PMULLW - Packed MULtiply Low Word

PMULLW xmm1, xmm2/m128    (S2
__m128i _mm_mullo_epi16(__m128i a, __m128i b)

For each WORD, calculate (1) * (2) and set the lower 16-bit of the 32-bit result to (3).
VPMULLW xmm1, xmm2, xmm3/m128    (V1
__m128i _mm_mullo_epi16(__m128i a, __m128i b)
VPMULLW xmm1{k1}{z}, xmm2, xmm3/m128    (V5+BW+VL
__m128i _mm_mask_mullo_epi16(__m128i s, __mmask8 k, __m128i a, __m128i b)
__m128i _mm_maskz_mullo_epi16(__mmask8 k, __m128i a, __m128i b)

For each WORD, calculate (1) * (2) and set the lower 16-bit of the 32-bit result to (3).
VPMULLW ymm1, ymm2, ymm3/m256    (V2
__m256i _mm256_mullo_epi16(__m256i a, __m256i b)
VPMULLW ymm1{k1}{z}, ymm2, ymm3/m256    (V5+BW+VL
__m256i _mm256_mask_mullo_epi16(__m256i s, __mmask16 k, __m256i a, __m256i b)
__m256i _mm256_maskz_mullo_epi16(__mmask16 k, __m256i a, __m256i b)

For each WORD, calculate (1) * (2) and set the lower 16-bit of the 32-bit result to (3).
VPMULLW zmm1{k1}{z}, zmm2, zmm3/m512    (V5+BW
__m512i _mm512_mullo_epi16(__m512i a, __m512i b)
__m512i _mm512_mask_mullo_epi16(__m512i s, __mmask32 k, __m512i a, __m512i b)
__m512i _mm512_maskz_mullo_epi16(__mmask32 k, __m512i a, __m512i b)

For each WORD, calculate (1) * (2) and set the lower 16-bit of the 32-bit result to (3).
x86/x64 SIMD Instruction List  Feedback