https://gcc.gnu.org/bugzilla/show_bug.cgi?id=114429
Bug ID: 114429
Summary: [x86] (neg a) ashifrt>> 31 can be optimized to a > 0.
Product: gcc
Version: 14.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: target
Assignee: unassigned at gcc dot gnu.org
Reporter: liuhongt at gcc dot gnu.org
Target Milestone: ---
typedef unsigned char uint8_t;
uint8_t x264_clip_uint8( int x )
{
return x&(~255) ? (-x)>>31 : x;
}
void
foo (int* a, int* __restrict b, int n)
{
for (int i = 0; i != 8; i++)
b[i] = x264_clip_uint8 (a[i]);
}
gcc -O2 -march=x86-64-v3 -S
foo(int*, int*, int):
..
mov eax, 255
vpxor xmm0, xmm0, xmm0
vmovd xmm1, eax
vpbroadcastd ymm1, xmm1
vmovdqu ymm2, YMMWORD PTR [rdi]
vpminud ymm3, ymm2, ymm1
vpsubd ymm0, ymm0, ymm2
vmovdqa YMMWORD PTR [rsp-32], ymm3
vpsrad ymm0, ymm0, 31
vpcmpeqd ymm3, ymm2, YMMWORD PTR [rsp-32]
vpblendvb ymm0, ymm0, ymm2, ymm3
vpand ymm1, ymm1, ymm0
vmovdqu YMMWORD PTR [rsi], ymm1
It can be better with
mov eax, 255
vmovd xmm1, eax
vpxor xmm0, xmm0, xmm0.
vpbroadcastd ymm1, xmm1
vmovdqu ymm2, YMMWORD PTR [rdi]
vpminud ymm3, ymm2, ymm1
vmovdqa YMMWORD PTR [rsp-32], ymm3
vcmpgtps ymm0, ymm2, ymm0
vpcmpeqd ymm3, ymm2, YMMWORD PTR [rsp-32]
vpblendvb ymm0, ymm0, ymm2, ymm3
vpand ymm1, ymm1, ymm0
vmovdqu YMMWORD PTR [rsi], ymm1