PSUBB - Packed SUBtract Byte

PSUBB xmm1, xmm2/m128    (S2
__m128i _mm_sub_epi8(__m128i a, __m128i b)

For each BYTE, calculate (1) - (2) and set the result to (3).
VPSUBB xmm1, xmm2, xmm3/m128    (V1
__m128i _mm_sub_epi8(__m128i a, __m128i b)
VPSUBB xmm1{k1}{z}, xmm2, xmm3/m128    (V5+BW+VL
__m128i _mm_mask_sub_epi8(__m128i s, __mmask16 k, __m128i a, __m128i b)
__m128i _mm_maskz_sub_epi8(__mmask16 k, __m128i a, __m128i b)

For each BYTE, calculate (1) - (2) and set the result to (3).
VPSUBB ymm1, ymm2, ymm3/m256    (V2
__m256i _mm256_sub_epi8(__m256i a, __m256i b)
VPSUBB ymm1{k1}{z}, ymm2, ymm3/m256    (V5+BW+VL
__m256i _mm256_mask_sub_epi8(__m256i s, __mmask32 k, __m256i a, __m256i b)
__m256i _mm256_maskz_sub_epi8(__mmask32 k, __m256i a, __m256i b)

For each BYTE, calculate (1) - (2) and set the result to (3).
VPSUBB zmm1{k1}{z}, zmm2, zmm3/m512    (V5+BW
__m512i _mm512_sub_epi8(__m512i a, __m512i b)
__m512i _mm512_mask_sub_epi8(__m512i s, __mmask64 k, __m512i a, __m512i b)
__m512i _mm512_maskz_sub_epi8(__mmask64 k, __m512i a, __m512i b)

For each BYTE, calculate (1) - (2) and set the result to (3).

x86/x64 SIMD Instruction List  Feedback