c++ - clang 无法优化掉仅在 main() 中使用的全局变量？

Question

如果我将此 c++ 程序插入 clang(3.7 版)

///*
#include "stdio.h"
#include "stdint.h"
//extern int printf(const unsigned char*, ...);


extern "C" void __cxa_pure_virtual() { }

struct A
{
    virtual void foo() = 0;
};

struct B : A
{
    uint32_t x;
    B(int x) : x(x) { }
    virtual void foo()
    {
        printf("This is a test %d\n", x);
    }
};
//*/
uint64_t thing = 0;
float other = 10.0f;
B b(12345);
int main()
{

    thing++;
    A* a = &b;
    other *= 3.14159f;
    a->foo();
}

然后用clang -emit-llvm main.cpp -fno-rtti -O3 -S编译，然后我得到以下字节码:

; ModuleID = 'main.cpp'
target datalayout = "e-m:e-p:32:32-f64:32:64-f80:32-n8:16:32-S128"
target triple = "i686-pc-linux-gnu"

%struct.B = type { %struct.A, i32 }
%struct.A = type { i32 (...)** }

$_ZN1B3fooEv = comdat any

$_ZTV1B = comdat any

@thing = global i64 0, align 8
@other = global float 1.000000e+01, align 4
@b = global %struct.B { %struct.A { i32 (...)** bitcast (i8** getelementptr inbounds ([3 x i8*], [3 x i8*]* @_ZTV1B, i64 0, i64 2) to i32 (...)**) }, i32 12345 }, align 4
@_ZTV1B = linkonce_odr unnamed_addr constant [3 x i8*] [i8* null, i8* null, i8* bitcast (void (%struct.B*)* @_ZN1B3fooEv to i8*)], comdat, align 4
@.str = private unnamed_addr constant [19 x i8] c"This is a test %d\0A\00", align 1
@llvm.global_ctors = appending global [0 x { i32, void ()*, i8* }] zeroinitializer

; Function Attrs: nounwind readnone
define void @__cxa_pure_virtual() #0 {
entry:
  ret void
}

define i32 @main() #1 {
entry:
  %0 = load i64, i64* @thing, align 8, !tbaa !1
  %inc = add i64 %0, 1
  store i64 %inc, i64* @thing, align 8, !tbaa !1
  %1 = load float, float* @other, align 4, !tbaa !5
  %mul = fmul float %1, 0x400921FA00000000
  store float %mul, float* @other, align 4, !tbaa !5
  %vtable = load void (%struct.A*)**, void (%struct.A*)*** bitcast (%struct.B* @b to void (%struct.A*)***), align 4, !tbaa !7
  %2 = load void (%struct.A*)*, void (%struct.A*)** %vtable, align 4
  tail call void %2(%struct.A* getelementptr inbounds (%struct.B, %struct.B* @b, i32 0, i32 0))
  ret i32 0
}

; Function Attrs: nounwind
define linkonce_odr void @_ZN1B3fooEv(%struct.B* nocapture readonly %this) unnamed_addr #2 comdat align 2 {
entry:
  %x = getelementptr inbounds %struct.B, %struct.B* %this, i32 0, i32 1
  %0 = load i32, i32* %x, align 4, !tbaa !9
  %call = tail call i32 (i8*, ...) @printf(i8* getelementptr inbounds ([19 x i8], [19 x i8]* @.str, i32 0, i32 0), i32 %0)
  ret void
}

; Function Attrs: nounwind
declare i32 @printf(i8* nocapture readonly, ...) #2

attributes #0 = { nounwind readnone "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="pentium4" "target-features"="+sse,+sse2" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #1 = { "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="pentium4" "target-features"="+sse,+sse2" "unsafe-fp-math"="false" "use-soft-float"="false" }
attributes #2 = { nounwind "disable-tail-calls"="false" "less-precise-fpmad"="false" "no-frame-pointer-elim"="false" "no-infs-fp-math"="false" "no-nans-fp-math"="false" "stack-protector-buffer-size"="8" "target-cpu"="pentium4" "target-features"="+sse,+sse2" "unsafe-fp-math"="false" "use-soft-float"="false" }

!llvm.ident = !{!0}

!0 = !{!"clang version 3.7.1 "}
!1 = !{!2, !2, i64 0}
!2 = !{!"long long", !3, i64 0}
!3 = !{!"omnipotent char", !4, i64 0}
!4 = !{!"Simple C/C++ TBAA"}
!5 = !{!6, !6, i64 0}
!6 = !{!"float", !3, i64 0}
!7 = !{!8, !8, i64 0}
!8 = !{!"vtable pointer", !4, i64 0}
!9 = !{!10, !11, i64 4}
!10 = !{!"_ZTS1B", !11, i64 4}
!11 = !{!"int", !3, i64 0}

如果你看一下主函数，我有两个无用的变量。当然，我会递增一个，然后对另一个进行一些乘法运算，但我从来没有使用过它们中的值。

但是如果您查看字节码的输出，它看起来仍然在做无用的数学运算。

这只是我的问题还是这是一个错误？

Answer 1

那些变量是全局范围内的变量。编译器根本无法确定这些变量是否可以在其他翻译单元中声明和引用。

如果任何现代 C++ 编译器足够复杂，能够确定执行流程无法以定义的方式转义此翻译单元，那么我会感到惊讶，因此可以安全地优化掉此翻译单元中未使用的全局变量.