虽然其他人已经解释了问题的原因是什么,但我认为“更好”的解决方案应该是用 if 编写条件:
int x1 = 10, x2=20, y1=132, y2=12, minx, miny, maxx, maxy;
if (x1<=x2)
{
minx=x1;
maxx=x2;
}
else
{
minx=x2;
maxx=x1;
}
if (y1<=y2)
{
miny=y1;
maxy=y2;
}
else
{
miny=y2;
maxy=y1;
}
是的,它长了几行,但它也更容易阅读和清楚到底发生了什么(如果你需要在调试器中单步执行它,你可以很容易地看到它的走向)。
任何现代编译器都应该能够将其中任何一个转换为相当有效的条件赋值,可以很好地避免分支(因此是“错误的分支预测”)。
我准备了一个小测试,我用它编译
g++ -O2 -fno-inline -S -Wall ifs.cpp
这是源代码(我必须将其设为参数以确保编译器不只是直接计算正确的值而只是做mov $12,%rdx
,而是实际上做了比较并决定更大):
void mine(int x1, int x2, int y1, int y2)
{
int minx, miny, maxx, maxy;
if (x1<=x2)
{
minx=x1;
maxx=x2;
}
else
{
minx=x2;
maxx=x1;
}
if (y1<=y2)
{
miny=y1;
maxy=y2;
}
else
{
miny=y2;
maxy=y1;
}
cout<<"minx="<<minx<<"\n";
cout<<"maxx="<<maxx<<"\n";
cout<<"miny="<<miny<<"\n";
cout<<"maxy="<<maxy<<"\n";
}
void original(int x1, int x2, int y1, int y2)
{
int minx, miny, maxx, maxy;
x1<=x2 ? (minx=x1,maxx=x2) : (minx=x2,maxx=x1);
y1<=y2 ? (miny=y1,maxy=y2) : (miny=y2,maxy=y1);
cout<<"minx="<<minx<<"\n";
cout<<"maxx="<<maxx<<"\n";
cout<<"miny="<<miny<<"\n";
cout<<"maxy="<<maxy<<"\n";
}
void romano(int x1, int x2, int y1, int y2)
{
int minx, miny, maxx, maxy;
minx = ((x1 <= x2) ? x1 : x2);
maxx = ((x1 <= x2) ? x2 : x1);
miny = ((y1 <= y2) ? y1 : y2);
maxy = ((y1 <= y2) ? y2 : y1);
cout<<"minx="<<minx<<"\n";
cout<<"maxx="<<maxx<<"\n";
cout<<"miny="<<miny<<"\n";
cout<<"maxy="<<maxy<<"\n";
}
int main()
{
int x1=10, x2=20, y1=132, y2=12;
mine(x1, x2, y1, y2);
original(x1, x2, y1, y2);
romano(x1, x2, y1, y2);
return 0;
}
生成的代码如下所示:
_Z4mineiiii:
.LFB966:
.cfi_startproc
movq %rbx, -32(%rsp)
movq %rbp, -24(%rsp)
movl %ecx, %ebx
movq %r12, -16(%rsp)
movq %r13, -8(%rsp)
movl %esi, %r12d
subq $40, %rsp
movl %edi, %r13d
cmpl %esi, %edi
movl %edx, %ebp
cmovg %edi, %r12d
cmovg %esi, %r13d
movl $_ZSt4cout, %edi
cmpl %ecx, %edx
movl $.LC0, %esi
cmovg %edx, %ebx
cmovg %ecx, %ebp
.... removed actual printout code that is quite long and unwieldy...
_Z8originaliiii:
movq %rbx, -32(%rsp)
movq %rbp, -24(%rsp)
movl %ecx, %ebx
movq %r12, -16(%rsp)
movq %r13, -8(%rsp)
movl %esi, %r12d
subq $40, %rsp
movl %edi, %r13d
cmpl %esi, %edi
movl %edx, %ebp
cmovg %edi, %r12d
cmovg %esi, %r13d
movl $_ZSt4cout, %edi
cmpl %ecx, %edx
movl $.LC0, %esi
cmovg %edx, %ebx
cmovg %ecx, %ebp
... print code goes here ...
_Z6romanoiiii:
movq %rbx, -32(%rsp)
movq %rbp, -24(%rsp)
movl %edx, %ebx
movq %r12, -16(%rsp)
movq %r13, -8(%rsp)
movl %edi, %r12d
subq $40, %rsp
movl %esi, %r13d
cmpl %esi, %edi
movl %ecx, %ebp
cmovle %edi, %r13d
cmovle %esi, %r12d
movl $_ZSt4cout, %edi
cmpl %ecx, %edx
movl $.LC0, %esi
cmovle %edx, %ebp
cmovle %ecx, %ebx
... printout code here....
如您所见,mine
andoriginal
是相同的,并且romano
使用稍微不同的寄存器和不同形式的cmov
,但除此之外它们在相同数量的指令中执行相同的操作。