search for: bb1_1

...entptr i64* %1, i64 2 %a_val = load i64* %8, align 8 call void @showValue(i64 %a_val) %9 = trunc i64 %a_val to i32 %10 = inttoptr i64 %a_val to [2 x i32]* br label %bb4_1 fun 1_subloop_1 bb_1 bb_1: ; preds = %bb4_1 br i1 undef, label %bb1_1, label %bb2_1 fun 1_subloop_1 bb1_1 bb1_1: ; preds = %bb_1 %t15_1 = load i32* %7, align 4 %t16_1 = getelementptr inbounds [2 x i32]* %10, i32 0, i32 %t15_1 %t17_1 = load i32* %t16_1, align 4 %t19_1 = mul nsw i32 %t17_1, undef %t19_1_64...

...4 %fl3, %fl2, 0dBFF0000000000000; > > mov.f64 %fl2, 0d0000000000000000; > > mov.f64 %fl5, %fl2; > > mov.f64 %fl4, %fl2; > > bra.uni BB1_1; > > BB1_2: > > add.f64 %fl2, %fl2, 0d3FF0000000000000; > > sub.f64 %fl6, %fl6, %fl7; > > add.f64 %fl6, %fl6, %fl1; > > add.f64 %fl5, %fl5, %...

Hi, All I want to implement DSWP Which is used for parallelization of loops. For this purpose, the loop was replaced with a new basic block in main function. And new functions were created and basic blocks of Loop assigned to them.I have checked blocks and branches for Succ and Pred relation and I have not found any problems. However I get the following error: * **opt:

...l3, %fl2, 0dBFF0000000000000; > > > mov.f64                                %fl2, 0d0000000000000000; > > > mov.f64                                %fl5, %fl2; > > > mov.f64                                %fl4, %fl2; > > > bra.uni                                BB1_1; > > > BB1_2: > > > add.f64                                %fl2, %fl2, 0d3FF0000000000000; > > > sub.f64                                %fl6, %fl6, %fl7; > > > add.f64                                %fl6, %fl6, %fl1; > > > add.f64                     ...

...%fl3, %fl2, 0dBFF0000000000000; >> > mov.f64 %fl2, 0d0000000000000000; >> > mov.f64 %fl5, %fl2; >> > mov.f64 %fl4, %fl2; >> > bra.uni BB1_1; >> > BB1_2: >> > add.f64 %fl2, %fl2, 0d3FF0000000000000; >> > sub.f64 %fl6, %fl6, %fl7; >> > add.f64 %fl6, %fl6, %fl1; >> > add.f64...

...000000000000; > >> > mov.f64 %fl2, 0d0000000000000000; > >> > mov.f64 %fl5, %fl2; > >> > mov.f64 %fl4, %fl2; > >> > bra.uni BB1_1; > >> > BB1_2: > >> > add.f64 %fl2, %fl2, > 0d3FF0000000000000; > >> > sub.f64 %fl6, %fl6, %fl7; > >> > add.f64 %fl6, %fl6, %fl1; > >> >...

...Begin function hoo 74 .p2align 4, 0x90 75 .type hoo, at function 76 hoo: # @hoo 77 .cfi_startproc 78 # BB#0: 79 movq a(%rip), %rax 80 movq cnt(%rip), %rcx 81 cmpq $0, i_hasval(%rip) 82 sete %sil 83 xorl %edx, %edx 84 .p2align 4, 0x90 85 .LBB1_1: # =>This Inner Loop Header: Depth=1 86 testb $1, %sil 87 je .LBB1_3 88 # BB#2: # in Loop: Header=BB1_1 Depth=1 89 movq b(%rip), %rsi 90 addq %rax, %rsi 91 movq %rsi, c(%rip) 92 movq $3, i_hasval(%rip) 93 incq %...

...tion_param_4; div.rn.f64 %fl2, %fl2, %fl3; add.f64 %fl2, %fl2, %fl2; add.f64 %fl3, %fl2, 0dBFF0000000000000; mov.f64 %fl2, 0d0000000000000000; mov.f64 %fl5, %fl2; mov.f64 %fl4, %fl2; bra.uni BB1_1; BB1_2: add.f64 %fl2, %fl2, 0d3FF0000000000000; sub.f64 %fl6, %fl6, %fl7; add.f64 %fl6, %fl6, %fl1; add.f64 %fl5, %fl5, %fl5; mul.f64 %fl4, %fl5, %fl4; add.f64 %fl4, %fl4, %fl3; mov.f64 %...

...# @hoo >> 77 .cfi_startproc >> 78 # BB#0: >> 79 movq a(%rip), %rax >> 80 movq cnt(%rip), %rcx >> 81 cmpq $0, i_hasval(%rip) >> 82 sete %sil >> 83 xorl %edx, %edx >> 84 .p2align 4, 0x90 >> 85 .LBB1_1: # =>This Inner Loop Header: >> Depth=1 >> 86 testb $1, %sil >> 87 je .LBB1_3 >> 88 # BB#2: # in Loop: Header=BB1_1 >> Depth=1 >> 89 movq b(%rip), %rsi >> 90 addq %rax, %rsi >...

...;> >> 78 # BB#0: >> >> 79 movq a(%rip), %rax >> >> 80 movq cnt(%rip), %rcx >> >> 81 cmpq $0, i_hasval(%rip) >> >> 82 sete %sil >> >> 83 xorl %edx, %edx >> >> 84 .p2align 4, 0x90 >> >> 85 .LBB1_1: # =>This Inner Loop Header: >> >> Depth=1 >> >> 86 testb $1, %sil >> >> 87 je .LBB1_3 >> >> 88 # BB#2: # in Loop: Header=BB1_1 >> >> Depth=1 >> >> 89 m...

...聽 聽 聽 聽 聽 聽 add.f64聽 聽 聽 聽 聽 聽 聽 聽 %fl3, %fl2, 0dBFF0000000000000; >聽 聽 聽 聽 聽 聽 聽 聽 mov.f64聽 聽 聽 聽 聽 聽 聽 聽 %fl2, 0d0000000000000000; >聽 聽 聽 聽 聽 聽 聽 聽 mov.f64聽 聽 聽 聽 聽 聽 聽 聽 %fl5, %fl2; >聽 聽 聽 聽 聽 聽 聽 聽 mov.f64聽 聽 聽 聽 聽 聽 聽 聽 %fl4, %fl2; >聽 聽 聽 聽 聽 聽 聽 聽 bra.uni聽 聽 聽 聽 聽 聽 聽 聽 BB1_1; > BB1_2: >聽 聽 聽 聽 聽 聽 聽 聽 add.f64聽 聽 聽 聽 聽 聽 聽 聽 %fl2, %fl2, 0d3FF0000000000000; >聽 聽 聽 聽 聽 聽 聽 聽 sub.f64聽 聽 聽 聽 聽 聽 聽 聽 %fl6, %fl6, %fl7; >聽 聽 聽 聽 聽 聽 聽 聽 add.f64聽 聽 聽 聽 聽 聽 聽 聽 %fl6, %fl6, %fl1; >聽 聽 聽 聽 聽 聽 聽 聽 add.f64聽 聽 聽 聽 聽 聽 聽 聽 %fl5, %fl5, %fl5; >聽 聽 聽 聽 聽 聽 聽 聽...

I am currently able to emit jump tables, but I cannot use then because I cant figure out how to add its address to the constant pool. For example, if I have the jump table ------------------------------------- .JTI1_0: .word .BB1_6 .word .BB1_7 .word .BB1_1 .word .BB1_2 ------------------------------------- the address ".JTI1_0" must be in a constant pool: --------------------------------- .xyz .word .JTI1_0 .... ldr r1, .xyz add r0, r0, r1 ldr r0, [r0] bx r0 --------------------------------- I intended to do something simi...

..., 56, %g1 save %g1, %o6, %o6 sethi 0, %l0 The nop right before sethi is one instruction I'm not being able to reach in my pass. But there is more: add %l0, 1, %l0 st %l0, [%i6+-12] .BB1_2: ! bb8 ld [%i6+-12], %l0 subcc %l0, 1000, %l0 bl .BB1_1 ! bb nop .BB1_3: ! bb12 ba .BB1_5 ! bb19 nop or %g0, 1, %l0 Here both the "ba" and the "nop", that are the 3rd and 2nd last operations of this snipet, are not reachable. Could I express myself good enougth? Is it possible to do what...

...movq a(%rip), %rax >>>> >> 80 movq cnt(%rip), %rcx >>>> >> 81 cmpq $0, i_hasval(%rip) >>>> >> 82 sete %sil >>>> >> 83 xorl %edx, %edx >>>> >> 84 .p2align 4, 0x90 >>>> >> 85 .LBB1_1: # =>This Inner Loop Header: >>>> >> Depth=1 >>>> >> 86 testb $1, %sil >>>> >> 87 je .LBB1_3 >>>> >> 88 # BB#2: # in Loop: Header=BB1_1 >>>> &...

...= a - b; return 0; } And here is the assembly: <Insert the pPPC assembly here> .text .global main .type main, @function .align 2 main: lfs 0, -8(1) lfs 1, -12(1) li 3, 0 fmuls 2, 1, 0 stfs 2, -12(1) lfs 2, -16(1) fnmsubs 0, 1, 0, 2 stfs 0, -16(1) stw 3, -20(1) stw 3, -4(1) BB1_1: # return lwz 3, -4(1) blr .size main,.-main At a glance, it looks right. Line 12 is, indeed the "fnmsubs" command, so the pattern did work. But look at Line 9. Here we see that the "fmuls" also happened! In effect, this means that the fmul happens TWICE. That can&...

...; 80 movq cnt(%rip), %rcx > >>>> >> 81 cmpq $0, i_hasval(%rip) > >>>> >> 82 sete %sil > >>>> >> 83 xorl %edx, %edx > >>>> >> 84 .p2align 4, 0x90 > >>>> >> 85 .LBB1_1: # =>This Inner Loop Header: > >>>> >> Depth=1 > >>>> >> 86 testb $1, %sil > >>>> >> 87 je .LBB1_3 > >>>> >> 88 # BB#2: # in Loop: Header=BB1_1 > >>&gt...

...,$2 bis $31,$31,$0 cmpeq $2,$1,$1 cmoveq $1,1,$0 ret $31,($26),1 ---------------------------------------- Now it compiles to ---------------------------------- zapnot $17,15,$0 zapnot $16,15,$1 cmpeq $1,$0,$0 beq $0,$BB1_2 #return $BB1_1: #cond_true bis $31,$31,$0 ret $31,($26),1 $BB1_2: #return lda $0,1($31) ret $31,($26),1 ---------------------------------- I have added createCFGSimplificationPass in ARMTargetMachine::addInstSelector to fix this problem. Is this the correct solution? I think that...

...inside of it, and it is wrong. hoo: # @hoo .cfi_startproc # BB#0: # %entry movq cnt(%rip), %rax cmpq $0, i_hasval(%rip) sete %dl xorl %ecx, %ecx .p2align 4, 0x90 .LBB1_1: # %do.body.us.i # =>This Inner Loop Header: Depth=1 testb $1, %dl je .LBB1_3 # BB#2: # %if.end2.us.i # in Loop: Header=BB1_1 De...

On Mon, Jul 17, 2017 at 11:18 AM, Sanjoy Das via llvm-dev < llvm-dev at lists.llvm.org> wrote: > Hi, > > On Mon, Jul 17, 2017 at 10:32 AM, Xinliang David Li <davidxl at google.com> > wrote: > > The issue blocks another optimization patch and Wei has spent huge > amount of > > effort isolating the the bootstrap failure to this same problem. I agree > >

...e". .686 .MMX .XMM .model flat EXTERN _abort:near .text public _foo ALIGN 16 _foo proc near sub ESP, 8 $label1: mov EAX, DWORD PTR [ESP + 12] mov DWORD PTR [ESP], EAX mov DWORD PTR [ESP + 4], 0 mov EAX, DWORD PTR [ESP] mov DWORD PTR [_gv], EAX cmp DWORD PTR [ESP], 6 jb $BB1_4 $BB1_1: ; %then mov DWORD PTR [ESP + 4], 0 ALIGN 16 $BB1_2: ; %while ; Loop Depth 1...