https://gcc.gnu.org/bugzilla/show_bug.cgi?id=101366
Bug ID: 101366
Summary: x86 memset codegen for constant sized is suboptimal
Product: gcc
Version: unknown
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: rtl-optimization
Assignee: unassigned at gcc dot gnu.org
Reporter: kutdanila at yandex dot ru
Target Milestone: ---
https://gcc.godbolt.org/z/hP99MYMEG
void Test(char* dst) {
__m128i pattern = _mm_set1_epi8(dst[-1]);
for (int i = 0; i < 4; i++) {
_mm_loadu_si128(reinterpret_cast<__m128i*>(dst + 16 * i), pattern);
}
}
vs
void TestStd(char* s) {
memset(s, s[-1], 64);
}
-O3 -msse4.2
Test(char*):
movzbl -1(%rdi), %eax
pxor %xmm1, %xmm1
movd %eax, %xmm0
pshufb %xmm1, %xmm0
movups %xmm0, (%rdi)
movups %xmm0, 16(%rdi)
movups %xmm0, 32(%rdi)
movups %xmm0, 48(%rdi)
ret
TestStd(char*):
movabsq $72340172838076673, %rdx
movzbl -1(%rdi), %eax
movq %rax, %rcx
imulq %rdx, %rcx
mulq %rdx
addq %rcx, %rdx
movq %rax, (%rdi)
movq %rdx, 8(%rdi)
movq %rax, 16(%rdi)
movq %rdx, 24(%rdi)
movq %rax, 32(%rdi)
movq %rdx, 40(%rdi)
movq %rax, 48(%rdi)
movq %rdx, 56(%rdi)
ret
