https://gcc.gnu.org/bugzilla/show_bug.cgi?id=65135
--- Comment #2 from H.J. Lu <hjl.tools at gmail dot com> ---
The assembly code generates by r220674 is much shorter:
bar:
call __x86.get_pc_thunk.ax
addl $_GLOBAL_OFFSET_TABLE_, %eax
movl FPtr@GOTOFF(%eax), %edx
movl inc@GOTOFF(%eax), %ecx
leal (%edx,%ecx,4), %ecx
cmpl %ecx, FEOF@GOTOFF(%eax)
movl 4(%esp), %ecx
cmovb F@GOTOFF(%eax), %edx
movl %ecx, (%edx)
movl inc@GOTOFF(%eax), %ecx
leal (%edx,%ecx,4), %edx
movl %edx, FPtr@GOTOFF(%eax)
ret
vs
bar:
call __x86.get_pc_thunk.dx
addl $_GLOBAL_OFFSET_TABLE_, %edx
pushl %edi
pushl %esi
movl FPtr@GOT(%edx), %ecx
pushl %ebx
movl inc@GOT(%edx), %ebx
movl FEOF@GOT(%edx), %edi
movl (%ecx), %eax
movl (%ebx), %esi
leal (%eax,%esi,4), %esi
cmpl %esi, (%edi)
jnb .L2
movl F@GOT(%edx), %eax
movl (%eax), %eax
.L2:
movl 16(%esp), %edx
movl %edx, (%eax)
movl (%ebx), %edx
leal (%eax,%edx,4), %eax
movl %eax, (%ecx)
popl %ebx
popl %esi
popl %edi
ret
.size bar, .-bar
Why doesn't it improve performance? Why does it hurt performance instead?
