PSUBUSB - Packed SUBtract Unsigned Saturation Byte

PSUBUSB xmm1, xmm2/m128    (S2
__m128i _mm_subs_epu8(__m128i a, __m128i b)

For each BYTE calculate (1) - (2) with unsigned saturation and set the result to (3). Set 0 on overflow.
VPSUBUSB xmm1, xmm2, xmm3/m128    (V1
__m128i _mm_subs_epu8(__m128i a, __m128i b)
VPSUBUSB xmm1{k1}{z}, xmm2, xmm3/m128    (V5+BW+VL
__m128i _mm_mask_subs_epu8(__m128i s, __mmask16 k, __m128i a, __m128i b)
__m128i _mm_maskz_subs_epu8(__mmask16 k, __m128i a, __m128i b)

For each BYTE calculate (1) - (2) with unsigned saturation and set the result to (3). Set 0 on overflow.
VPSUBUSB ymm1, ymm2, ymm3/m256    (V2
__m256i _mm256_subs_epu8(__m256i a, __m256i b)
VPSUBUSB ymm1{k1}{z}, ymm2, ymm3/m256    (V5+BW+VL
__m256i _mm256_mask_subs_epu8(__m256i s, __mmask32 k, __m256i a, __m256i b)
__m256i _mm256_maskz_subs_epu8(__mmask32 k, __m256i a, __m256i b)

For each BYTE calculate (1) - (2) with unsigned saturation and set the result to (3). Set 0 on overflow.
VPSUBUSB zmm1{k1}{z}, zmm2, zmm3/m512    (V5+BW
__m512i _mm512_subs_epu8(__m512i a, __m512i b)
__m512i _mm512_mask_subs_epu8(__m512i s, __mmask64 k, __m512i a, __m512i b)
__m512i _mm512_maskz_subs_epu8(__mmask64 k, __m512i a, __m512i b)

For each BYTE calculate (1) - (2) with unsigned saturation and set the result to (3). Set 0 on overflow.

x86/x64 SIMD Instruction List  Feedback