__builtin_expect详解

转自：http://hi.baidu.com/lammy/blog/item/bc5e3d4e869073c3d1c86a89.html

在GTK+2.0源码中有很多这样的宏：G_LIKELY和G_UNLIKELY。比如下面这段代码：

if (G_LIKELY (acat == 1))    
/* allocate through magazine layer */
   
{
     
ThreadMemory *tmem = thread_memory_from_self();
     
guint ix = SLAB_INDEX (allocator, chunk_size);
     
if (G_UNLIKELY (thread_memory_magazine1_is_empty (tmem, ix)))
       
{
         
thread_memory_swap_magazines (tmem, ix);
         
if (G_UNLIKELY (thread_memory_magazine1_is_empty (tmem, ix)))
           
thread_memory_magazine1_reload (tmem, ix);
       
}
     
mem = thread_memory_magazine1_alloc (tmem, ix);
   
}

在源码中，宏G_LIKELY和G_UNLIKELY 是这么定义的：

#define G_LIKELY(expr) (__builtin_expect (_G_BOOLEAN_EXPR(expr), 1))
#define G_UNLIKELY(expr) (__builtin_expect (_G_BOOLEAN_EXPR(expr), 0))

宏_G_BOOLEAN_EXPR的作用是把expr转换为0和1，即真假两种。要理解宏G_LIKELY和G_UNLIKELY ，很明显必须理解__builtin_expect。__builtin_expect是GCC(version>=2.9)引进的宏，其作用就是帮助编译器判断条件跳转的预期值，避免跳转造成时间乱费。拿上面的代码来说：

if (G_LIKELY (acat == 1))     //表示大多数情况下if里面是真，程序大多数直接执行if里面的程序

而

if (G_UNLIKELY (thread_memory_magazine1_is_empty (tmem, ix)))//表示大多数情况if里面为假，程序大多数直接执行else里面的程序

可能大家看到还是一头雾水，看下面一段就会明白其中的乐趣啦；

//test_builtin_expect.c
#define LIKELY(x) __builtin_expect(!!(x), 1)
#define UNLIKELY(x) __builtin_expect(!!(x), 0)

int test_likely(int x)
{
if(LIKELY(x))
{
  
x = 5;
}
else
{
  
x = 6;
}
  
return x;
}

int test_unlikely(int x)
{
if(UNLIKELY(x))
{
  
x = 5;
}
else
{
  
x = 6;
}
  
return x;
}

[lammy@localhost test_builtin_expect]$ gcc -fprofile-arcs -O2 -c test_builtin_expect.c
[lammy@localhost test_builtin_expect]$ objdump -d test_builtin_expect.o

test_builtin_expect.o:    
file format elf32-i386

Disassembly of section .text:

00000000 <test_likely>:
  
0: 55                  
push  
%ebp
  
1: 89 e5               
mov   
%esp,%ebp
  
3: 8b 45 08            
mov   
0x8(%ebp),%eax
  
6: 83 05 38 00 00 00 01
addl  
$0x1,0x38
  
d: 83 15 3c 00 00 00 00
adcl  
$0x0,0x3c
14: 85 c0               
test  
%eax,%eax
16: 74 15               
je    
2d <test_likely+0x2d>//主要看这里
18: 83 05 40 00 00 00 01
addl  
$0x1,0x40
1f: b8 05 00 00 00      
mov   
$0x5,%eax
24: 83 15 44 00 00 00 00
adcl  
$0x0,0x44
2b: 5d                  
pop   
%ebp
2c: c3                  
ret   
2d: 83 05 48 00 00 00 01
addl  
$0x1,0x48
34: b8 06 00 00 00      
mov   
$0x6,%eax
39: 83 15 4c 00 00 00 00
adcl  
$0x0,0x4c
40: 5d                  
pop   
%ebp
41: c3                  
ret   
42: 8d b4 26 00 00 00 00
lea   
0x0(%esi,%eiz,1),%esi
49: 8d bc 27 00 00 00 00
lea   
0x0(%edi,%eiz,1),%edi

00000050 <test_unlikely>:
50: 55                  
push  
%ebp
51: 89 e5               
mov   
%esp,%ebp
53: 8b 55 08            
mov   
0x8(%ebp),%edx
56: 83 05 20 00 00 00 01
addl  
$0x1,0x20
5d: 83 15 24 00 00 00 00
adcl  
$0x0,0x24
64: 85 d2               
test  
%edx,%edx
66: 75 15               
jne   
7d <test_unlikely+0x2d>//主要看这里

68: 83 05 30 00 00 00 01
addl  
$0x1,0x30
6f: b8 06 00 00 00      
mov   
$0x6,%eax
74: 83 15 34 00 00 00 00
adcl  
$0x0,0x34
7b: 5d                  
pop   
%ebp
7c: c3                  
ret   
7d: 83 05 28 00 00 00 01
addl  
$0x1,0x28
84: b8 05 00 00 00      
mov   
$0x5,%eax
89: 83 15 2c 00 00 00 00
adcl  
$0x0,0x2c
90: 5d                  
pop   
%ebp
91: c3                  
ret   
92: 8d b4 26 00 00 00 00
lea   
0x0(%esi,%eiz,1),%esi
99: 8d bc 27 00 00 00 00
lea   
0x0(%edi,%eiz,1),%edi

000000a0 <_GLOBAL__I_65535_0_test_likely>:
a0: 55                  
push  
%ebp
a1: 89 e5               
mov   
%esp,%ebp
a3: 83 ec 08            
sub   
$0x8,%esp
a6: c7 04 24 00 00 00 00
movl  
$0x0,(%esp)
ad: e8 fc ff ff ff      
call  
ae <_GLOBAL__I_65535_0_test_likely+0xe>
b2: c9                  
leave
b3: c3                  
ret   
[lammy@localhost test_builtin_expect]$

两个函数编译生成的汇编语句所使用到的跳转指令不一样，仔细分析下会发现__builtin_expect实际上是为了满足在大多数情况不执行跳转指令，所以__builtin_expect仅仅是告诉编译器优化，并没有改变其对真值的判断。

这种用法在linux内核中也经常用到，国外也有一篇相关的文章，大家不妨看看：http://kernelnewbies.org/FAQ/LikelyUnlikely

不知大家注意到没有，我在生产汇编时用的是gcc -fprofile-arcs -O2 -c test_builtin_expect.c，而不是gcc -O2 -c test_builtin_expect.c，具体可以参考http://gcc.gnu.org/onlinedocs/gcc/Other-Builtins.html。