VPSHLDVW - Packed SHift Left Double Variable Word

VPSHLDVW xmm1{k1}{z}, xmm2, xmm3/m128    (V5+VBMI2+VL
__m128i _mm_shldv_epi16(__m128i a, __m128i b, __m128i c)
__m128i _mm_mask_shldv_epi16(__m128i a, __mmask8 k, __m128i b, __m128i c)
__m128i _mm_maskz_shldv_epi16(__mmask8 k, __m128i a, __m128i b, __m128i c)

For each WORD, (1) is shifted to the left by the number of bits specified in bit 3:0 of (3). Upper bits of (2) are copied to the emptied lower bits. The result is stored in (4).
VPSHLDVW ymm1{k1}{z}, ymm2, ymm3/m256    (V5+VBMI2+VL
__m256i _mm256_shldv_epi16(__m256i a, __m256i b, __m256i c)
__m256i _mm256_mask_shldv_epi16(__m256i a, __mmask16 k, __m256i b, __m256i c)
__m256i _mm256_maskz_shldv_epi16(__mmask16 k, __m256i a, __m256i b, __m256i c)

For each WORD, (1) is shifted to the left by the number of bits specified in bit 3:0 of (3). Upper bits of (2) are copied to the emptied lower bits. The result is stored in (4).
VPSHLDVW zmm1{k1}{z}, zmm2, zmm3/m512    (V5+VBMI2
__m512i _mm512_shldv_epi16(__m512i a, __m512i b, __m512i c)
__m512i _mm512_mask_shldv_epi16(__m512i a, __mmask32 k, __m512i b, __m512i c)
__m512i _mm512_maskz_shldv_epi16(__mmask32 k, __m512i a, __m512i b, __m512i c)

For each WORD, (1) is shifted to the left by the number of bits specified in bit 3:0 of (3). Upper bits of (2) are copied to the emptied lower bits. The result is stored in (4).

_mask_  if k bit is 0, a is copied.
_maskz_  if k bit is 0, zero cleared.


x86/x64 SIMD Instruction List  Feedback