------- Comment #4 from rguenth at gcc dot gnu dot org 2009-01-23 15:33 -------
The testcase should be
subroutine to_product_of(self,a,b,a1,a2)
complex(kind=8) :: self (:)
complex(kind=8), intent(in) :: a(:,:)
complex(kind=8), intent(in) :: b(:)
integer a1,a2
do i = 1,a1
do j = 1,a2
self(i) = self(i) + a(j,i)*b(j)
end do
end do
end subroutine
to be meaningful - otherwise we are accessing a in non-continuous ways in the
inner loop which would prevent vectorization.
With the versioning for stride == 1 I get then
.L13:
movupd 16(%rax), %xmm1
movupd (%rax), %xmm3
incl %ecx
movupd (%rdx), %xmm4
addq $32, %rax
movapd %xmm3, %xmm0
unpckhpd %xmm1, %xmm3
unpcklpd %xmm1, %xmm0
movupd 16(%rdx), %xmm1
movapd %xmm4, %xmm2
addq $32, %rdx
movapd %xmm3, %xmm9
cmpl %ecx, %r8d
unpcklpd %xmm1, %xmm2
unpckhpd %xmm1, %xmm4
movapd %xmm4, %xmm1
movapd %xmm2, %xmm4
mulpd %xmm1, %xmm9
mulpd %xmm0, %xmm4
mulpd %xmm3, %xmm2
mulpd %xmm1, %xmm0
subpd %xmm9, %xmm4
addpd %xmm2, %xmm0
addpd %xmm4, %xmm6
addpd %xmm0, %xmm5
ja .L13
haddpd %xmm5, %xmm5
cmpl %r15d, %edi
movl -4(%rsp), %ecx
haddpd %xmm6, %xmm6
addsd %xmm5, %xmm8
addsd %xmm6, %xmm7
jne .L12
jmp .L14
for the innermost loop, followed by a tail loop (peel for niters). This is
about 15% faster on AMD K10 than the non-vectorized loop (if you disable
the cost-model and make sure to have enough iterations in the inner loop
to pay back for the extra guarding conditions).
--
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=37021
