SQRTPS - SQuare RooT Packed Single

SQRTPS xmm1, xmm2/m128    (S1
__m128 _mm_sqrt_ps(__m128 a)
VSQRTPS xmm1, xmm2/m128    (V1
__m128 _mm_sqrt_ps(__m128 a)
VSQRTPS xmm1{k1}{z}, xmm2/m128/m32bcst    (V5+VL
__m128 _mm_mask_sqrt_ps(__m128 s, __mmask8 k, __m128 a)
__m128 _mm_maskz_sqrt_ps(__mmask8 k, __m128 a)

For each float, calculate square root of (1) and set the result to (2).
VSQRTPS ymm1, ymm2/m256    (V1
__m256 _mm256_sqrt_ps(__m256 a)
VSQRTPS ymm1{k1}{z}, ymm2/m256/m32bcst    (V5+VL
__m256 _mm256_mask_sqrt_ps(__m256 s, __mmask8 k, __m256 a)
__m256 _mm256_maskz_sqrt_ps(__mmask8 k, __m256 a)

For each float, calculate square root of (1) and set the result to (2).
VSQRTPS zmm1{k1}{z}, zmm2/m512/m32bcst{er}    (V5
__m512 _mm512_sqrt_ps(__m512 a)
__m512 _mm512_mask_sqrt_ps(__m512 s, __mmask16 k, __m512 a)
__m512 _mm512_maskz_sqrt_ps(__mmask16 k, __m512 a)
__m512 _mm512_sqrt_round_ps(__m512 a, int r)
__m512 _mm512_mask_sqrt_round_ps(__m512 s, __mmask16 k, __m512 a, int r)
__m512 _mm512_maskz_sqrt_round_ps(__mmask16 k, __m512 a, int r)

For each float, calculate square root of (1) and set the result to (2).

x86/x64 SIMD Instruction List  Feedback