VPMOVDW - Packed MOVe Dword Word

DWORD → WORD    copy lowest 16-bit.

VPMOVDW xmm1 {k1}{z}, xmm2    (V5+VL
__m128i _mm_cvtepi32_epi16(__m128i a)
__m128i _mm_mask_cvtepi32_epi16(__m128i s, __mmask8 k, __m128i a)
__m128i _mm_maskz_cvtepi32_epi16(__mmask8 k, __m128i a)

VPMOVDW m64 {k1}, xmm2    (V5+VL
void _mm_mask_cvtepi32_storeu_epi16(void* d, __mmask8 k, __m128i a)

VPMOVDW xmm1 {k1}{z}, ymm2    (V5+VL
__m128i _mm256_cvtepi32_epi16(__m256i a)
__m128i _mm256_mask_cvtepi32_epi16(__m128i s, __mmask8 k, __m256i a)
__m128i _mm256_maskz_cvtepi32_epi16(__mmask8 k, __m256i a)

VPMOVDW m128 {k1}, ymm2    (V5+VL
void _mm256_mask_cvtepi32_storeu_epi16(void* d, __mmask8 k, __m256i a)

VPMOVDW ymm1 {k1}{z}, zmm2    (V5
__m256i _mm512_cvtepi32_epi16(__m512i a)
__m256i _mm512_mask_cvtepi32_epi16(__m256i s, __mmask16 k, __m512i a)
__m256i _mm512_maskz_cvtepi32_epi16(__mmask16 k, __m512i a)

VPMOVDW m256 {k1}, zmm2    (V5
void _mm512_mask_cvtepi32_storeu_epi16(void* d, __mmask16 k, __m512i a)


x86/x64 SIMD Instruction List  Feedback