search for: tmp6

Dear all I use R for Windows 2.3.1 on a fully updated Windows XP Home SP2 machine and I have two related regular expression problems. platform i386-pc-mingw32 arch i386 os mingw32 system i386, mingw32 status major 2 minor

...=1] %tmp2 = icmp eq i32 %tmp1, 167772160 ; <i1> [#uses=2] %tmp3 = and i32 %tmp, -65536 ; <i32> [#uses=2] %tmp4 = icmp ne i32 %tmp3, 168296448 ; <i1> [#uses=1] %tmp5 = and i1 %tmp2, %tmp4 ; <i1> [#uses=1] %tmp6 = and i32 %tmp, -256 ; <i32> [#uses=2] %tmp7 = icmp eq i32 %tmp6, 168296704 ; <i1> [#uses=1] %tmp8 = icmp eq i32 %tmp3, 168296448 ; <i1> [#uses=2] %tmp9 = icmp ne i32 %tmp6, 168296704 ; <i1> [#uses=1] %tmp10 = and...

...; <[2 x i32*]*> [#uses=2] %tmp1 = getelementptr [2 x i32*]* %x, i32 0, i32 1 ; <i32**> [#uses=1] %tmp23 = ptrtoint i32** %tmp1 to i32 ; <i32> [#uses=1] %x45 = ptrtoint [2 x i32*]* %x to i32 ; <i32> [#uses=1] %tmp6 = sub i32 %tmp23, %x45 ; <i32> [#uses=1] %tmp7 = ashr i32 %tmp6, 2 ; <i32> [#uses=1] ret i32 %tmp7 } The return value is 1. The ashr exposes the pointer size by shifting the 4 byte distance over by 2. For the analysis that I am doing, it would...

...32* %gVal, align 4, !tbaa !2 store i32 %shr47.i197, i32* %bVal, align 4, !tbaa !2 store i32 %threadSliceNum, i32* %threadID, align 4, !tbaa !2 %.idx.val.i = load i32* %.idx.i, align 4, !tbaa !2 %arrayidx.i.i.i = getelementptr inbounds i32* inttoptr (i32 33807872 to i32*), i32 %.idx.val.i %tmp6.i.i.i = load i32* %arrayidx.i.i.i, align 4, !tbaa !2 %inc.i.i.i = add i32 %tmp6.i.i.i, 1 store i32 %inc.i.i.i, i32* %arrayidx.i.i.i, align 4, !tbaa !2 %arrayidx.i.i6.i = getelementptr inbounds i32* inttoptr (i32 33812992 to i32*), i32 %.idx.val.i %tmp6.i.i7.i = load i32* %arrayidx.i.i6.i, a...

...0; i < x; i++) { ret += 1+i*i + i*(i+2); } return ret; } generates: define i32 @loop(i32 %x) nounwind readnone { %1 = icmp sgt i32 %x, 0 br i1 %1, label %bb.nph, label %3 bb.nph: ; preds = %0 %tmp4 = add i32 %x, -1 %tmp6 = add i32 %x, -2 %tmp16 = add i32 %x, -3 %tmp7 = zext i32 %tmp6 to i33 %tmp5 = zext i32 %tmp4 to i33 %tmp17 = zext i32 %tmp16 to i33 %tmp15 = mul i33 %tmp5, %tmp7 %tmp18 = mul i33 %tmp15, %tmp17 %tmp8 = mul i32 %tmp4, %tmp6 %tmp19 = lshr i33 %tmp18, 1 %2 = shl i3...

...store i32 %threadSliceNum, i32* %threadID, align 4, !tbaa !2 %.idx.val.i = load i32* %.idx.i, align 4, !tbaa !2 /// and this load replaced by the original reg (%shr47.i197 above) %arrayidx.i.i.i = getelementptr inbounds i32* inttoptr (i32 33807872 to i32*), i32 %.idx.val.i %tmp6.i.i.i = load i32* %arrayidx.i.i.i, align 4, !tbaa !2 %inc.i.i.i = add i32 %tmp6.i.i.i, 1 store i32 %inc.i.i.i, i32* %arrayidx.i.i.i, align 4, !tbaa !2 %arrayidx.i.i6.i = getelementptr inbounds i32* inttoptr (i32 33812992 to i32*), i32 %.idx.val.i %tmp6.i.i7.i = load i32* %arrayidx.i.i6.i, align...

...2 to i32, !dbg !1023 ; <i32> [#uses=1] store i32 %tmp3, i32* %xx, align 4, !dbg !1023 %tmp4 = load i16* %y, align 2, !dbg !1024 ; <i16> [#uses=1] %tmp5 = sext i16 %tmp4 to i32, !dbg !1024 ; <i32> [#uses=1] store i32 %tmp5, i32* %yy, align 4, !dbg !1024 %tmp6 = load %struct.MT** @mt, align 8, !dbg !1025 ; <%struct.MT*> [#uses=1] call void @MTPoint_DIRECT(%struct.MT* %tmp6, i32* %xx, i32* %yy) nounwind %tmp8 = load i32* %xx, align 4, !dbg !1026 ; <i32> [#uses=1] %tmp9 = trunc i32 %tmp8 to i16, !dbg !1026 ; <i16> [#uses=1...

...pos, align 4 %tmp1044 = sub i32 %tmp842, %tmp943 %tmp1145 = icmp slt i32 %tmp1044, 512 br i1 %tmp1145, label %bb, label %bb13 bb: %tmp2.rle = phi i32 [ %tmp842, %entry ], [ %tmp8, %bb ] %tmp3 = shl i32 %tmp2.rle, 1 store i32 %tmp3, i32* @yybuflen, align 4 %tmp5 = load i8** @yybuf, align 4 %tmp6 = tail call i8* @realloc( i8* %tmp5, i32 %tmp3 ) store i8* %tmp6, i8** @yybuf, align 4 %tmp8 = load i32* @yybuflen, align 4 %tmp9 = load i32* @yypos, align 4 %tmp10 = sub i32 %tmp8, %tmp9 %tmp11 = icmp slt i32 %tmp10, 512 br i1 %tmp11, label %bb, label %bb13 bb13: %tmp15 = load %struct._IO_...

Hi, For a call like this, %tmp6 = call i32 (...)* bitcast (i32 (i8*, i8, i8**)* @ssplit to i32 (...)*)(i8* %tmp599, i32 46, i8** %domainv3) nounwind ; <i32> does the 2nd argument get zero extended or sign extended? Thanks, Arushi -------------- next part -------------- An HTML attachment was scrubbed... URL: <http://li...

...b, struct bar *addr) { struct bar tmp; tmp.a = a; tmp.b = b; *addr = tmp; } * Solution A: Replicate SDAG * Note: (#) is the size of the virtual register. - Translation: arg1(32) = copy R0 arg2(32) = copy R1 addr(32) = copy R2 a(16) = truncate arg1(32) b(16) = truncate arg2(32) tmp5(16), tmp6(16) = merge_value a(16), b(16) store tmp5(16), addr(32), 0 store tmp6(16), addr(32), 4 - Legalization: arg1(32) = copy R0 arg2(32) = copy R1 addr(32) = copy R2 tmp5(16) = extract_subreg a(32), 0 tmp6(16) = extract_subreg b(32), 0 store tmp5(16), addr(32), 0 store tmp6(16), addr(32), 4 * Solution...

...2*] ; <[2 x i32*]*> [#uses=2] %tmp1 = getelementptr [2 x i32*]* %x, i32 0, i32 1 ; <i32**> [#uses=1] %tmp23 = ptrtoint i32** %tmp1 to i32 ; <i32> [#uses=1] %x45 = ptrtoint [2 x i32*]* %x to i32 ; <i32> [#uses=1] %tmp6 = sub i32 %tmp23, %x45 ; <i32> [#uses=1] %size = getelementptr i32** null, i32 1 ; <i32**> [#uses=1] %sizeI = ptrtoint i32** %size to i32 ; <i32> [#uses=1] %tmp7 = ashr i32 %tmp6, %sizeI ; <i32> [#uses=1]...

...ionID == sessionU01[i,],select=c(timelineMSEC,X,Y)) userSubset x<-as.numeric(userSubset$X) y<-as.numeric(userSubset$Y) scatter3d(x,y,userSubset$timeline,xlim = c(0,1280), ylim = c(0,1024), zlim=c(0,1800000),type="h",main=sessionU01[i,],sub=sessionU01[i,]) tmp6=rep(".ps") tmp7=paste(sessionU01[i,],tmp6,sep="") tmp7 rgl.postscript(tmp7,"ps",drawText=FALSE) #pdf(file=tmp7) #dev.print(file=tmp7, device=pdf, width=600) #dev.off(2) }

...> entry.header.loop.end: ; preds = %cond.then.i201.i, %phi.exit138.i > %cond.i204.i = phi float [ %tmp43.i200.i, %cond.then.i201.i ], [ %tmp38.i194.i, %phi.exit138.i ] > %arrayidx82.i = getelementptr float addrspace(1)* %5, i64 %8 > %tmp85.i = fmul float %tmp63.i, %cond.i204.i > %tmp88.i = fmul float %tmp9.i, %cond.i135.i > %tmp89.i = fsub float %tmp85.i, %tmp88.i > store float %tmp89.i, float addrspace(1)* %arrayidx82.i, align 4 > %inc = add i32 %7, 1 > %exitcond = icmp eq i32 %inc, %local_size_0 > br i1 %exitcond, label %exit, l...

...(){ entry: %n = alloca i32 %f = alloca i32 %i = alloca i32 %zero = alloca i32 %inc = alloca i32 store i32 5, i32* %n store i32 1, i32* %f store i32 1, i32* %i store i32 0 , i32* %zero store i32 1 , i32* %inc %tmp7 = load i32* %n %tmp8 = load i32* %zero %tmp6 = icmp sgt i32 %tmp7, %tmp8 br i1 %tmp6, label %then4, label %else12 then4: %tmp14 = load i32* %i %tmp16 = load i32* %n %tmp18 = load i32* %inc %tmp15 = add i32 %tmp16, %tmp18 %tmp13 = icmp slt i32 %tmp14, %tmp15 br i1 %tmp13, label %then11, label %else12 then11: %tm...

...k: %.str3 = getelementptr [8 x i8]* @.str2, i64 0, i64 0 ; <i8*> [#uses=1] %.str4 = getelementptr [8 x i8]* @.str1, i64 0, i64 0 ; <i8*> [#uses=1] %tmp5 = call i8* @strcat( i8* %.str3, i8* %.str4 ) ; <i8*> [#uses=1] %tmp6 = call i32 @puts( i8* %tmp5 ) ; <i32> [#uses=0] %.str8 = getelementptr [21 x i8]* @.str7, i64 0, i64 0 ; <i8*> [#uses=1] %tmp9 = call i32 @puts( i8* %.str8 ) ; <i32> [#uses=0] ret i32 0 } After compilation I see next(without...

Hello everybody, I have stumbled upon a test case (the attached module is a slightly reduced version) that shows extremely reduced performance on linux compared to windows when executed using LLVM's JIT. We narrowed the problem down to the actual code being generated, the source IR on both systems is the same. Try compiling the attached module: llc -O3 -filetype=asm -o BAD.s BAD.ll Under

...iple = "x86_64-unknown-linux-gnu" ; Function Attrs: nounwind readonly define i32 @get32Bits(i8* inreg nocapture readonly %x_arg) #0 { %tmp1 = getelementptr inbounds i8* %x_arg, i64 3 %tmp2 = load i8* %tmp1, align 1 %tmp3 = zext i8 %tmp2 to i32 %tmp4 = shl nuw nsw i32 %tmp3, 24 %tmp6 = getelementptr inbounds i8* %x_arg, i64 2 %tmp7 = load i8* %tmp6, align 1 %tmp8 = zext i8 %tmp7 to i32 %tmp9 = shl nuw nsw i32 %tmp8, 16 %tmp10 = or i32 %tmp9, %tmp4 %tmp12 = getelementptr inbounds i8* %x_arg, i64 1 %tmp13 = load i8* %tmp12, align 1 %tmp14 = zext i8 %tmp13 to i32 %...

...: (#) is the size of the virtual register. >> >> >> - Translation: >> >> >> >> >> arg1(32) = copy R0 >> arg2(32) = copy R1 >> addr(32) = copy R2 >> a(16) = truncate arg1(32) >> b(16) = truncate arg2(32) >> tmp5(16), tmp6(16) = merge_value a(16), b(16) >> store tmp5(16), addr(32), 0 >> store tmp6(16), addr(32), 4 >> >> >> - Legalization: >> >> >> >> arg1(32) = copy R0 >> arg2(32) = copy R1 >> addr(32) = copy R2 >> tmp5(16) = extract_subreg...

...nicity of heuristic* What I'm trying to say here is the greedy algorithms work best when the heuristic they are computing is monotonic. Consider this: if (a) { tmp1 = *b; tmp2 = *c; tmp3 = tmp1 + tmp2; *d = tmp3; } else { tmp4 = *b; tmp5 = *c; tmp6 = tmp4 + tmp5; *e = tmp6; } If we proceed sequentially from the bottom of these blocks, trying to determine if sinking them is worthwhile: Step 1: [*e = tmp6], [*d = tmp3] - This is the same operation, a store, but it requires two PHIs - one for (e,d) and one for (tmp6, tmp3). - Thi...

Thanks, Sanjay, that makes sense. The opportunity for improving instcombining splat sounds promising. Another question about shuffle simplification. This is a testcase from test/Transforms/InstCombine/vec_shuffle.ll: define <4 x i32> @test10(<4 x i32> %tmp5) nounwind { %tmp6 = shufflevector <4 x i32> %tmp5, <4 x i32> undef, <4 x i32> <i32 1, i32 undef, i32 undef, i32 undef> %tmp7 = shufflevector <4 x i32> %tmp6, <4 x i32> undef, <4 x i32> zeroinitializer ret <4 x i32> %tmp7 } opt –instcombine will combine to: defin...