Expose AVX (VEX-encoded) versions of the Vector Neural Network
Instructions to guest.
The bit definition:
CPUID.(EAX=7,ECX=1):EAX[bit 4] AVX_VNNI
The following instructions are available when this feature is
present in the guest.
1. VPDPBUS: Multiply and Add Unsigned and Signed Bytes
2. VPDPBUSDS: Multiply and Add Unsigned and Signed Bytes with Saturation
3. VPDPWSSD: Multiply and Add Signed Word Integers
4. VPDPWSSDS: Multiply and Add Signed Integers with Saturation
As for the kvm related code, please reference Linux commit id
1085a6b585d7.
The release document ref below link:
https://software.intel.com/content/www/us/en/develop/download/\
intel-architecture-instruction-set-extensions-programming-reference.html
Signed-off-by: Yang Zhong <yang.zhong@intel.com>
Message-Id: <
20210407015609.22936-1-yang.zhong@intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
.type = CPUID_FEATURE_WORD,
.feat_names = {
NULL, NULL, NULL, NULL,
- NULL, "avx512-bf16", NULL, NULL,
+ "avx-vnni", "avx512-bf16", NULL, NULL,
NULL, NULL, NULL, NULL,
NULL, NULL, NULL, NULL,
NULL, NULL, NULL, NULL,
MSR_ARCH_CAP_SKIP_L1DFL_VMENTRY | MSR_ARCH_CAP_MDS_NO |
MSR_ARCH_CAP_PSCHANGE_MC_NO | MSR_ARCH_CAP_TAA_NO,
.features[FEAT_7_1_EAX] =
- CPUID_7_1_EAX_AVX512_BF16,
+ CPUID_7_1_EAX_AVX_VNNI | CPUID_7_1_EAX_AVX512_BF16,
/*
* Missing: XSAVES (not supported by some Linux versions,
* including v4.1 to v4.12).
/* Speculative Store Bypass Disable */
#define CPUID_7_0_EDX_SPEC_CTRL_SSBD (1U << 31)
+/* AVX VNNI Instruction */
+#define CPUID_7_1_EAX_AVX_VNNI (1U << 4)
/* AVX512 BFloat16 Instruction */
#define CPUID_7_1_EAX_AVX512_BF16 (1U << 5)