:0)[880B,1056r:0)[1120r,1168B:2) 0 at 448B-phi 1 at 416r 2 at 1120r merge %vreg37:0 at 1008r into %vreg32:0 at 448B --> @448B erased:1008r%vreg37<def> = COPY %vreg32:sel_w; R600_Reg32:%vreg37 R600_Reg128:%vreg32 updated: 1040B%vreg10:sel_w<def> = COPY %vreg32:sel_w; R600_Reg128:%vreg10,%vreg32 Joined. Result = %vreg32[416r,448B:1)[448B,704r:0)[880B,1056r:0)[1120r,1168B:2) 0 at 448B-phi 1 at 416r 2 at 1120r 1024B%vreg10<def> = COPY %vreg36<kill>; R600_Reg128:%vreg10,%vreg36 Considering merging to R600_Reg128 with %vreg36 in %vreg10 RHS = %vreg36 [976r,992r:1)[992r,1024r:0) 0 at 992r 1 at 976r LHS = %vreg10 [1024r,1040r:1)[1040r,1120r:0) 0 at 1040r 1 at 1024r merge %vreg10:1 at 1024r into %vreg36:0 at 992r --> @992r erased:1024r%vreg10<def> = COPY %vreg36<kill>; R600_Reg128:%vreg10,%vreg36 updated: 976B%vreg10<def> = COPY %vreg32; R600_Reg128:%vreg10,%vreg32 updated: 992B%vreg10:sel_z<def> = COPY %vreg47; R600_Reg128:%vreg10 R600_Reg32:%vreg47 Joined. Result = %vreg10[976r,992r:0)[992r,1040r:1)[1040r,1120r:2) 0 at 976r 1 at 992r 2 at 1040r 1040B%vreg10:sel_w<def> = COPY %vreg32:sel_w; R600_Reg128:%vreg10,%vreg32 Considering merging to R600_Reg128 with %vreg32 in %vreg10 RHS = %vreg32 [416r,448B:1)[448B,704r:0)[880B,1056r:0)[1120r,1168B:2) 0 at 448B-phi 1 at 416r 2 at 1120r LHS = %vreg10 [976r,992r:0)[992r,1040r:1)[1040r,1120r:2) 0 at 976r 1 at 992r 2 at 1040r merge %vreg10:0 at 976r into %vreg32:0 at 448B --> @448B merge %vreg10:2 at 1040r into %vreg32:0 at 448B --> @448B merge %vreg32:2 at 1120r into %vreg10:2 at 1040r --> @448B conflict at %vreg10:1 at 992r taints local %vreg32:0 at 880B to 1056r tainted lanes used by: %vreg9<def> = COPY %vreg32:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg32 Interference! 1056B%vreg9<def> = COPY %vreg32:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg32 Considering merging to R600_Reg128 with %vreg9 in %vreg32:sel_z RHS = %vreg9 [1056r,1104r:0) 0 at 1056r LHS = %vreg32 [416r,448B:1)[448B,704r:0)[880B,1056r:0)[1120r,1168B:2) 0 at 448B-phi 1 at 416r 2 at 1120r merge %vreg9:0 at 1056r into %vreg32:0 at 448B --> @448B erased:1056r%vreg9<def> = COPY %vreg32:sel_z; R600_Reg32:%vreg9 R600_Reg128:%vreg32 updated: 1104B%vreg47<def> = COPY %vreg32:sel_z; R600_Reg32:%vreg47 R600_Reg128:%vreg32 Joined. Result = %vreg32[416r,448B:1)[448B,704r:0)[880B,1104r:0)[1120r,1168B:2) 0 at 448B-phi 1 at 416r 2 at 1120r 1104B%vreg47<def> = COPY %vreg32:sel_z; R600_Reg32:%vreg47 R600_Reg128:%vreg32 Considering merging to R600_Reg128 with %vreg47 in %vreg32:sel_z RHS = %vreg47 [400r,448B:0)[448B,592B:1)[880B,992r:1)[1104r,1168B:2) 0 at 400r 1 at 448B-phi 2 at 1104r LHS = %vreg32 [416r,448B:1)[448B,704r:0)[880B,1104r:0)[1120r,1168B:2) 0 at 448B-phi 1 at 416r 2 at 1120r interference at %vreg32:1 at 416r Interference! 1120B%vreg32<def> = COPY %vreg10; R600_Reg128:%vreg32,%vreg10 Considering merging to R600_Reg128 with %vreg10 in %vreg32 RHS = %vreg10 [976r,992r:0)[992r,1040r:1)[1040r,1120r:2) 0 at 976r 1 at 992r 2 at 1040r LHS = %vreg32 [416r,448B:1)[448B,704r:0)[880B,1104r:0)[1120r,1168B:2) 0 at 448B-phi 1 at 416r 2 at 1120r merge %vreg10:0 at 976r into %vreg32:0 at 448B --> @448B merge %vreg10:2 at 1040r into %vreg32:0 at 448B --> @448B merge %vreg32:2 at 1120r into %vreg10:2 at 1040r --> @448B conflict at %vreg10:1 at 992r taints local %vreg32:0 at 880B to 1104r tainted lanes used by: %vreg47<def> = COPY %vreg32:sel_z; R600_Reg32:%vreg47 R600_Reg128:%vreg32 Extending: %vreg32 result = [416r,448B:1)[448B,704r:0)[880B,1168B:0) 0 at 448B-phi 1 at 416r Shrink: [976r,992r:0)[992r,1040r:1)[1040r,1120r:2) 0 at 976r 1 at 992r 2 at 1040r Shrunk: [976r,992r:0)[992r,1040r:1)[1040r,1040d:2) 0 at 976r 1 at 992r 2 at 1040r Trivial! 1136B%vreg49<def> = COPY %vreg11<kill>; R600_Reg32:%vreg49,%vreg11 Considering merging to R600_Reg32 with %vreg11 in %vreg49 RHS = %vreg11 [1088r,1136r:0) 0 at 1088r LHS = %vreg49 [432r,448B:0)[448B,592B:1)[880B,1088r:1)[1136r,1168B:2) 0 at 432r 1 at 448B-phi 2 at 1136r merge %vreg49:2 at 1136r into %vreg11:0 at 1088r --> @1088r erased:1136r%vreg49<def> = COPY %vreg11<kill>; R600_Reg32:%vreg49,%vreg11 updated: 1088B%vreg49<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg49, 0, 0, 0, %vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg49,%vreg38 Joined. Result = %vreg49[432r,448B:0)[448B,592B:1)[880B,1088r:1)[1088r,1168B:2) 0 at 432r 1 at 448B-phi 2 at 1088r : 16B%vreg17<def> = COPY %T1_W; R600_TReg32:%vreg17 Considering merging %vreg17 with %T1_W Can only merge into reserved registers. 32B%vreg16<def> = COPY %T1_Z; R600_TReg32:%vreg16 Considering merging %vreg16 with %T1_Z Can only merge into reserved registers. 48B%vreg15<def> = COPY %T1_Y; R600_TReg32:%vreg15 Considering merging %vreg15 with %T1_Y Can only merge into reserved registers. 64B%vreg14<def> = COPY %T1_X; R600_TReg32:%vreg14 Considering merging %vreg14 with %T1_X Can only merge into reserved registers. 80B%vreg18<def> = COPY %C1_X; R600_Reg32:%vreg18 Considering merging %vreg18 with %C1_X RHS = %vreg18 [80r,128r:0) 0 at 80r updated: 128B%vreg21:sel_x<def,read-undef> = COPY %C1_X; R600_Reg128:%vreg21 Joined. Result = %C1_X 96B%vreg19:sel_x<def,read-undef> = COPY %vreg14<kill>; R600_Reg128:%vreg19 R600_TReg32:%vreg14 Considering merging to R600_Reg128 with %vreg14 in %vreg19:sel_x RHS = %vreg14 [64r,96r:0) 0 at 64r LHS = %vreg19 [96r,144r:0) 0 at 96r merge %vreg19:0 at 96r into %vreg14:0 at 64r --> @64r erased:96r%vreg19:sel_x<def,read-undef> = COPY %vreg14<kill>; R600_Reg128:%vreg19 R600_TReg32:%vreg14 updated: 64B%vreg19:sel_x<def,read-undef> = COPY %T1_X; R600_Reg128:%vreg19 Joined. Result = %vreg19[64r,144r:0) 0 at 64r 112B%vreg2<def> = COPY %C1_Y; R600_Reg32:%vreg2 Considering merging %vreg2 with %C1_Y RHS = %vreg2 [112r,400r:0) 0 at 112r updated: 400B%vreg47<def> = COPY %C1_Y; R600_Reg32:%vreg47 updated: 192B%vreg24:sel_y<def> = COPY %C1_Y; R600_Reg128:%vreg24 Joined. Result = %C1_Y 128B%vreg21:sel_x<def,read-undef> = COPY %C1_X; R600_Reg128:%vreg21 Not coalescable. 144B%vreg23<def> = COPY %vreg19; R600_Reg128:%vreg23,%vreg19 Considering merging to R600_Reg128 with %vreg19 in %vreg23 RHS = %vreg19 [64r,144r:0) 0 at 64r LHS = %vreg23 [144r,160r:1)[160r,224r:0) 0 at 160r 1 at 144r merge %vreg23:1 at 144r into %vreg19:0 at 64r --> @64r erased:144r%vreg23<def> = COPY %vreg19; R600_Reg128:%vreg23,%vreg19 updated: 64B%vreg23:sel_x<def,read-undef> = COPY %T1_X; R600_Reg128:%vreg23 Joined. Result = %vreg23[64r,160r:0)[160r,224r:1) 0 at 64r 1 at 160r 160B%vreg23:sel_y<def> = COPY %vreg15<kill>; R600_Reg128:%vreg23 R600_TReg32:%vreg15 Considering merging to R600_Reg128 with %vreg15 in %vreg23:sel_y RHS = %vreg15 [48r,160r:0) 0 at 48r LHS = %vreg23 [64r,160r:0)[160r,224r:1) 0 at 64r 1 at 160r merge %vreg23:1 at 160r into %vreg15:0 at 48r --> @48r pruned %vreg15 at 64r: [48r,64r:0) 0 at 48r pruned all of %vreg23 at 160r: [64r,160r:0) 0 at 64r 1 at 160r erased:160r%vreg23:sel_y<def> = COPY %vreg15<kill>; R600_Reg128:%vreg23 R600_TReg32:%vreg15 restoring liveness to 3 points: [48r,64r:0)[64r,160r:1) 0 at 48r 1 at 64r updated: 48B%vreg23:sel_y<def,read-undef> = COPY %T1_Y; R600_Reg128:%vreg23 Joined. Result = %vreg23[48r,64r:0)[64r,224r:1) 0 at 48r 1 at 64r 176B%vreg24<def> = COPY %vreg21<kill>; R600_Reg128:%vreg24,%vreg21 Considering merging to R600_Reg128 with %vreg21 in %vreg24 RHS = %vreg21 [128r,176r:0) 0 at 128r LHS = %vreg24 [176r,192r:1)[192r,256r:0) 0 at 192r 1 at 176r merge %vreg24:1 at 176r into %vreg21:0 at 128r --> @128r erased:176r%vreg24<def> = COPY %vreg21<kill>; R600_Reg128:%vreg24,%vreg21 updated: 128B%vreg24:sel_x<def,read-undef> = COPY %C1_X; R600_Reg128:%vreg24 Joined. Result = %vreg24[128r,192r:0)[192r,256r:1) 0 at 128r 1 at 192r 192B%vreg24:sel_y<def> = COPY %C1_Y; R600_Reg128:%vreg24 Not coalescable. 208B%vreg25<def> = COPY %C1_Z; R600_Reg32:%vreg25 Considering merging %vreg25 with %C1_Z RHS = %vreg25 [208r,272r:0) 0 at 208r updated: 272B%vreg27:sel_z<def> = COPY %C1_Z; R600_Reg128:%vreg27 Joined. Result = %C1_Z 224B%vreg26<def> = COPY %vreg23; R600_Reg128:%vreg26,%vreg23 Considering merging to R600_Reg128 with %vreg23 in %vreg26 RHS = %vreg23 [48r,64r:0)[64r,224r:1) 0 at 48r 1 at 64r LHS = %vreg26 [224r,240r:1)[240r,336r:0) 0 at 240r 1 at 224r merge %vreg26:1 at 224r into %vreg23:1 at 64r --> @64r erased:224r%vreg26<def> = COPY %vreg23; R600_Reg128:%vreg26,%vreg23 updated: 48B%vreg26:sel_y<def,read-undef> = COPY %T1_Y; R600_Reg128:%vreg26 updated: 64B%vreg26:sel_x<def> = COPY %T1_X; R600_Reg128:%vreg26 Joined. Result = %vreg26[48r,64r:0)[64r,240r:1)[240r,336r:2) 0 at 48r 1 at 64r 2 at 240r 240B%vreg26:sel_z<def> = COPY %vreg16<kill>; R600_Reg128:%vreg26 R600_TReg32:%vreg16 Considering merging to R600_Reg128 with %vreg16 in %vreg26:sel_z RHS = %vreg16 [32r,240r:0) 0 at 32r LHS = %vreg26 [48r,64r:0)[64r,240r:1)[240r,336r:2) 0 at 48r 1 at 64r 2 at 240r merge %vreg26:2 at 240r into %vreg16:0 at 32r --> @32r pruned %vreg16 at 48r: [32r,48r:0) 0 at 32r pruned %vreg16 at 64r: [32r,48r:0) 0 at 32r pruned all of %vreg26 at 240r: [48r,64r:0)[64r,240r:1) 0 at 48r 1 at 64r 2 at 240r erased:240r%vreg26:sel_z<def> = COPY %vreg16<kill>; R600_Reg128:%vreg26 R600_TReg32:%vreg16 restoring liveness to 4 points: [32r,48r:0)[48r,64r:1)[64r,240r:2) 0 at 32r 1 at 48r 2 at 64r updated: 32B%vreg26:sel_z<def,read-undef> = COPY %T1_Z; R600_Reg128:%vreg26 Joined. Result = %vreg26[32r,48r:0)[48r,64r:1)[64r,336r:2) 0 at 32r 1 at 48r 2 at 64r 256B%vreg27<def> = COPY %vreg24; R600_Reg128:%vreg27,%vreg24 Considering merging to R600_Reg128 with %vreg24 in %vreg27 RHS = %vreg24 [128r,192r:0)[192r,256r:1) 0 at 128r 1 at 192r LHS = %vreg27 [256r,272r:1)[272r,304r:0) 0 at 272r 1 at 256r merge %vreg27:1 at 256r into %vreg24:1 at 192r --> @192r erased:256r%vreg27<def> = COPY %vreg24; R600_Reg128:%vreg27,%vreg24 updated: 128B%vreg27:sel_x<def,read-undef> = COPY %C1_X; R600_Reg128:%vreg27 updated: 192B%vreg27:sel_y<def> = COPY %C1_Y; R600_Reg128:%vreg27 Joined. Result = %vreg27[128r,192r:0)[192r,272r:1)[272r,304r:2) 0 at 128r 1 at 192r 2 at 272r 272B%vreg27:sel_z<def> = COPY %C1_Z; R600_Reg128:%vreg27 Not coalescable. 288B%vreg28<def> = COPY %C1_W; R600_Reg32:%vreg28 Considering merging %vreg28 with %C1_W RHS = %vreg28 [288r,320r:0) 0 at 288r updated: 320B%vreg3:sel_w<def> = COPY %C1_W; R600_Reg128:%vreg3 Joined. Result = %C1_W 304B%vreg3<def> = COPY %vreg27; R600_Reg128:%vreg3,%vreg27 Considering merging to R600_Reg128 with %vreg27 in %vreg3 RHS = %vreg3 [304r,320r:1)[320r,416r:0) 0 at 320r 1 at 304r LHS = %vreg27 [128r,192r:0)[192r,272r:1)[272r,304r:2) 0 at 128r 1 at 192r 2 at 272r merge %vreg3:1 at 304r into %vreg27:2 at 272r --> @272r erased:304r%vreg3<def> = COPY %vreg27; R600_Reg128:%vreg3,%vreg27 updated: 320B%vreg27:sel_w<def> = COPY %C1_W; R600_Reg128:%vreg27 updated: 416B%vreg32<def> = COPY %vreg27; R600_Reg128:%vreg32,%vreg27 Joined. Result = %vreg27[128r,192r:0)[192r,272r:1)[272r,320r:2)[320r,416r:3) 0 at 128r 1 at 192r 2 at 272r 3 at 320r 320B%vreg27:sel_w<def> = COPY %C1_W; R600_Reg128:%vreg27 Not coalescable. 336B%vreg1<def> = COPY %vreg26; R600_Reg128:%vreg1,%vreg26 Considering merging to R600_Reg128 with %vreg26 in %vreg1 RHS = %vreg26 [32r,48r:0)[48r,64r:1)[64r,336r:2) 0 at 32r 1 at 48r 2 at 64r LHS = %vreg1 [336r,352r:1)[352r,832r:0)[880B,1168B:0) 0 at 352r 1 at 336r merge %vreg1:1 at 336r into %vreg26:2 at 64r --> @64r erased:336r%vreg1<def> = COPY %vreg26; R600_Reg128:%vreg1,%vreg26 updated: 32B%vreg1:sel_z<def,read-undef> = COPY %T1_Z; R600_Reg128:%vreg1 updated: 64B%vreg1:sel_x<def> = COPY %T1_X; R600_Reg128:%vreg1 updated: 48B%vreg1:sel_y<def> = COPY %T1_Y; R600_Reg128:%vreg1 Joined. Result = %vreg1[32r,48r:0)[48r,64r:1)[64r,352r:2)[352r,832r:3)[880B,1168B:3) 0 at 32r 1 at 48r 2 at 64r 3 at 352r 352B%vreg1:sel_w<def> = COPY %vreg17<kill>; R600_Reg128:%vreg1 R600_TReg32:%vreg17 Considering merging to R600_Reg128 with %vreg17 in %vreg1:sel_w RHS = %vreg17 [16r,352r:0) 0 at 16r LHS = %vreg1 [32r,48r:0)[48r,64r:1)[64r,352r:2)[352r,832r:3)[880B,1168B:3) 0 at 32r 1 at 48r 2 at 64r 3 at 352r merge %vreg1:3 at 352r into %vreg17:0 at 16r --> @16r pruned %vreg17 at 32r: [16r,32r:0) 0 at 16r pruned %vreg17 at 48r: [16r,32r:0) 0 at 16r pruned %vreg17 at 64r: [16r,32r:0) 0 at 16r pruned all of %vreg1 at 352r: [32r,48r:0)[48r,64r:1)[64r,352r:2) 0 at 32r 1 at 48r 2 at 64r 3 at 352r erased:352r%vreg1:sel_w<def> = COPY %vreg17<kill>; R600_Reg128:%vreg1 R600_TReg32:%vreg17 restoring liveness to 8 points: [16r,32r:0)[32r,48r:1)[48r,64r:2)[64r,352r:3) 0 at 16r 1 at 32r 2 at 48r 3 at 64r updated: 16B%vreg1:sel_w<def,read-undef> = COPY %T1_W; R600_Reg128:%vreg1 Joined. Result = %vreg1[16r,32r:0)[32r,48r:1)[48r,64r:2)[64r,832r:3)[880B,1168B:3) 0 at 16r 1 at 32r 2 at 48r 3 at 64r 384B%vreg0<def> = COPY %C0_X; R600_Reg32:%vreg0 Considering merging %vreg0 with %C0_X RHS = %vreg0 [384r,592B:0)[880B,1168B:0) 0 at 384r updated: 512B%vreg30<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %vreg49, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg30,%vreg49 Joined. Result = %C0_X 400B%vreg47<def> = COPY %C1_Y; R600_Reg32:%vreg47 Considering merging %vreg47 with %C1_Y Cannot join defs into reserved register. 416B%vreg32<def> = COPY %vreg27; R600_Reg128:%vreg32,%vreg27 Considering merging to R600_Reg128 with %vreg27 in %vreg32 RHS = %vreg32 [416r,448B:1)[448B,704r:0)[880B,1168B:0) 0 at 448B-phi 1 at 416r LHS = %vreg27 [128r,192r:0)[192r,272r:1)[272r,320r:2)[320r,416r:3) 0 at 128r 1 at 192r 2 at 272r 3 at 320r merge %vreg32:1 at 416r into %vreg27:3 at 320r --> @320r erased:416r%vreg32<def> = COPY %vreg27; R600_Reg128:%vreg32,%vreg27 updated: 608B%vreg39<def> = COPY %vreg27:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg27 updated: 640B%vreg40<def> = COPY %vreg27:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg27 updated: 672B%vreg41<def> = COPY %vreg27:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg27 updated: 704B%vreg42<def> = COPY %vreg27:sel_w; R600_Reg32:%vreg42 R600_Reg128:%vreg27 updated: 976B%vreg10<def> = COPY %vreg27; R600_Reg128:%vreg10,%vreg27 updated: 1040B%vreg10:sel_w<def,dead> = COPY %vreg27:sel_w; R600_Reg128:%vreg10,%vreg27 updated: 1104B%vreg47<def> = COPY %vreg27:sel_z; R600_Reg32:%vreg47 R600_Reg128:%vreg27 Joined. Result = %vreg27[128r,192r:0)[192r,272r:1)[272r,320r:2)[320r,448B:3)[448B,704r:4)[880B,1168B:4) 0 at 128r 1 at 192r 2 at 272r 3 at 320r 4 at 448B-phi 432B%vreg49<def> = COPY %vreg13<kill>; R600_Reg32:%vreg49,%vreg13 Considering merging to R600_Reg32 with %vreg13 in %vreg49 RHS = %vreg13 [368r,432r:0) 0 at 368r LHS = %vreg49 [432r,448B:0)[448B,592B:1)[880B,1088r:1)[1088r,1168B:2) 0 at 432r 1 at 448B-phi 2 at 1088r merge %vreg49:0 at 432r into %vreg13:0 at 368r --> @368r erased:432r%vreg49<def> = COPY %vreg13<kill>; R600_Reg32:%vreg49,%vreg13 updated: 368B%vreg49<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg49 Joined. Result = %vreg49[368r,448B:0)[448B,592B:1)[880B,1088r:1)[1088r,1168B:2) 0 at 368r 1 at 448B-phi 2 at 1088r : 608B%vreg39<def> = COPY %vreg27:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg27 Considering merging to R600_Reg128 with %vreg39 in %vreg27:sel_x RHS = %vreg39 [608r,624r:0) 0 at 608r LHS = %vreg27 [128r,192r:0)[192r,272r:1)[272r,320r:2)[320r,448B:3)[448B,704r:4)[880B,1168B:4) 0 at 128r 1 at 192r 2 at 272r 3 at 320r 4 at 448B-phi merge %vreg39:0 at 608r into %vreg27:4 at 448B --> @448B erased:608r%vreg39<def> = COPY %vreg27:sel_x; R600_Reg32:%vreg39 R600_Reg128:%vreg27 updated: 624B%T2_X<def> = COPY %vreg27:sel_x; R600_Reg128:%vreg27 Joined. Result = %vreg27[128r,192r:0)[192r,272r:1)[272r,320r:2)[320r,448B:3)[448B,704r:4)[880B,1168B:4) 0 at 128r 1 at 192r 2 at 272r 3 at 320r 4 at 448B-phi 624B%T2_X<def> = COPY %vreg27:sel_x; R600_Reg128:%vreg27 Considering merging %vreg27 with %T2_XYZW Can only merge into reserved registers. 640B%vreg40<def> = COPY %vreg27:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg27 Considering merging to R600_Reg128 with %vreg40 in %vreg27:sel_y RHS = %vreg40 [640r,656r:0) 0 at 640r LHS = %vreg27 [128r,192r:0)[192r,272r:1)[272r,320r:2)[320r,448B:3)[448B,704r:4)[880B,1168B:4) 0 at 128r 1 at 192r 2 at 272r 3 at 320r 4 at 448B-phi merge %vreg40:0 at 640r into %vreg27:4 at 448B --> @448B erased:640r%vreg40<def> = COPY %vreg27:sel_y; R600_Reg32:%vreg40 R600_Reg128:%vreg27 updated: 656B%T2_Y<def> = COPY %vreg27:sel_y; R600_Reg128:%vreg27 Joined. Result = %vreg27[128r,192r:0)[192r,272r:1)[272r,320r:2)[320r,448B:3)[448B,704r:4)[880B,1168B:4) 0 at 128r 1 at 192r 2 at 272r 3 at 320r 4 at 448B-phi 656B%T2_Y<def> = COPY %vreg27:sel_y; R600_Reg128:%vreg27 Considering merging %vreg27 with %T2_XYZW Can only merge into reserved registers. 672B%vreg41<def> = COPY %vreg27:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg27 Considering merging to R600_Reg128 with %vreg41 in %vreg27:sel_z RHS = %vreg41 [672r,688r:0) 0 at 672r LHS = %vreg27 [128r,192r:0)[192r,272r:1)[272r,320r:2)[320r,448B:3)[448B,704r:4)[880B,1168B:4) 0 at 128r 1 at 192r 2 at 272r 3 at 320r 4 at 448B-phi merge %vreg41:0 at 672r into %vreg27:4 at 448B --> @448B erased:672r%vreg41<def> = COPY %vreg27:sel_z; R600_Reg32:%vreg41 R600_Reg128:%vreg27 updated: 688B%T2_Z<def> = COPY %vreg27:sel_z; R600_Reg128:%vreg27 Joined. Result = %vreg27[128r,192r:0)[192r,272r:1)[272r,320r:2)[320r,448B:3)[448B,704r:4)[880B,1168B:4) 0 at 128r 1 at 192r 2 at 272r 3 at 320r 4 at 448B-phi 688B%T2_Z<def> = COPY %vreg27:sel_z; R600_Reg128:%vreg27 Considering merging %vreg27 with %T2_XYZW Can only merge into reserved registers. 704B%vreg42<def> = COPY %vreg27:sel_w; R600_Reg32:%vreg42 R600_Reg128:%vreg27 Considering merging to R600_Reg128 with %vreg42 in %vreg27:sel_w RHS = %vreg42 [704r,720r:0) 0 at 704r LHS = %vreg27 [128r,192r:0)[192r,272r:1)[272r,320r:2)[320r,448B:3)[448B,704r:4)[880B,1168B:4) 0 at 128r 1 at 192r 2 at 272r 3 at 320r 4 at 448B-phi merge %vreg42:0 at 704r into %vreg27:4 at 448B --> @448B erased:704r%vreg42<def> = COPY %vreg27:sel_w; R600_Reg32:%vreg42 R600_Reg128:%vreg27 updated: 720B%T2_W<def> = COPY %vreg27:sel_w; R600_Reg128:%vreg27 Joined. Result = %vreg27[128r,192r:0)[192r,272r:1)[272r,320r:2)[320r,448B:3)[448B,720r:4)[880B,1168B:4) 0 at 128r 1 at 192r 2 at 272r 3 at 320r 4 at 448B-phi 720B%T2_W<def> = COPY %vreg27:sel_w; R600_Reg128:%vreg27 Considering merging %vreg27 with %T2_XYZW Can only merge into reserved registers. 736B%vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1 Considering merging to R600_Reg128 with %vreg43 in %vreg1:sel_x RHS = %vreg43 [736r,752r:0) 0 at 736r LHS = %vreg1 [16r,32r:0)[32r,48r:1)[48r,64r:2)[64r,832r:3)[880B,1168B:3) 0 at 16r 1 at 32r 2 at 48r 3 at 64r merge %vreg43:0 at 736r into %vreg1:3 at 64r --> @64r erased:736r%vreg43<def> = COPY %vreg1:sel_x; R600_Reg32:%vreg43 R600_Reg128:%vreg1 updated: 752B%T1_X<def> = COPY %vreg1:sel_x; R600_Reg128:%vreg1 Joined. Result = %vreg1[16r,32r:0)[32r,48r:1)[48r,64r:2)[64r,832r:3)[880B,1168B:3) 0 at 16r 1 at 32r 2 at 48r 3 at 64r 752B%T1_X<def> = COPY %vreg1:sel_x; R600_Reg128:%vreg1 Considering merging %vreg1 with %T1_XYZW Can only merge into reserved registers. 768B%vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1 Considering merging to R600_Reg128 with %vreg44 in %vreg1:sel_y RHS = %vreg44 [768r,784r:0) 0 at 768r LHS = %vreg1 [16r,32r:0)[32r,48r:1)[48r,64r:2)[64r,832r:3)[880B,1168B:3) 0 at 16r 1 at 32r 2 at 48r 3 at 64r merge %vreg44:0 at 768r into %vreg1:3 at 64r --> @64r erased:768r%vreg44<def> = COPY %vreg1:sel_y; R600_Reg32:%vreg44 R600_Reg128:%vreg1 updated: 784B%T1_Y<def> = COPY %vreg1:sel_y; R600_Reg128:%vreg1 Joined. Result = %vreg1[16r,32r:0)[32r,48r:1)[48r,64r:2)[64r,832r:3)[880B,1168B:3) 0 at 16r 1 at 32r 2 at 48r 3 at 64r 784B%T1_Y<def> = COPY %vreg1:sel_y; R600_Reg128:%vreg1 Considering merging %vreg1 with %T1_XYZW Can only merge into reserved registers. 800B%vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1 Considering merging to R600_Reg128 with %vreg45 in %vreg1:sel_z RHS = %vreg45 [800r,816r:0) 0 at 800r LHS = %vreg1 [16r,32r:0)[32r,48r:1)[48r,64r:2)[64r,832r:3)[880B,1168B:3) 0 at 16r 1 at 32r 2 at 48r 3 at 64r merge %vreg45:0 at 800r into %vreg1:3 at 64r --> @64r erased:800r%vreg45<def> = COPY %vreg1:sel_z; R600_Reg32:%vreg45 R600_Reg128:%vreg1 updated: 816B%T1_Z<def> = COPY %vreg1:sel_z; R600_Reg128:%vreg1 Joined. Result = %vreg1[16r,32r:0)[32r,48r:1)[48r,64r:2)[64r,832r:3)[880B,1168B:3) 0 at 16r 1 at 32r 2 at 48r 3 at 64r 816B%T1_Z<def> = COPY %vreg1:sel_z; R600_Reg128:%vreg1 Considering merging %vreg1 with %T1_XYZW Can only merge into reserved registers. 832B%vreg46<def> = COPY %vreg1:sel_w; R600_Reg32:%vreg46 R600_Reg128:%vreg1 Considering merging to R600_Reg128 with %vreg46 in %vreg1:sel_w RHS = %vreg46 [832r,848r:0) 0 at 832r LHS = %vreg1 [16r,32r:0)[32r,48r:1)[48r,64r:2)[64r,832r:3)[880B,1168B:3) 0 at 16r 1 at 32r 2 at 48r 3 at 64r merge %vreg46:0 at 832r into %vreg1:3 at 64r --> @64r erased:832r%vreg46<def> = COPY %vreg1:sel_w; R600_Reg32:%vreg46 R600_Reg128:%vreg1 updated: 848B%T1_W<def> = COPY %vreg1:sel_w; R600_Reg128:%vreg1 Joined. Result = %vreg1[16r,32r:0)[32r,48r:1)[48r,64r:2)[64r,848r:3)[880B,1168B:3) 0 at 16r 1 at 32r 2 at 48r 3 at 64r 848B%T1_W<def> = COPY %vreg1:sel_w; R600_Reg128:%vreg1 Considering merging %vreg1 with %T1_XYZW Can only merge into reserved registers. 976B%vreg10<def> = COPY %vreg27; R600_Reg128:%vreg10,%vreg27 Considering merging to R600_Reg128 with %vreg27 in %vreg10 RHS = %vreg10 [976r,992r:0)[992r,1040r:1)[1040r,1040d:2) 0 at 976r 1 at 992r 2 at 1040r LHS = %vreg27 [128r,192r:0)[192r,272r:1)[272r,320r:2)[320r,448B:3)[448B,720r:4)[880B,1168B:4) 0 at 128r 1 at 192r 2 at 272r 3 at 320r 4 at 448B-phi merge %vreg10:0 at 976r into %vreg27:4 at 448B --> @448B interference at %vreg10:1 at 992r Interference! 992B%vreg10:sel_z<def> = COPY %vreg47; R600_Reg128:%vreg10 R600_Reg32:%vreg47 Considering merging to R600_Reg128 with %vreg47 in %vreg10:sel_z RHS = %vreg47 [400r,448B:0)[448B,592B:1)[880B,992r:1)[1104r,1168B:2) 0 at 400r 1 at 448B-phi 2 at 1104r LHS = %vreg10 [976r,992r:0)[992r,1040r:1)[1040r,1040d:2) 0 at 976r 1 at 992r 2 at 1040r interference at %vreg10:0 at 976r Interference! 1040B%vreg10:sel_w<def,dead> = COPY %vreg27:sel_w; R600_Reg128:%vreg10,%vreg27 Copy is dead. Deleting dead def 1040r%vreg10:sel_w<def,dead> = COPY %vreg27:sel_w; R600_Reg128:%vreg10,%vreg27 Shrink: [128r,192r:0)[192r,272r:1)[272r,320r:2)[320r,448B:3)[448B,720r:4)[880B,1168B:4) 0 at 128r 1 at 192r 2 at 272r 3 at 320r 4 at 448B-phi live-in at 592B live-in at 880B Shrunk: [128r,192r:0)[192r,272r:1)[272r,320r:2)[320r,448B:3)[448B,720r:4)[880B,1168B:4) 0 at 128r 1 at 192r 2 at 272r 3 at 320r 4 at 448B-phi Shrink: [976r,992r:0)[992r,1040r:1) 0 at 976r 1 at 992r All defs dead: 992r%vreg10:sel_z<def,dead> = COPY %vreg47; R600_Reg128:%vreg10 R600_Reg32:%vreg47 Shrunk: [976r,992r:0)[992r,992d:1) 0 at 976r 1 at 992r Deleting dead def 992r%vreg10:sel_z<def,dead> = COPY %vreg47; R600_Reg128:%vreg10 R600_Reg32:%vreg47 Shrink: [400r,448B:0)[448B,592B:1)[880B,992r:1)[1104r,1168B:2) 0 at 400r 1 at 448B-phi 2 at 1104r All defs dead: 400r%vreg47<def,dead> = COPY %C1_Y; R600_Reg32:%vreg47 Dead PHI at invalid may separate interval All defs dead: 1104r%vreg47<def,dead> = COPY %vreg27:sel_z; R600_Reg32:%vreg47 R600_Reg128:%vreg27 Shrunk: [400r,400d:0)[1104r,1104d:2) 0 at 400r 1 at x 2 at 1104r 2 components: [400r,400d:0)[1104r,1104d:1) 0 at 400r 1 at 1104r [400r,400d:0) 0 at 400r [1104r,1104d:0) 0 at 1104r Deleting dead def 1104r%vreg50<def,dead> = COPY %vreg27:sel_z; R600_Reg32:%vreg50 R600_Reg128:%vreg27 Deleting dead def 400r%vreg47<def,dead> = COPY %C1_Y; R600_Reg32:%vreg47 Shrink: [128r,192r:0)[192r,272r:1)[272r,320r:2)[320r,448B:3)[448B,720r:4)[880B,1168B:4) 0 at 128r 1 at 192r 2 at 272r 3 at 320r 4 at 448B-phi live-in at 592B live-in at 880B Shrunk: [128r,192r:0)[192r,272r:1)[272r,320r:2)[320r,448B:3)[448B,720r:4)[880B,1168B:4) 0 at 128r 1 at 192r 2 at 272r 3 at 320r 4 at 448B-phi Shrink: [976r,992r:0) 0 at 976r All defs dead: 976r%vreg10<def,dead> = COPY %vreg27; R600_Reg128:%vreg10,%vreg27 Shrunk: [976r,976d:0) 0 at 976r Deleting dead def 976r%vreg10<def,dead> = COPY %vreg27; R600_Reg128:%vreg10,%vreg27 Shrink: [128r,192r:0)[192r,272r:1)[272r,320r:2)[320r,448B:3)[448B,720r:4)[880B,1168B:4) 0 at 128r 1 at 192r 2 at 272r 3 at 320r 4 at 448B-phi live-in at 592B live-in at 880B Shrunk: [128r,192r:0)[192r,272r:1)[272r,320r:2)[320r,448B:3)[448B,720r:4)[880B,1168B:4) 0 at 128r 1 at 192r 2 at 272r 3 at 320r 4 at 448B-phi Trying to inflate 0 regs. ********** INTERVALS ********** C0_X = EMPTY C1_W = EMPTY C1_X = EMPTY C1_Y = EMPTY C1_Z = EMPTY T1_W = [0B,16r:0)[848r,864r:1) 0 at 0B-phi 1 at 848r T1_X = [0B,64r:0)[752r,864r:1) 0 at 0B-phi 1 at 752r T1_Y = [0B,48r:0)[784r,864r:1) 0 at 0B-phi 1 at 784r T1_Z = [0B,32r:0)[816r,864r:1) 0 at 0B-phi 1 at 816r %vreg1 = [16r,32r:0)[32r,48r:1)[48r,64r:2)[64r,848r:3)[880B,1168B:3) 0 at 16r 1 at 32r 2 at 48r 3 at 64r %vreg27 = [128r,192r:0)[192r,272r:1)[272r,320r:2)[320r,448B:3)[448B,720r:4)[880B,1168B:4) 0 at 128r 1 at 192r 2 at 272r 3 at 320r 4 at 448B-phi %vreg30 = [512r,544r:0) 0 at 512r %vreg38 = [1072r,1088r:0) 0 at 1072r %vreg49 = [368r,448B:0)[448B,592B:1)[880B,1088r:1)[1088r,1168B:2) 0 at 368r 1 at 448B-phi 2 at 1088r ********** MACHINEINSTRS ********** # Machine code for function main: Post SSA Function Live Ins: %T1_X in %vreg14, %T1_Y in %vreg15, %T1_Z in %vreg16, %T1_W in %vreg17 Function Live Outs: %T1_W %T1_Z %T1_Y %T1_X %T2_W %T2_Z %T2_Y %T2_X 0BBB#0: derived from LLVM BB %0 Live Ins: %T1_X %T1_Y %T1_Z %T1_W 16B%vreg1:sel_w<def,read-undef> = COPY %T1_W; R600_Reg128:%vreg1 32B%vreg1:sel_z<def> = COPY %T1_Z; R600_Reg128:%vreg1 48B%vreg1:sel_y<def> = COPY %T1_Y; R600_Reg128:%vreg1 64B%vreg1:sel_x<def> = COPY %T1_X; R600_Reg128:%vreg1 128B%vreg27:sel_x<def,read-undef> = COPY %C1_X; R600_Reg128:%vreg27 192B%vreg27:sel_y<def> = COPY %C1_Y; R600_Reg128:%vreg27 272B%vreg27:sel_z<def> = COPY %C1_Z; R600_Reg128:%vreg27 320B%vreg27:sel_w<def> = COPY %C1_W; R600_Reg128:%vreg27 368B%vreg49<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg49 Successors according to CFG: BB#1 448BBB#1: derived from LLVM BB %25 Predecessors according to CFG: BB#0 BB#3 512B%vreg30<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %vreg49, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg30,%vreg49 544B%PREDICATE_BIT<def> = PRED_X %vreg30, 152, 16; R600_Reg32:%vreg30 560BJUMP <BB#3>, pred:%PREDICATE_BIT 576BJUMP <BB#2>, pred:%noreg Successors according to CFG: BB#2(4) BB#3(124) 592BBB#2: derived from LLVM BB %31 Predecessors according to CFG: BB#1 624B%T2_X<def> = COPY %vreg27:sel_x; R600_Reg128:%vreg27 656B%T2_Y<def> = COPY %vreg27:sel_y; R600_Reg128:%vreg27 688B%T2_Z<def> = COPY %vreg27:sel_z; R600_Reg128:%vreg27 720B%T2_W<def> = COPY %vreg27:sel_w; R600_Reg128:%vreg27 752B%T1_X<def> = COPY %vreg1:sel_x; R600_Reg128:%vreg1 784B%T1_Y<def> = COPY %vreg1:sel_y; R600_Reg128:%vreg1 816B%T1_Z<def> = COPY %vreg1:sel_z; R600_Reg128:%vreg1 848B%T1_W<def> = COPY %vreg1:sel_w; R600_Reg128:%vreg1 864BRETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>, %T1_X<imp-use>, %T2_W<imp-use,kill>, %T2_Z<imp-use,kill>, %T2_Y<imp-use,kill>, %T2_X<imp-use,kill> 880BBB#3: derived from LLVM BB %41 Predecessors according to CFG: BB#1 1072B%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38 1088B%vreg49<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg49, 0, 0, 0, %vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg49,%vreg38 1152BJUMP <BB#1>, pred:%noreg Successors according to CFG: BB#1 # End machine code for function main. ********** DEBUG VARIABLES ********** ********** GREEDY REGISTER ALLOCATION ********** ********** Function: main selectOrSplit R600_Reg128:%vreg1 [16r,32r:0)[32r,48r:1)[48r,64r:2)[64r,848r:3)[880B,1168B:3) 0 at 16r 1 at 32r 2 at 48r 3 at 64r AllocationOrder(R600_Reg128) = [ %T1_XYZW %T2_XYZW %T3_XYZW %T4_XYZW %T5_XYZW %T6_XYZW %T7_XYZW %T8_XYZW %T9_XYZW %T10_XYZW %T11_XYZW %T12_XYZW %T13_XYZW %T14_XYZW %T15_XYZW %T16_XYZW %T17_XYZW %T18_XYZW %T19_XYZW %T20_XYZW %T21_XYZW %T22_XYZW %T23_XYZW %T24_XYZW %T25_XYZW %T26_XYZW %T27_XYZW %T28_XYZW %T29_XYZW %T30_XYZW %T31_XYZW %T32_XYZW %T33_XYZW %T34_XYZW %T35_XYZW %T36_XYZW %T37_XYZW %T38_XYZW %T39_XYZW %T40_XYZW %T41_XYZW %T42_XYZW %T43_XYZW %T44_XYZW %T45_XYZW %T46_XYZW %T47_XYZW %T48_XYZW %T49_XYZW %T50_XYZW %T51_XYZW %T52_XYZW %T53_XYZW %T54_XYZW %T55_XYZW %T56_XYZW %T57_XYZW %T58_XYZW %T59_XYZW %T60_XYZW %T61_XYZW %T62_XYZW %T63_XYZW %T64_XYZW %T65_XYZW %T66_XYZW %T67_XYZW %T68_XYZW %T69_XYZW %T70_XYZW %T71_XYZW %T72_XYZW %T73_XYZW %T74_XYZW %T75_XYZW %T76_XYZW %T77_XYZW %T78_XYZW %T79_XYZW %T80_XYZW %T81_XYZW %T82_XYZW %T83_XYZW %T84_XYZW %T85_XYZW %T86_XYZW %T87_XYZW %T88_XYZW %T89_XYZW %T90_XYZW %T91_XYZW %T92_XYZW %T93_XYZW %T94_XYZW %T95_XYZW %T96_XYZW %T97_XYZW %T98_XYZW %T99_XYZW %T100_XYZW %T101_XYZW %T102_XYZW %T103_XYZW %T104_XYZW %T105_XYZW %T106_XYZW %T107_XYZW %T108_XYZW %T109_XYZW %T110_XYZW %T111_XYZW %T112_XYZW %T113_XYZW %T114_XYZW %T115_XYZW %T116_XYZW %T117_XYZW %T118_XYZW %T119_XYZW %T120_XYZW %T121_XYZW %T122_XYZW %T123_XYZW %T124_XYZW %T125_XYZW %T126_XYZW %T127_XYZW ] assigning %vreg1 to %T1_XYZW: T1_W T1_X T1_Y T1_Z selectOrSplit R600_Reg128:%vreg27 [128r,192r:0)[192r,272r:1)[272r,320r:2)[320r,448B:3)[448B,720r:4)[880B,1168B:4) 0 at 128r 1 at 192r 2 at 272r 3 at 320r 4 at 448B-phi assigning %vreg27 to %T2_XYZW: T2_W T2_X T2_Y T2_Z selectOrSplit R600_Reg32:%vreg49 [368r,448B:0)[448B,592B:1)[880B,1088r:1)[1088r,1168B:2) 0 at 368r 1 at 448B-phi 2 at 1088r AllocationOrder(R600_Reg32) = [ %T1_X %T1_Y %T1_Z %T1_W %T2_X %T2_Y %T2_Z %T2_W %T3_X %T3_Y %T3_Z %T3_W %T4_X %T4_Y %T4_Z %T4_W %T5_X %T5_Y %T5_Z %T5_W %T6_X %T6_Y %T6_Z %T6_W %T7_X %T7_Y %T7_Z %T7_W %T8_X %T8_Y %T8_Z %T8_W %T9_X %T9_Y %T9_Z %T9_W %T10_X %T10_Y %T10_Z %T10_W %T11_X %T11_Y %T11_Z %T11_W %T12_X %T12_Y %T12_Z %T12_W %T13_X %T13_Y %T13_Z %T13_W %T14_X %T14_Y %T14_Z %T14_W %T15_X %T15_Y %T15_Z %T15_W %T16_X %T16_Y %T16_Z %T16_W %T17_X %T17_Y %T17_Z %T17_W %T18_X %T18_Y %T18_Z %T18_W %T19_X %T19_Y %T19_Z %T19_W %T20_X %T20_Y %T20_Z %T20_W %T21_X %T21_Y %T21_Z %T21_W %T22_X %T22_Y %T22_Z %T22_W %T23_X %T23_Y %T23_Z %T23_W %T24_X %T24_Y %T24_Z %T24_W %T25_X %T25_Y %T25_Z %T25_W %T26_X %T26_Y %T26_Z %T26_W %T27_X %T27_Y %T27_Z %T27_W %T28_X %T28_Y %T28_Z %T28_W %T29_X %T29_Y %T29_Z %T29_W %T30_X %T30_Y %T30_Z %T30_W %T31_X %T31_Y %T31_Z %T31_W %T32_X %T32_Y %T32_Z %T32_W %T33_X %T33_Y %T33_Z %T33_W %T34_X %T34_Y %T34_Z %T34_W %T35_X %T35_Y %T35_Z %T35_W %T36_X %T36_Y %T36_Z %T36_W %T37_X %T37_Y %T37_Z %T37_W %T38_X %T38_Y %T38_Z %T38_W %T39_X %T39_Y %T39_Z %T39_W %T40_X %T40_Y %T40_Z %T40_W %T41_X %T41_Y %T41_Z %T41_W %T42_X %T42_Y %T42_Z %T42_W %T43_X %T43_Y %T43_Z %T43_W %T44_X %T44_Y %T44_Z %T44_W %T45_X %T45_Y %T45_Z %T45_W %T46_X %T46_Y %T46_Z %T46_W %T47_X %T47_Y %T47_Z %T47_W %T48_X %T48_Y %T48_Z %T48_W %T49_X %T49_Y %T49_Z %T49_W %T50_X %T50_Y %T50_Z %T50_W %T51_X %T51_Y %T51_Z %T51_W %T52_X %T52_Y %T52_Z %T52_W %T53_X %T53_Y %T53_Z %T53_W %T54_X %T54_Y %T54_Z %T54_W %T55_X %T55_Y %T55_Z %T55_W %T56_X %T56_Y %T56_Z %T56_W %T57_X %T57_Y %T57_Z %T57_W %T58_X %T58_Y %T58_Z %T58_W %T59_X %T59_Y %T59_Z %T59_W %T60_X %T60_Y %T60_Z %T60_W %T61_X %T61_Y %T61_Z %T61_W %T62_X %T62_Y %T62_Z %T62_W %T63_X %T63_Y %T63_Z %T63_W %T64_X %T64_Y %T64_Z %T64_W %T65_X %T65_Y %T65_Z %T65_W %T66_X %T66_Y %T66_Z %T66_W %T67_X %T67_Y %T67_Z %T67_W %T68_X %T68_Y %T68_Z %T68_W %T69_X %T69_Y %T69_Z %T69_W %T70_X %T70_Y %T70_Z %T70_W %T71_X %T71_Y %T71_Z %T71_W %T72_X %T72_Y %T72_Z %T72_W %T73_X %T73_Y %T73_Z %T73_W %T74_X %T74_Y %T74_Z %T74_W %T75_X %T75_Y %T75_Z %T75_W %T76_X %T76_Y %T76_Z %T76_W %T77_X %T77_Y %T77_Z %T77_W %T78_X %T78_Y %T78_Z %T78_W %T79_X %T79_Y %T79_Z %T79_W %T80_X %T80_Y %T80_Z %T80_W %T81_X %T81_Y %T81_Z %T81_W %T82_X %T82_Y %T82_Z %T82_W %T83_X %T83_Y %T83_Z %T83_W %T84_X %T84_Y %T84_Z %T84_W %T85_X %T85_Y %T85_Z %T85_W %T86_X %T86_Y %T86_Z %T86_W %T87_X %T87_Y %T87_Z %T87_W %T88_X %T88_Y %T88_Z %T88_W %T89_X %T89_Y %T89_Z %T89_W %T90_X %T90_Y %T90_Z %T90_W %T91_X %T91_Y %T91_Z %T91_W %T92_X %T92_Y %T92_Z %T92_W %T93_X %T93_Y %T93_Z %T93_W %T94_X %T94_Y %T94_Z %T94_W %T95_X %T95_Y %T95_Z %T95_W %T96_X %T96_Y %T96_Z %T96_W %T97_X %T97_Y %T97_Z %T97_W %T98_X %T98_Y %T98_Z %T98_W %T99_X %T99_Y %T99_Z %T99_W %T100_X %T100_Y %T100_Z %T100_W %T101_X %T101_Y %T101_Z %T101_W %T102_X %T102_Y %T102_Z %T102_W %T103_X %T103_Y %T103_Z %T103_W %T104_X %T104_Y %T104_Z %T104_W %T105_X %T105_Y %T105_Z %T105_W %T106_X %T106_Y %T106_Z %T106_W %T107_X %T107_Y %T107_Z %T107_W %T108_X %T108_Y %T108_Z %T108_W %T109_X %T109_Y %T109_Z %T109_W %T110_X %T110_Y %T110_Z %T110_W %T111_X %T111_Y %T111_Z %T111_W %T112_X %T112_Y %T112_Z %T112_W %T113_X %T113_Y %T113_Z %T113_W %T114_X %T114_Y %T114_Z %T114_W %T115_X %T115_Y %T115_Z %T115_W %T116_X %T116_Y %T116_Z %T116_W %T117_X %T117_Y %T117_Z %T117_W %T118_X %T118_Y %T118_Z %T118_W %T119_X %T119_Y %T119_Z %T119_W %T120_X %T120_Y %T120_Z %T120_W %T121_X %T121_Y %T121_Z %T121_W %T122_X %T122_Y %T122_Z %T122_W %T123_X %T123_Y %T123_Z %T123_W %T124_X %T124_Y %T124_Z %T124_W %T125_X %T125_Y %T125_Z %T125_W %T126_X %T126_Y %T126_Z %T126_W %T127_X %T127_Y %T127_Z %T127_W %ArrayBase448 %ArrayBase449 %ArrayBase450 %ArrayBase451 %ArrayBase452 %ArrayBase453 %ArrayBase454 %ArrayBase455 %ArrayBase456 %ArrayBase457 %ArrayBase458 %ArrayBase459 %ArrayBase460 %ArrayBase461 %ArrayBase462 %ArrayBase463 %ArrayBase464 ] assigning %vreg49 to %T3_X: T3_X selectOrSplit R600_Reg32:%vreg30 [512r,544r:0) 0 at 512r assigning %vreg30 to %T3_Y: T3_Y selectOrSplit R600_Reg32:%vreg38 [1072r,1088r:0) 0 at 1072r assigning %vreg38 to %T3_Y: T3_Y ********** REWRITE VIRTUAL REGISTERS ********** ********** Function: main ********** REGISTER MAP ********** [%vreg1 -> %T1_XYZW] R600_Reg128 [%vreg27 -> %T2_XYZW] R600_Reg128 [%vreg30 -> %T3_Y] R600_Reg32 [%vreg38 -> %T3_Y] R600_Reg32 [%vreg49 -> %T3_X] R600_Reg32 0BBB#0: derived from LLVM BB %0 Live Ins: %T1_X %T1_Y %T1_Z %T1_W 16B%vreg1:sel_w<def,read-undef> = COPY %T1_W; R600_Reg128:%vreg1 32B%vreg1:sel_z<def> = COPY %T1_Z; R600_Reg128:%vreg1 48B%vreg1:sel_y<def> = COPY %T1_Y; R600_Reg128:%vreg1 64B%vreg1:sel_x<def> = COPY %T1_X; R600_Reg128:%vreg1 128B%vreg27:sel_x<def,read-undef> = COPY %C1_X; R600_Reg128:%vreg27 192B%vreg27:sel_y<def> = COPY %C1_Y; R600_Reg128:%vreg27 272B%vreg27:sel_z<def> = COPY %C1_Z; R600_Reg128:%vreg27 320B%vreg27:sel_w<def> = COPY %C1_W; R600_Reg128:%vreg27 368B%vreg49<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg49 Successors according to CFG: BB#1> %T1_W<def> = COPY %T1_W, %T1_XYZW<imp-def>Identity copy: %T1_W<def> = KILL %T1_W, %T1_XYZW<imp-def>> %T1_Z<def> = COPY %T1_Z, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def>Identity copy: %T1_Z<def> = KILL %T1_Z, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def>> %T1_Y<def> = COPY %T1_Y, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def>Identity copy: %T1_Y<def> = KILL %T1_Y, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def>> %T1_X<def> = COPY %T1_X, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def>Identity copy: %T1_X<def> = KILL %T1_X, %T1_XYZW<imp-use,kill>, %T1_XYZW<imp-def>> %T2_X<def> = COPY %C1_X, %T2_XYZW<imp-def> > %T2_Y<def> = COPY %C1_Y, %T2_XYZW<imp-use,kill>, %T2_XYZW<imp-def> > %T2_Z<def> = COPY %C1_Z, %T2_XYZW<imp-use,kill>, %T2_XYZW<imp-def> > %T2_W<def> = COPY %C1_W, %T2_XYZW<imp-use,kill>, %T2_XYZW<imp-def> > %T3_X<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0448BBB#1: derived from LLVM BB %25 Live Ins: %T1_XYZW %T2_XYZW %T3_X Predecessors according to CFG: BB#0 BB#3 512B%vreg30<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %vreg49, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg30,%vreg49 544B%PREDICATE_BIT<def> = PRED_X %vreg30<kill>, 152, 16; R600_Reg32:%vreg30 560BJUMP <BB#3>, pred:%PREDICATE_BIT 576BJUMP <BB#2>, pred:%noreg Successors according to CFG: BB#2(4) BB#3(124)> %T3_Y<def> = SETGT_INT 0, 0, 1, 0, 0, 0, %C0_X, 0, 0, 0, %T3_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > %PREDICATE_BIT<def> = PRED_X %T3_Y<kill>, 152, 16 > JUMP <BB#3>, pred:%PREDICATE_BIT > JUMP <BB#2>, pred:%noreg592BBB#2: derived from LLVM BB %31 Live Ins: %T1_XYZW %T2_XYZW Predecessors according to CFG: BB#1 624B%T2_X<def> = COPY %vreg27:sel_x; R600_Reg128:%vreg27 656B%T2_Y<def> = COPY %vreg27:sel_y; R600_Reg128:%vreg27 688B%T2_Z<def> = COPY %vreg27:sel_z; R600_Reg128:%vreg27 720B%T2_W<def> = COPY %vreg27:sel_w; R600_Reg128:%vreg27 752B%T1_X<def> = COPY %vreg1:sel_x; R600_Reg128:%vreg1 784B%T1_Y<def> = COPY %vreg1:sel_y; R600_Reg128:%vreg1 816B%T1_Z<def> = COPY %vreg1:sel_z; R600_Reg128:%vreg1 848B%T1_W<def> = COPY %vreg1:sel_w; R600_Reg128:%vreg1 864BRETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>, %T1_X<imp-use>, %T2_W<imp-use>, %T2_Z<imp-use>, %T2_Y<imp-use>, %T2_X<imp-use>> %T2_X<def> = COPY %T2_XDeleting identity copy.> %T2_Y<def> = COPY %T2_YDeleting identity copy.> %T2_Z<def> = COPY %T2_ZDeleting identity copy.> %T2_W<def> = COPY %T2_WDeleting identity copy.> %T1_X<def> = COPY %T1_XDeleting identity copy.> %T1_Y<def> = COPY %T1_YDeleting identity copy.> %T1_Z<def> = COPY %T1_ZDeleting identity copy.> %T1_W<def> = COPY %T1_WDeleting identity copy.> RETURN %T1_W<imp-use>, %T1_Z<imp-use>, %T1_Y<imp-use>, %T1_X<imp-use>, %T2_W<imp-use>, %T2_Z<imp-use>, %T2_Y<imp-use>, %T2_X<imp-use>880BBB#3: derived from LLVM BB %41 Live Ins: %T1_XYZW %T2_XYZW %T3_X Predecessors according to CFG: BB#1 1072B%vreg38<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1; R600_Reg32:%vreg38 1088B%vreg49<def> = ADD_INT 0, 0, 1, 0, 0, 0, %vreg49<kill>, 0, 0, 0, %vreg38<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0; R600_Reg32:%vreg49,%vreg38 1152BJUMP <BB#1>, pred:%noreg Successors according to CFG: BB#1> %T3_Y<def> = MOV 1, 0, 0, 0, %ALU_LITERAL_X, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 1 > %T3_X<def> = ADD_INT 0, 0, 1, 0, 0, 0, %T3_X<kill>, 0, 0, 0, %T3_Y<kill>, 0, 0, 0, 1, pred:%PRED_SEL_OFF, 0 > JUMP <BB#1>, pred:%noreg
Seemingly Similar Threads
- [LLVMdev] RegisterCoalescing Pass seems to ignore part of CFG.
- [LLVMdev] RegisterCoalescing Pass seems to ignore part of CFG.
- [LLVMdev] RegisterCoalescing Pass seems to ignore part of CFG.
- [LLVMdev] RegisterCoalescing Pass seems to ignore part of CFG.
- [LLVMdev] RegisterCoalescing Pass seems to ignore part of CFG.