Hi,
The following C code call __builtin_expect() is to decalre that
the branch condition is more probable.
int sgn(int x, int y)
{
int s;
if (__builtin_expect(x < 0, 1))
s = -1;
else
s = 1;
return s;
}
Compiled by gcc, we can get its asm code as follows:
1 _sgn:
2 pushl %ebp
3 movl %esp, %ebp
4 subl $16, %esp
5 movl 8(%ebp), %eax
6 shrl $31, %eax
7 testl %eax, %eax
8 je L2
9 movl $-1, -4(%ebp)
10 jmp L3
11 L2:
12 movl $1, -4(%ebp)
13 L3:
14 movl -4(%ebp), %eax
15 leave
16 ret
Now that I think that (x < 0) is more likely, gcc put the instruction
'movl $-1, -4(%ebp)' immediately after conditional branch instruction
'je L2'. But, with more conderation about this code, the goal of
improvement in instruction prefetching successfully can not be
achieved similarly. While executing 'je', the CPU is meant to prefetch
the next 'movl'. Even if this prefecthing is sucessful, the following
instruction 'jmp' will cause another failure of prefecthing
definitely. In fact, for a 'if' structure it is seems that the 'jmp'
insturction is inevitable regrardless of how the gcc arrage the code.
Therefore, as a whole, there is no improvement in instruction
prefetching. It is more likely that my opinion is limited somewhere
and the __builtin_expect() should play its role. So, I expect some
explanation about this problem.
