x86-64.net

Instruction

VPCMPB

Compares packed signed bytes with a predicate chosen by an immediate and writes the results to a mask register.

Extensions
Forms
6 (6 EVEX)
Data
Intel XED v2026.08.23

Forms

Every encoding of VPCMPB that Intel XED knows, one row per XED instruction form (iform). How to read the notation.
InstructionEncodingRequires
VPCMPB k {k}, xmm, xmm, imm8 VPCMPB_MASKmskw_MASKmskw_XMMi8_XMMi8_IMM8_AVX512EVEX.128.66.0F3A.W0 3F /r ibAVX10.1 or AVX512BW + AVX512VL
VPCMPB k {k}, xmm, m128, imm8 VPCMPB_MASKmskw_MASKmskw_XMMi8_MEMi8_IMM8_AVX512EVEX.128.66.0F3A.W0 3F /r ibAVX10.1 or AVX512BW + AVX512VL
VPCMPB k {k}, ymm, ymm, imm8 VPCMPB_MASKmskw_MASKmskw_YMMi8_YMMi8_IMM8_AVX512EVEX.256.66.0F3A.W0 3F /r ibAVX10.1 or AVX512BW + AVX512VL
VPCMPB k {k}, ymm, m256, imm8 VPCMPB_MASKmskw_MASKmskw_YMMi8_MEMi8_IMM8_AVX512EVEX.256.66.0F3A.W0 3F /r ibAVX10.1 or AVX512BW + AVX512VL
VPCMPB k {k}, zmm, zmm, imm8 VPCMPB_MASKmskw_MASKmskw_ZMMi8_ZMMi8_IMM8_AVX512EVEX.512.66.0F3A.W0 3F /r ibAVX10.1 or AVX512BW
VPCMPB k {k}, zmm, m512, imm8 VPCMPB_MASKmskw_MASKmskw_ZMMi8_MEMi8_IMM8_AVX512EVEX.512.66.0F3A.W0 3F /r ibAVX10.1 or AVX512BW

Intrinsics

The C intrinsics of Clang 23.1.2 that compile to VPCMPB, each with the form it compiles to and the Clang options it needs. The forms come from compiling every intrinsic and decoding the result with Intel XED; all intrinsics A–Z explains the method.

IntrinsicCompiles to
_mm_cmp_epi8_mask __mmask16 _mm_cmp_epi8_mask(__m128i a, __m128i b, const int p)

VPCMPB k, xmm, xmm, imm8 EVEX.128 -mavx512vl -mavx512bw

_mm_mask_cmp_epi8_mask __mmask16 _mm_mask_cmp_epi8_mask(__mmask16 m, __m128i a, __m128i b, const int p)

VPCMPB k, xmm, xmm, imm8 EVEX.128 -mavx512vl -mavx512bw

_mm_cmpge_epi8_mask __mmask16 _mm_cmpge_epi8_mask(__m128i A, __m128i B)

VPCMPB k, xmm, xmm, imm8 EVEX.128 -mavx512vl -mavx512bw

_mm_mask_cmpge_epi8_mask __mmask16 _mm_mask_cmpge_epi8_mask(__mmask16 k, __m128i A, __m128i B)

VPCMPB k, xmm, xmm, imm8 EVEX.128 -mavx512vl -mavx512bw

_mm_cmple_epi8_mask __mmask16 _mm_cmple_epi8_mask(__m128i A, __m128i B)

VPCMPB k, xmm, xmm, imm8 EVEX.128 -mavx512vl -mavx512bw

_mm_mask_cmple_epi8_mask __mmask16 _mm_mask_cmple_epi8_mask(__mmask16 k, __m128i A, __m128i B)

VPCMPB k, xmm, xmm, imm8 EVEX.128 -mavx512vl -mavx512bw

_mm_cmpneq_epi8_mask __mmask16 _mm_cmpneq_epi8_mask(__m128i A, __m128i B)

VPCMPB k, xmm, xmm, imm8 EVEX.128 -mavx512vl -mavx512bw

_mm_mask_cmpneq_epi8_mask __mmask16 _mm_mask_cmpneq_epi8_mask(__mmask16 k, __m128i A, __m128i B)

VPCMPB k, xmm, xmm, imm8 EVEX.128 -mavx512vl -mavx512bw

_mm_cmpneq_epu8_mask __mmask16 _mm_cmpneq_epu8_mask(__m128i A, __m128i B)

VPCMPB k, xmm, xmm, imm8 EVEX.128 -mavx512vl -mavx512bw

_mm_mask_cmpneq_epu8_mask __mmask16 _mm_mask_cmpneq_epu8_mask(__mmask16 k, __m128i A, __m128i B)

VPCMPB k, xmm, xmm, imm8 EVEX.128 -mavx512vl -mavx512bw

_mm256_cmp_epi8_mask __mmask32 _mm256_cmp_epi8_mask(__m256i a, __m256i b, const int p)

VPCMPB k, ymm, ymm, imm8 EVEX.256 -mavx512vl -mavx512bw

_mm256_mask_cmp_epi8_mask __mmask32 _mm256_mask_cmp_epi8_mask(__mmask32 m, __m256i a, __m256i b, const int p)

VPCMPB k, ymm, ymm, imm8 EVEX.256 -mavx512vl -mavx512bw

_mm256_cmpge_epi8_mask __mmask32 _mm256_cmpge_epi8_mask(__m256i A, __m256i B)

VPCMPB k, ymm, ymm, imm8 EVEX.256 -mavx512vl -mavx512bw

_mm256_mask_cmpge_epi8_mask __mmask32 _mm256_mask_cmpge_epi8_mask(__mmask32 k, __m256i A, __m256i B)

VPCMPB k, ymm, ymm, imm8 EVEX.256 -mavx512vl -mavx512bw

_mm256_cmple_epi8_mask __mmask32 _mm256_cmple_epi8_mask(__m256i A, __m256i B)

VPCMPB k, ymm, ymm, imm8 EVEX.256 -mavx512vl -mavx512bw

_mm256_mask_cmple_epi8_mask __mmask32 _mm256_mask_cmple_epi8_mask(__mmask32 k, __m256i A, __m256i B)

VPCMPB k, ymm, ymm, imm8 EVEX.256 -mavx512vl -mavx512bw

_mm256_cmpneq_epi8_mask __mmask32 _mm256_cmpneq_epi8_mask(__m256i A, __m256i B)

VPCMPB k, ymm, ymm, imm8 EVEX.256 -mavx512vl -mavx512bw

_mm256_mask_cmpneq_epi8_mask __mmask32 _mm256_mask_cmpneq_epi8_mask(__mmask32 k, __m256i A, __m256i B)

VPCMPB k, ymm, ymm, imm8 EVEX.256 -mavx512vl -mavx512bw

_mm256_cmpneq_epu8_mask __mmask32 _mm256_cmpneq_epu8_mask(__m256i A, __m256i B)

VPCMPB k, ymm, ymm, imm8 EVEX.256 -mavx512vl -mavx512bw

_mm256_mask_cmpneq_epu8_mask __mmask32 _mm256_mask_cmpneq_epu8_mask(__mmask32 k, __m256i A, __m256i B)

VPCMPB k, ymm, ymm, imm8 EVEX.256 -mavx512vl -mavx512bw

_mm512_cmp_epi8_mask __mmask64 _mm512_cmp_epi8_mask(__m512i a, __m512i b, const int p)

VPCMPB k, zmm, zmm, imm8 EVEX.512 -mavx512bw

_mm512_mask_cmp_epi8_mask __mmask64 _mm512_mask_cmp_epi8_mask(__mmask64 m, __m512i a, __m512i b, const int p)

VPCMPB k, zmm, zmm, imm8 EVEX.512 -mavx512bw

_mm512_cmpge_epi8_mask __mmask64 _mm512_cmpge_epi8_mask(__m512i A, __m512i B)

VPCMPB k, zmm, zmm, imm8 EVEX.512 -mavx512bw

_mm512_mask_cmpge_epi8_mask __mmask64 _mm512_mask_cmpge_epi8_mask(__mmask64 k, __m512i A, __m512i B)

VPCMPB k, zmm, zmm, imm8 EVEX.512 -mavx512bw

_mm512_cmple_epi8_mask __mmask64 _mm512_cmple_epi8_mask(__m512i A, __m512i B)

VPCMPB k, zmm, zmm, imm8 EVEX.512 -mavx512bw

_mm512_mask_cmple_epi8_mask __mmask64 _mm512_mask_cmple_epi8_mask(__mmask64 k, __m512i A, __m512i B)

VPCMPB k, zmm, zmm, imm8 EVEX.512 -mavx512bw

_mm512_cmpneq_epi8_mask __mmask64 _mm512_cmpneq_epi8_mask(__m512i A, __m512i B)

VPCMPB k, zmm, zmm, imm8 EVEX.512 -mavx512bw

_mm512_mask_cmpneq_epi8_mask __mmask64 _mm512_mask_cmpneq_epi8_mask(__mmask64 k, __m512i A, __m512i B)

VPCMPB k, zmm, zmm, imm8 EVEX.512 -mavx512bw

_mm512_cmpneq_epu8_mask __mmask64 _mm512_cmpneq_epu8_mask(__m512i A, __m512i B)

VPCMPB k, zmm, zmm, imm8 EVEX.512 -mavx512bw

_mm512_mask_cmpneq_epu8_mask __mmask64 _mm512_mask_cmpneq_epu8_mask(__mmask64 k, __m512i A, __m512i B)

VPCMPB k, zmm, zmm, imm8 EVEX.512 -mavx512bw

CPUID and processors

Each form belongs to an XED ISA set. A form can be used when the processor reports every CPUID bit of one of its ISA set's alternatives.

CPUID requirements and processors of the XED ISA sets above. Alternatives are separated by “or”; processors follow XED’s chip model, which covers AMD processors up to Zen 2.
ISA setCPUIDProcessors in XED
AVX512BW_128

AVX10.1
CPUID.(EAX=07H,ECX=1):EDX[19] AVX10
CPUID.(EAX=24H,ECX=0):EBX[7:0] ≥ 1 AVX10 version

or

AVX512BW + AVX512VL
CPUID.(EAX=07H,ECX=0):EBX[30] AVX512BW
CPUID.(EAX=07H,ECX=0):EBX[31] AVX512VL

Cannon Lake, Ice Lake (client), Tiger Lake, Nova Lake, Skylake-SP, Cascade Lake, Cooper Lake, Ice Lake (server), Sapphire Rapids, Emerald Rapids, Granite Rapids, Diamond Rapids
AVX512BW_256

AVX10.1
CPUID.(EAX=07H,ECX=1):EDX[19] AVX10
CPUID.(EAX=24H,ECX=0):EBX[7:0] ≥ 1 AVX10 version

or

AVX512BW + AVX512VL
CPUID.(EAX=07H,ECX=0):EBX[30] AVX512BW
CPUID.(EAX=07H,ECX=0):EBX[31] AVX512VL

Cannon Lake, Ice Lake (client), Tiger Lake, Nova Lake, Skylake-SP, Cascade Lake, Cooper Lake, Ice Lake (server), Sapphire Rapids, Emerald Rapids, Granite Rapids, Diamond Rapids
AVX512BW_512

AVX10.1
CPUID.(EAX=07H,ECX=1):EDX[19] AVX10
CPUID.(EAX=24H,ECX=0):EBX[7:0] ≥ 1 AVX10 version

or

AVX512BW
CPUID.(EAX=07H,ECX=0):EBX[30] AVX512BW

Cannon Lake, Ice Lake (client), Tiger Lake, Nova Lake, Skylake-SP, Cascade Lake, Cooper Lake, Ice Lake (server), Sapphire Rapids, Emerald Rapids, Granite Rapids, Diamond Rapids

More AVX10.1 instructions

All 686 AVX10.1 instructions

Sources

  1. Intel XED v2026.08.23 (commit 0bcb6237345c): forms, encodings, ISA sets, CPUID bits and chip model.
  2. Clang's x86 intrinsic headers, LLVM 23.1.2 (commit 85ac56026243): the intrinsics, their signatures and doc comments, and the Clang of that release, which compiled each of them.
  3. Intel Advanced Vector Extensions 10.2 Architecture Specification, revision 6.0 (361050-006, January 2026)

The tables are derived from Intel XED, Copyright Intel Corporation, licensed under the Apache License 2.0; x86-64.net converted and reformatted them. The intrinsics and their signatures come from Clang, part of the LLVM Project, licensed under the Apache License 2.0 with LLVM Exceptions. The text is our own.