LLVM opt mem2reg has no effect

问题:

I am currently playing around with LLVM and am trying to write a few optimizers to familiarize myself with opt and clang. I wrote a test.c file that is as follow:

int foo(int aa, int bb, int cc){
    int sum = aa + bb;
    return sum/cc;
}

I compiled the source code and generated 2 .ll files, one unoptimized and one with mem2reg optimizer pass:

clang -emit-llvm -O0 -c test.c -o test.bc
llvm-dis test.bc
opt -mem2reg -S test.ll -o test-mem2reg.ll

Both .ll files gave me the following output:

ModuleID = 'test.bc'
source_filename = "test.c"
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"

; Function Attrs: noinline nounwind optnone uwtable
define i32 @foo(i32 %aa, i32 %bb, i32 %cc) #0 {
entry:
  %aa.addr = alloca i32, align 4
  %bb.addr = alloca i32, align 4
  %cc.addr = alloca i32, align 4
  %sum = alloca i32, align 4
  store i32 %aa, i32* %aa.addr, align 4
  store i32 %bb, i32* %bb.addr, align 4
  store i32 %cc, i32* %cc.addr, align 4
  %0 = load i32, i32* %aa.addr, align 4
  %1 = load i32, i32* %bb.addr, align 4
  %add = add nsw i32 %0, %1
  store i32 %add, i32* %sum, align 4
  %2 = load i32, i32* %sum, align 4
  %3 = load i32, i32* %cc.addr, align 4
  %div = sdiv i32 %2, %3
  ret i32 %div
}

attributes #0 = { noinline nounwind optnone uwtable "correctly-rounded-divide-sqrt-fp-math"="false" "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="true" "no-frame-pointer-elim-non-leaf" "no-infs-fp-math"="false" "no-jump-tables"="false" "no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" "no-trapping-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+fxsr,+mmx,+sse,+sse2,+x87" "unsafe-fp-math"="false" "use-soft-float"="false" }

!llvm.module.flags = !{!0}
!llvm.ident = !{!1}

!0 = !{i32 1, !"wchar_size", i32 4}
!1 = !{!"clang version 6.0.0 (trunk 314616)"}

So it seems that my mem2reg pass didn't work! What would be the problem?

回答1:

Recently, when compiled with -O0, clang started to add optnone attribute to each function, which prevents further optimizations afterwards including mem2reg pass. To prevent that, add -Xclang -disable-O0-optnone to clang.