https://gcc.gnu.org/bugzilla/show_bug.cgi?id=88461
--- Comment #3 from Daniel Fruzynski <bugzi...@poradnik-webmastera.com> ---
Good catch, mask should be 16-bit. Here is fixed version:
[code]
#include <immintrin.h>
#include <stdint.h>
int test(uint16_t* data, int a)
{
__m128i v = _mm_load_si128((const __m128i*)data);
__mmask16 m = _mm_testn_epi16_mask(v, v);
m = _kshiftli_mask16(m, 1);
m = _kandn_mask16(m, a);
return m;
}
[/code]
[asm]
test(unsigned short*, int):
vmovdqa64 xmm0, XMMWORD PTR [rdi]
kmovw k4, esi
vptestnmw k1, xmm0, xmm0
kmovb eax, k1
kmovw k2, eax
kshiftlw k0, k2, 1
kandnw k3, k0, k4
kmovw eax, k3
ret
[/asm]
This still can be optimized, there is no need to move value from k1 to eax and
then to k2 - vptestnmw zeroes upper bits if k register.
