PAVGW - Packed AVeraGe Word

PAVGW xmm1, xmm2/m128    (S2
__m128i _mm_avg_epu16(__m128i a, __m128i b)

For each unsigned WORD, calculate ( (1) + (2) + 1 ) >> 1, and set the result to (3).
VPAVGW xmm1, xmm2, xmm3/m128    (V1
__m128i _mm_avg_epu16(__m128i a, __m128i b)
VPAVGW xmm1{k1}{z}, xmm2, xmm3/m128    (V5+BW+VL
__m128i _mm_mask_avg_epu16(__m128i s, __mmask8 k, __m128i a, __m128i b)
__m128i _mm_maskz_avg_epu16(__mmask8 k, __m128i a, __m128i b)

For each unsigned WORD, calculate ( (1) + (2) + 1 ) >> 1, and set the result to (3).
VPAVGW ymm1, ymm2, ymm3/m256    (V2
__m256i _mm256_avg_epu16(__m256i a, __m256i b)
VPAVGW ymm1{k1}{z}, ymm2, ymm3/m256    (V5+BW+VL
__m256i _mm256_mask_avg_epu16(__m256i s, __mmask16 k, __m256i a, __m256i b)
__m256i _mm256_maskz_avg_epu16(__mmask16 k, __m256i a, __m256i b)

For each unsigned WORD, calculate ( (1) + (2) + 1 ) >> 1, and set the result to (3).
VPAVGW zmm1{k1}{z}, zmm2, zmm3/m512    (V5+BW
__m512i _mm512_avg_epu16(__m512i a, __m512i b)
__m512i _mm512_mask_avg_epu16(__m512i s, __mmask32 k, __m512i a, __m512i b)
__m512i _mm512_maskz_avg_epu16(__mmask32 k, __m512i a, __m512i b)

For each unsigned WORD, calculate ( (1) + (2) + 1 ) >> 1, and set the result to (3).
x86/x64 SIMD Instruction List  Feedback