------- Comment #10 from uros at kss-loka dot si 2005-10-04 12:57 -------
(In reply to comment #9)
Sorry for typing too fast... Of course, load of %ebp is here:
foo:
pushl %ebp
pushl %edi
pushl %esi
pushl %ebx
subl $1032, %esp
leal 8(%esp), %ebp <<<<<<< load of %ebp
movl 1052(%esp), %eax
andl $15, %eax
shrl $2, %eax
negl %eax
andl $3, %eax
je .L2
movl $0, %ecx
.L4:
movl 1052(%esp), %edx
movl %ebp, (%edx,%ecx,4)
And just for fun, without vectorization, following code is produced:
foo:
subl $1024, %esp
movl 1028(%esp), %ecx
movl %esp, %edx
movl $1, %eax
.L2:
movl %edx, -4(%ecx,%eax,4)
incl %eax
cmpl $11, %eax
jne .L2
addl $1024, %esp
ret
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=24160
