现代C ++编译器是否内联了仅被调用一次的函数？

Question

例如，说我的头文件是：

class A
{
    void Complicated();
}

和我的源文件

void A::Complicated()
{
    ...really long function...
}

我可以将源文件拆分为

void DoInitialStuff(pass necessary vars by ref or value)
{
    ...
}
void HandleCaseA(pass necessary vars by ref or value)
{
    ...
}
void HandleCaseB(pass necessary vars by ref or value)
{
    ...
}
void FinishUp(pass necessary vars by ref or value)
{
    ...
}
void A::Complicated()
{
    ...
    DoInitialStuff(...);
    switch ...
        HandleCaseA(...)
        HandleCaseB(...)
    ...
    FinishUp(...)
}

是否完全出于可读性考虑，而又不担心会对性能产生影响？

Answer 1

您应该标记函数，static以便编译器知道它们在该翻译单元中是本地的。

没有static编译器就不能假设（除非LTO / WPA）该函数仅被调用一次，因此不太可能内联它。

使用“ LLVM试用”页面进行演示。

就是说，首先要针对可读性的代码进行微优化（这种调整就是微优化），然后再执行性能指标。

例：

#include <cstdio>

static void foo(int i) {
  int m = i % 3;
  printf("%d %d", i, m);
}

int main(int argc, char* argv[]) {
  for (int i = 0; i != argc; ++i) {
    foo(i);
  }
}

与产生static：

; ModuleID = '/tmp/webcompile/_27689_0.bc'
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
target triple = "x86_64-unknown-linux-gnu"

@.str = private constant [6 x i8] c"%d %d\00"     ; <[6 x i8]*> [#uses=1]

define i32 @main(i32 %argc, i8** nocapture %argv) nounwind {
entry:
  %cmp4 = icmp eq i32 %argc, 0                    ; <i1> [#uses=1]
  br i1 %cmp4, label %for.end, label %for.body

for.body:                                         ; preds = %for.body, %entry
  %0 = phi i32 [ %inc, %for.body ], [ 0, %entry ] ; <i32> [#uses=3]
  %rem.i = srem i32 %0, 3                         ; <i32> [#uses=1]
  %call.i = tail call i32 (i8*, ...)* @printf(i8* getelementptr inbounds ([6 x i8]* @.str, i64 0, i64 0), i32 %0, i32 %rem.i) nounwind ; <i32> [#uses=0]
  %inc = add nsw i32 %0, 1                        ; <i32> [#uses=2]
  %exitcond = icmp eq i32 %inc, %argc             ; <i1> [#uses=1]
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body, %entry
  ret i32 0
}

declare i32 @printf(i8* nocapture, ...) nounwind

没有static：

; ModuleID = '/tmp/webcompile/_27859_0.bc'
target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64"
target triple = "x86_64-unknown-linux-gnu"

@.str = private constant [6 x i8] c"%d %d\00"     ; <[6 x i8]*> [#uses=1]

define void @foo(int)(i32 %i) nounwind {
entry:
  %rem = srem i32 %i, 3                           ; <i32> [#uses=1]
  %call = tail call i32 (i8*, ...)* @printf(i8* getelementptr inbounds ([6 x i8]* @.str, i64 0, i64 0), i32 %i, i32 %rem) ; <i32> [#uses=0]
  ret void
}

declare i32 @printf(i8* nocapture, ...) nounwind

define i32 @main(i32 %argc, i8** nocapture %argv) nounwind {
entry:
  %cmp4 = icmp eq i32 %argc, 0                    ; <i1> [#uses=1]
  br i1 %cmp4, label %for.end, label %for.body

for.body:                                         ; preds = %for.body, %entry
  %0 = phi i32 [ %inc, %for.body ], [ 0, %entry ] ; <i32> [#uses=3]
  %rem.i = srem i32 %0, 3                         ; <i32> [#uses=1]
  %call.i = tail call i32 (i8*, ...)* @printf(i8* getelementptr inbounds ([6 x i8]* @.str, i64 0, i64 0), i32 %0, i32 %rem.i) nounwind ; <i32> [#uses=0]
  %inc = add nsw i32 %0, 1                        ; <i32> [#uses=2]
  %exitcond = icmp eq i32 %inc, %argc             ; <i1> [#uses=1]
  br i1 %exitcond, label %for.end, label %for.body

for.end:                                          ; preds = %for.body, %entry
  ret i32 0
}