https://gcc.gnu.org/bugzilla/show_bug.cgi?id=79173
Thomas Koenig <tkoenig at gcc dot gnu.org> changed:
What |Removed |Added
----------------------------------------------------------------------------
CC| |tkoenig at gcc dot gnu.org
Last reconfirmed|2017-01-23 00:00:00 |2021-5-28
--- Comment #10 from Thomas Koenig <tkoenig at gcc dot gnu.org> ---
Just had a look at trunk.
It currently produces
adc:
leaq 800(%rsi), %rcx
xorl %edx, %edx
.L2:
movq (%rdi), %rax
addb $-1, %dl
adcq (%rsi), %rax
setc %dl
addq $8, %rsi
movq %rax, (%rdi)
addq $8, %rdi
cmpq %rcx, %rsi
jne .L2
ret
Clang does
adc: # @adc
movl $4, %eax
xorl %ecx, %ecx
.LBB0_1: # =>This Inner Loop Header: Depth=1
movq -32(%rsi,%rax,8), %rdx
addb $-1, %cl
adcq %rdx, -32(%rdi,%rax,8)
movq -24(%rsi,%rax,8), %rcx
adcq %rcx, -24(%rdi,%rax,8)
movq -16(%rsi,%rax,8), %rcx
adcq %rcx, -16(%rdi,%rax,8)
movq -8(%rsi,%rax,8), %rcx
adcq %rcx, -8(%rdi,%rax,8)
movq (%rsi,%rax,8), %rcx
adcq %rcx, (%rdi,%rax,8)
setb %cl
addq $5, %rax
cmpq $104, %rax
jne .LBB0_1
retq
so it actually unrolls the loop and does the ideal sequence of
add with carry.