VMINPH - MINimum Packed Half
VMINPH xmm1{k1}{z}, xmm2, xmm3/m128/m16bcst (V5+FP16+VL
__m128h _mm_min_ph(__m128h a, __m128h b)
__m128h _mm_mask_min_ph(__m128h s, __mmask8 k, __m128h a, __m128h b)
__m128h _mm_maskz_min_ph(__mmask8 k, __m128h a, __m128h b)
For each FP16, compare values of (1) and (2), and store the minimum value in (3).
VMINPH ymm1{k1}{z}, ymm2, ymm3/m256/m16bcst (V5+FP16+VL
__m256h _mm256_min_ph(__m256h a, __m256h b)
__m256h _mm256_mask_min_ph(__m256h s, __mmask16 k, __m256h a, __m256h b)
__m256h _mm256_maskz_min_ph(__mmask16 k, __m256h a, __m256h b)
For each FP16, compare values of (1) and (2), and store the minimum value in (3).
VMINPH zmm1{k1}{z}, zmm2, zmm3/m512/m16bcst{sae} (V5+FP16
__m512h _mm512_min_ph(__m512h a, __m512h b)
__m512h _mm512_mask_min_ph(__m512h s, __mmask32 k, __m512h a, __m512h b)
__m512h _mm512_maskz_min_ph(__mmask32 k, __m512h a, __m512h b)
__m512h _mm512_min_round_ph(__m512h a, __m512h b, int sae)
__m512h _mm512_mask_min_round_ph(__m512h s, __mmask32 k, __m512h a, __m512h b, int sae)
__m512h _mm512_maskz_min_round_ph(__mmask32 k, __m512h a, __m512h b, int sae)
For each FP16, compare values of (1) and (2), and store the minimum value in (3).
x86/x64 SIMD Instruction List
Feedback