https://gcc.gnu.org/bugzilla/show_bug.cgi?id=120683
Bug ID: 120683
Summary: vector_loop generates horrible prologue and epilogue
on memset
Product: gcc
Version: 16.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: target
Assignee: unassigned at gcc dot gnu.org
Reporter: hjl.tools at gmail dot com
CC: hubicka at ucw dot cz, liuhongt at gcc dot gnu.org,
ubizjak at gmail dot com
Target Milestone: ---
Target: x86-64
For
---
#include <sys/types.h>
void
foo (void *p1, size_t len)
{
__builtin_memset(p1, 0, len);
}
---
-O2 -mmemset-strategy=vector_loop:256:noalign,libcall:-1:noalign
-minline-all-stringops
generates horrible prologue and epilogue:
foo:
.LFB6:
.cfi_startproc
movq %rdi, %rax
pxor %xmm0, %xmm0
cmpq $64, %rsi
jnb .L18
.L2:
andl $63, %esi
je .L1
xorl %edx, %edx
testb $1, %sil
je .L5
movl $1, %edx
movb $0, (%rax)
cmpq %rsi, %rdx
jnb .L19
.L5:
movb $0, (%rax,%rdx)
movb $0, 1(%rax,%rdx)
addq $2, %rdx
cmpq %rsi, %rdx
jb .L5
.L1:
ret
.p2align 4,,10
.p2align 3
.L18:
movq %rsi, %rdx
xorl %eax, %eax
andq $-64, %rdx
.L3:
movups %xmm0, (%rdi,%rax)
movups %xmm0, 16(%rdi,%rax)
movups %xmm0, 32(%rdi,%rax)
movups %xmm0, 48(%rdi,%rax)
addq $64, %rax
cmpq %rdx, %rax
jb .L3
addq %rdi, %rax
jmp .L2
.L19:
ret
.cfi_endproc
It uses a 1-byte loop to clear a 8 byte memory.
