Visible to Intel only — GUID: GUID-81AE1A2F-960E-4C7E-9CC8-6FA39FFA8E4D
Visible to Intel only — GUID: GUID-81AE1A2F-960E-4C7E-9CC8-6FA39FFA8E4D
enum dnnl_cpu_isa_t
Overview
CPU instruction set flags. More…
#include <dnnl_types.h>
enum dnnl_cpu_isa_t
{
dnnl_cpu_isa_default = 0x0,
dnnl_cpu_isa_sse41 = 0x1,
dnnl_cpu_isa_avx = 0x3,
dnnl_cpu_isa_avx2 = 0x7,
dnnl_cpu_isa_avx2_vnni = 0xf,
dnnl_cpu_isa_avx2_vnni_2 = 0x1f,
dnnl_cpu_isa_avx512_core = 0x27,
dnnl_cpu_isa_avx512_core_vnni = 0x67,
dnnl_cpu_isa_avx512_core_bf16 = 0xe7,
dnnl_cpu_isa_avx512_core_fp16 = 0x1ef,
dnnl_cpu_isa_avx512_core_amx = 0xfef,
dnnl_cpu_isa_avx512_core_amx_fp16 = 0x1fef,
};
Detailed Documentation
CPU instruction set flags.
Enum Values
dnnl_cpu_isa_default
Library choice of ISA (excepting those listed as initial support)
dnnl_cpu_isa_sse41
Intel Streaming SIMD Extensions 4.1 (Intel SSE4.1)
dnnl_cpu_isa_avx
Intel Advanced Vector Extensions (Intel AVX)
dnnl_cpu_isa_avx2
Intel Advanced Vector Extensions 2 (Intel AVX2)
dnnl_cpu_isa_avx2_vnni
Intel AVX2 and Intel Deep Learning Boost (Intel DL Boost) support.
dnnl_cpu_isa_avx2_vnni_2
Intel AVX2 and Intel Deep Learning Boost (Intel DL Boost) with 8-bit integer, float16 and bfloat16 support.
dnnl_cpu_isa_avx512_core
Intel AVX-512 subset for Intel Xeon Scalable processor family and Intel Core processor family.
dnnl_cpu_isa_avx512_core_vnni
Intel AVX-512 and Intel Deep Learning Boost (Intel DL Boost) support for Intel Xeon Scalable processor family and Intel Core processor family.
dnnl_cpu_isa_avx512_core_bf16
Intel AVX-512, Intel DL Boost and bfloat16 support for Intel Xeon Scalable processor family and Intel Core processor family.
dnnl_cpu_isa_avx512_core_fp16
Intel AVX-512 with float16, Intel DL Boost and bfloat16 support for Intel Xeon Scalable processor family and Intel Core processor family.
dnnl_cpu_isa_avx512_core_amx
Intel AVX-512 with float16, Intel DL Boost and bfloat16 support and Intel AMX with 8-bit integer and bfloat16 support.
dnnl_cpu_isa_avx512_core_amx_fp16
Intel AVX-512 with float16, Intel DL Boost and bfloat16 support and Intel AMX with 8-bit integer, bfloat16 and float16 support.