https://gcc.gnu.org/bugzilla/show_bug.cgi?id=108724
--- Comment #10 from Richard Biener <rguenth at gcc dot gnu.org> ---
On trunk we're back to vectorizing but as intended with DImode which makes us
save half of the loads and stores and we think the extended required arithmetic
covers up for that (by quite some margin).
movabsq $9223372034707292159, %rcx
movq (%rdx), %rax
movq (%rsi), %rsi
movq %rcx, %rdx
andq %rax, %rdx
andq %rsi, %rcx
xorq %rsi, %rax
addq %rcx, %rdx
movabsq $-9223372034707292160, %rcx
andq %rcx, %rax
xorq %rdx, %rax
movq %rax, (%rdi)
vs
movl (%rdx), %eax
addl (%rsi), %eax
movl %eax, (%rdi)
movl 4(%rdx), %eax
addl 4(%rsi), %eax
movl %eax, 4(%rdi)
