https://gcc.gnu.org/bugzilla/show_bug.cgi?id=103750
--- Comment #11 from Hongtao.liu <crazylht at gmail dot com> ---
(In reply to Thiago Macieira from comment #6)
> It got worse. Now I'm seeing:
>
> .L807:
> vmovdqu16 (%rsi), %ymm2
> vmovdqu16 32(%rsi), %ymm3
> vpcmpuw $6, %ymm0, %ymm2, %k2
> vpcmpuw $6, %ymm0, %ymm3, %k3
> kmovw %k2, %eax
> kmovw %k3, %edx
> kmovd %eax, %k4
> kmovd %edx, %k5
> kortestd %k5, %k4
> je .L814
>
(define_insn "*zero_extend<mode>si2"
[(set (match_operand:SI 0 "register_operand" "=r,*r,*k")
(zero_extend:SI
(match_operand:SWI12 1 "nonimmediate_operand" "<r>m,*k,*km")))]
"!(TARGET_ZERO_EXTEND_WITH_AND && optimize_function_for_speed_p (cfun))"
zero_extendhisi is supported with k alternative, it should be optimized to
vmovdqu16 (%rsi), %ymm2
vmovdqu16 32(%rsi), %ymm3
vpcmpuw $6, %ymm0, %ymm2, %k2
vpcmpuw $6, %ymm0, %ymm3, %k3
kmovw %k2, %k4
kmovw %k3, %k5
kortestd %k5, %k4
And considering vpcmpuw will implicitly zero extend k2&k3, it can be further
optimized to
vmovdqu16 (%rsi), %ymm2
vmovdqu16 32(%rsi), %ymm3
vpcmpuw $6, %ymm0, %ymm2, %k2
vpcmpuw $6, %ymm0, %ymm3, %k3
kortestd %k3, %k2
> Code snippet:
>
> auto loadAndCompare = [maxval](const Char *ptr, unsigned mask = ~0U)
> {
> if constexpr (sizeof(Char) == 1) {
> __m256i mval = _mm256_set1_epi8(maxval);
> __m256i data = _mm256_maskz_loadu_epi8(mask, ptr);
> return _mm256_cmpgt_epu8_mask(data, mval);
> } else if constexpr (sizeof(Char) == 2) {
> __m256i mval = _mm256_set1_epi16(maxval);
> __m256i data = _mm256_maskz_loadu_epi16(mask, ptr);
> return _mm256_cmpgt_epu16_mask(data, mval);
> } else if constexpr (sizeof(Char) == 4) {
> __m256i mval = _mm256_set1_epi32(maxval);
> __m256i data = _mm256_maskz_loadu_epi32(mask, ptr);
> return _mm256_cmpgt_epu32_mask(data, mval);
> }
> };
> /*...*/
> auto mask1 = loadAndCompare(n1);
> auto mask2 = loadAndCompare(n2);
>
> I can make a compilable version if you need me to
Yes, please.
