Latest Intel platform GraniteRapids-D introduces AMX-COMPLEX, which adds two instructions to perform matrix multiplication of two tiles containing complex elements and accumulate the results into a packed single precision tile.
AMX-COMPLEX is enumerated via CPUID.(EAX=7,ECX=1):EDX[bit 8]. Add the CPUID definition for AMX-COMPLEX, AMX-COMPLEX will be enabled automatically when using '-cpu host' and KVM advertises AMX-COMPLEX to userspace. Signed-off-by: Tao Su <tao1...@linux.intel.com> Reviewed-by: Xiaoyao Li <xiaoyao...@intel.com> --- KVM part of advertising AMX-COMPLEX CPUID bit already has been applied to kvm-x86 misc. [1/1] KVM: x86: Advertise AMX-COMPLEX CPUID to userspace https://github.com/kvm-x86/linux/commit/99b668545356 --- target/i386/cpu.c | 2 +- target/i386/cpu.h | 2 ++ 2 files changed, 3 insertions(+), 1 deletion(-) diff --git a/target/i386/cpu.c b/target/i386/cpu.c index 00f913b638..24ee67b42d 100644 --- a/target/i386/cpu.c +++ b/target/i386/cpu.c @@ -980,7 +980,7 @@ FeatureWordInfo feature_word_info[FEATURE_WORDS] = { .feat_names = { NULL, NULL, NULL, NULL, "avx-vnni-int8", "avx-ne-convert", NULL, NULL, - NULL, NULL, NULL, NULL, + "amx-complex", NULL, NULL, NULL, NULL, NULL, "prefetchiti", NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, NULL, diff --git a/target/i386/cpu.h b/target/i386/cpu.h index a6000e93bd..fbb05eace5 100644 --- a/target/i386/cpu.h +++ b/target/i386/cpu.h @@ -930,6 +930,8 @@ uint64_t x86_cpu_get_supported_feature_word(FeatureWord w, #define CPUID_7_1_EDX_AVX_VNNI_INT8 (1U << 4) /* AVX NE CONVERT Instructions */ #define CPUID_7_1_EDX_AVX_NE_CONVERT (1U << 5) +/* AMX COMPLEX Instructions */ +#define CPUID_7_1_EDX_AMX_COMPLEX (1U << 8) /* PREFETCHIT0/1 Instructions */ #define CPUID_7_1_EDX_PREFETCHITI (1U << 14) base-commit: 813bac3d8d70d85cb7835f7945eb9eed84c2d8d0 -- 2.34.1