search for: tmp53

...il call float @llvm.log.f32(float %tmp40.i) nounwind > %tmp45.i = fmul float %tmp33.i, %tmp33.i > %tmp47.i = fdiv float %tmp45.i, 2.000000e+00 > %tmp48.i = fadd float %tmp27.i, %tmp47.i > %tmp50.i = fmul float %tmp48.i, %tmp21.i > %tmp51.i = fadd float %call41.i, %tmp50.i > %tmp53.i = fdiv float %tmp51.i, %tmp37.i > %tmp56.i = fsub float %tmp53.i, %tmp37.i > %tmp59.i = fsub float -0.000000e+00, %tmp27.i > %tmp61.i = fmul float %tmp21.i, %tmp59.i > %call62.i = tail call float @llvm.exp.f32(float %tmp61.i) nounwind > %tmp63.i = fmul float %tmp9.i, %call62.i...

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

...tions, and is causing a problem with MachineBranchFolding. The problem is this, I have two branches of a switch statement that are identical, except for the size of the store. Here is some cut-down LLVM-IR to showcase the issue: switch.case: ; preds = %if.end %tmp53 = extractelement <4 x i32> %format, i32 1 ; <i32> [#uses=1] switch i32 %tmp53, label %if.then [ i32 1, label %switch.case55 i32 2, label %switch.case61 ] switch.case55: ; preds = %switch.case %arrayidx = getelementptr i8 addrspace(1)* %co...

...is causing a problem with MachineBranchFolding. The problem is this, I have two branches of a switch statement that are identical, except for the size of the store. Here is some cut-down LLVM-IR to showcase the issue: > switch.case: ; preds = %if.end > %tmp53 = extractelement <4 x i32> %format, i32 1 ; <i32> [#uses=1] > switch i32 %tmp53, label %if.then [ > i32 1, label %switch.case55 > i32 2, label %switch.case61 > ] > switch.case55: ; preds = %switch.case > %arrayidx = gete...

...ualZero12: br label %l1 StringEqualZero12: %tmp50 = load i32* @yybegin, align 4 %tmp51 = load i32* @yyend, align 4 call void @yyDo(void (i8*, i32)* @yy_13_body, i32 %tmp50, i32 %tmp51) %yypos11 = load i32* @yypos %yythunkpos11 = load i32* @yythunkpos %tmp52 = call i32 @yymatchChar(i8 102) %tmp53 = icmp ne i32 %tmp102, 0 br i1 %tmp53, label %StringNotEqualZero13, label %StringEqualZero13 StringNotEqualZero13: br label %l12 StringEqualZero13: call i32 @yyText(i32 %yybegin, i32 %yyend) %tmp54 = ptrtoint i8* @str0 to i32 %tmp55 = icmp eq i32 %tmp0, 0 br i1 %tmp55, label %PredicateEqualZe...