llvm 代码优化选项不起作用

Question

我正在阅读有关 LLVM 代码优化的信息。我尝试在一些示例上应用 opt 命令选项，但它们没有任何效果。例如。下面是一个名为 deadCode.cpp 的 c++ 代码：

 #include<stdio.h>

int square(int x){
return x*x;
}

int main(){

    int a=2;
    int b=3;
    int c=4;

    int result =square(a);
    printf("%d\n",b);

}

我使用 clang 生成了 LLVM IR，如下所示：

clang -emit-llvm -S deadCode.cpp -o deadCodeBefore

结果文件deadCodeBefore内容为：

    ; ModuleID = 'deadCode.cpp'
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-pc-linux-gnu"

@.str = private unnamed_addr constant [4 x i8] c"%d\0A\00", align 1

; Function Attrs: nounwind uwtable
define i32 @_Z6squarei(i32 %x) #0 {
  %1 = alloca i32, align 4
  store i32 %x, i32* %1, align 4
  %2 = load i32, i32* %1, align 4
  %3 = load i32, i32* %1, align 4
  %4 = mul nsw i32 %2, %3
  ret i32 %4
}

; Function Attrs: norecurse uwtable
define i32 @main() #1 {
  %a = alloca i32, align 4
  %b = alloca i32, align 4
  %c = alloca i32, align 4
  %result = alloca i32, align 4
  store i32 2, i32* %a, align 4
  store i32 3, i32* %b, align 4
  store i32 4, i32* %c, align 4
  %1 = load i32, i32* %a, align 4
  %2 = call i32 @_Z6squarei(i32 %1)
  store i32 %2, i32* %result, align 4
  %3 = load i32, i32* %b, align 4
  %4 = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([4 x i8], [4 x i8]* @.str, i32 0, i32 0), i32 %3)
  ret i32 0
}

declare i32 @printf(i8*, ...) #2

attributes #0 = { nounwind uwtable "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-nans-fp-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+fxsr,+mmx,+sse,+sse2" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #1 = { norecurse uwtable "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-nans-fp-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+fxsr,+mmx,+sse,+sse2" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #2 = { "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-nans-fp-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+fxsr,+mmx,+sse,+sse2" "unsafe-fp-math"="false" "use-soft-float"="false" }

!llvm.ident = !{!0}

!0 = !{!"clang version 3.8.0-2ubuntu4 (tags/RELEASE_380/final)"}

我使用的优化命令：

选择 -S -adce deadCodeBefore -o deadCodeAfter1

当我读到它应该删除对 square 函数的调用以及 c 变量的声明，因为它们没有效果。但结果是一样的。这里是 deadCodeAfter1，与 deadCodeBefore 相同：

 ; ModuleID = 'deadCodeBefore'
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-pc-linux-gnu"

@.str = private unnamed_addr constant [4 x i8] c"%d\0A\00", align 1

; Function Attrs: nounwind uwtable
define i32 @_Z6squarei(i32 %x) #0 {
  %1 = alloca i32, align 4
  store i32 %x, i32* %1, align 4
  %2 = load i32, i32* %1, align 4
  %3 = load i32, i32* %1, align 4
  %4 = mul nsw i32 %2, %3
  ret i32 %4
}

; Function Attrs: norecurse uwtable
define i32 @main() #1 {
  %a = alloca i32, align 4
  %b = alloca i32, align 4
  %c = alloca i32, align 4
  %result = alloca i32, align 4
  store i32 2, i32* %a, align 4
  store i32 3, i32* %b, align 4
  store i32 4, i32* %c, align 4
  %1 = load i32, i32* %a, align 4
  %2 = call i32 @_Z6squarei(i32 %1)
  store i32 %2, i32* %result, align 4
  %3 = load i32, i32* %b, align 4
  %4 = call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([4 x i8], [4 x i8]* @.str, i32 0, i32 0), i32 %3)
  ret i32 0
}

declare i32 @printf(i8*, ...) #2

attributes #0 = { nounwind uwtable "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-nans-fp-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+fxsr,+mmx,+sse,+sse2" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #1 = { norecurse uwtable "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-nans-fp-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+fxsr,+mmx,+sse,+sse2" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #2 = { "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-nans-fp-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="x86-64" "target-features"="+fxsr,+mmx,+sse,+sse2" "unsafe-fp-math"="false" "use-soft-float"="false" }

!llvm.ident = !{!0}

!0 = !{!"clang version 3.8.0-2ubuntu4 (tags/RELEASE_380/final)"}

Answer 1

因为它完全按照它应该做的那样做。它在 IR 中检查一条指令是否正在被其他指令使用。如果不仅如此，它将删除它。例如，在您的代码中，store 指令 store i32 2, i32* %a, align 4 中使用了变量 %a (%a = alloca i32, align 4) 的声明

如果您刚刚声明了一个变量并且没有为其分配任何值，那么adce pass 将消除它。你可以通过声明int e; 之类的变量并对其运行优化来看到这一点。

LLVM 中的传递通常依赖于其他传递的输出才能有效。单个传递本身可能不会为您提供您可能期望它提供的结果。