------- Comment #5 from ubizjak at gmail dot com 2008-03-21 10:17 -------
Inner loop, generated with -O2 -mmmx -fno-strict-aliasing,
gcc version 4.0.2 20051125 (Red Hat 4.0.2-8):
.L45:
movq (%ebx), %mm0
psubw (%ecx), %mm0
movq %mm0, %mm1
psraw $15, %mm1
pxor %mm1, %mm0
psubw %mm1, %mm0
movq %mm0, %mm1
punpckhwd %mm2, %mm1
punpcklwd %mm0, %mm0
psrad $16, %mm0
paddd %mm1, %mm0
movl %eax, -56(%ebp)
movl %edx, -52(%ebp)
movq -56(%ebp), %mm1
paddd %mm1, %mm0
movq %mm0, -56(%ebp)
movl -56(%ebp), %eax
movl -52(%ebp), %edx
movl %eax, -24(%ebp)
movl %edx, -20(%ebp)
addl $4, %esi
addl $8, %ebx
addl $8, %ecx
cmpl %esi, %edi
jg .L45
time ./a.out
144
real 0m4.587s
user 0m4.584s
sys 0m0.004s
Inner loop, generated with -O2 -mmmx -fno-strict-aliasing,
gcc version 4.4.0 20080318 (experimental) [trunk revision 133304] (GCC)
(this one has improved MMX move instructions):
.L23:
movq (%ecx,%eax,2), %mm0
psubw (%edx,%eax,2), %mm0
addl $4, %eax
cmpl %eax, %ebx
movq %mm0, %mm1
psraw $15, %mm1
pxor %mm1, %mm0
psubw %mm1, %mm0
movq %mm0, %mm1
punpcklwd %mm0, %mm0
punpckhwd %mm3, %mm1
psrad $16, %mm0
paddd %mm1, %mm0
paddd %mm0, %mm2
movq %mm2, -24(%ebp)
jg .L23
time ./a.out
144
real 0m0.755s
user 0m0.752s
sys 0m0.000s
Current mainline is _SIX_ times faster.
Unfortunatelly, there are no plans to backport this functionality to anything
older than 4.4, so fixed for 4.4.
--
ubizjak at gmail dot com changed:
What |Removed |Added
----------------------------------------------------------------------------
Status|WAITING |RESOLVED
Resolution| |FIXED
Target Milestone|--- |4.4.0
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=21395
