VSQRTPH - SQuare RooT Packed Half
VSQRTPH xmm1{k1}{z}, xmm2/m128/m16bcst (V5+FP16+VL
__m128h _mm_sqrt_ph(__m128h a)
__m128h _mm_mask_sqrt_ph(__m128h s, __mmask8 k, __m128h a)
__m128h _mm_maskz_sqrt_ph(__mmask8 k, __m128h a)
For each FP16, calculate square root of (1) and store the result in (2).
VSQRTPH ymm1{k1}{z}, ymm2/m256/m16bcst (V5+FP16+VL
__m256h _mm256_sqrt_ph(__m256h a)
__m256h _mm256_mask_sqrt_ph(__m256h s, __mmask16 k, __m256h a)
__m256h _mm256_maskz_sqrt_ph(__mmask16 k, __m256h a)
For each FP16, calculate square root of (1) and store the result in (2).
VSQRTPH zmm1{k1}{z}, zmm2/m512/m16bcst (V5+FP16
__m512h _mm512_sqrt_ph(__m512h a)
__m512h _mm512_mask_sqrt_ph(__m512h s, __mmask32 k, __m512h a)
__m512h _mm512_maskz_sqrt_ph(__mmask32 k, __m512h a)
For each FP16, calculate square root of (1) and store the result in (2).
x86/x64 SIMD Instruction List
Feedback