https://gcc.gnu.org/bugzilla/show_bug.cgi?id=106475
--- Comment #1 from Richard Biener <rguenth at gcc dot gnu.org> ---
The loop seems to be vectorized just fine? The issue is just that we need a
runtime alias check because of the variable stride and the fact that we need a
VF of two to fill up to 16 byte vectors:
.L5:
movq (%rcx), %xmm1
movq (%rdx), %xmm0
addl $1, %esi
movhps (%rcx,%r10), %xmm1
movhps (%rdx,%r9), %xmm0
addq %r14, %rcx
addq %r13, %rdx
paddb %xmm1, %xmm0
paddb %xmm2, %xmm0
movq %xmm0, (%rax)
movhps %xmm0, (%rax,%rdi)
addq %r12, %rax
cmpl %esi, %r15d
jne .L5
movl %ebp, %eax
andl $-2, %eax
andl $1, %ebp
je .L1
.L4:
imulq %rax, %r10
imulq %rax, %r9
imulq %rdi, %rax
movq (%rbx,%r10), %xmm0
movq (%r8,%r9), %xmm1
paddb %xmm1, %xmm0
movq .LC1(%rip), %xmm1
paddb %xmm1, %xmm0
movq %xmm0, (%r11,%rax)
yes, the BB vectorization result is smaller but only uses half of a vector:
.L3:
movq (%r8), %xmm0
movq (%rdx), %xmm1
addl $1, %ecx
addq %rdi, %rdx
addq %rsi, %r8
paddb %xmm1, %xmm0
paddb %xmm2, %xmm0
movq %xmm0, (%rax)
addq %r10, %rax
cmpl %ecx, %r11d
jne .L3
