diff options
| author | Chang S. Bae <chang.seok.bae@intel.com> | 2022-11-25 13:58:41 +0100 |
|---|---|---|
| committer | Paolo Bonzini <pbonzini@redhat.com> | 2022-11-28 19:33:27 +0100 |
| commit | af2872f6225476566bcbbd523a74dcaba29e159e (patch) | |
| tree | 77f67d3c838b5e5cff455f52fe87fe2176ee1d94 /arch/x86/kvm | |
| parent | x86: KVM: Advertise CMPccXADD CPUID to user space (diff) | |
| download | linux-af2872f6225476566bcbbd523a74dcaba29e159e.tar.xz linux-af2872f6225476566bcbbd523a74dcaba29e159e.zip | |
x86: KVM: Advertise AMX-FP16 CPUID to user space
Latest Intel platform Granite Rapids has introduced a new instruction -
AMX-FP16, which performs dot-products of two FP16 tiles and accumulates
the results into a packed single precision tile. AMX-FP16 adds FP16
capability and also allows a FP16 GPU trained model to run faster
without loss of accuracy or added SW overhead.
The bit definition:
CPUID.(EAX=7,ECX=1):EAX[bit 21]
AMX-FP16 is on an expected-dense CPUID leaf and some other bits on this
leaf have kernel usages. Given that, define this feature bit like
X86_FEATURE_<name> in kernel. Considering AMX-FP16 itself has no truly
kernel usages and /proc/cpuinfo has too much unreadable flags, hide this
one in /proc/cpuinfo.
Advertise AMX-FP16 to KVM userspace. This is safe because there are no
new VMX controls or additional host enabling required for guests to use
this feature.
Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Signed-off-by: Jiaxi Chen <jiaxi.chen@linux.intel.com>
Acked-by: Borislav Petkov <bp@suse.de>
Message-Id: <20221125125845.1182922-5-jiaxi.chen@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
Diffstat (limited to 'arch/x86/kvm')
| -rw-r--r-- | arch/x86/kvm/cpuid.c | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index 2f263ff911d6..6360075ca70f 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -663,7 +663,7 @@ void kvm_set_cpu_caps(void) kvm_cpu_cap_set(X86_FEATURE_SPEC_CTRL_SSBD); kvm_cpu_cap_mask(CPUID_7_1_EAX, - F(AVX_VNNI) | F(AVX512_BF16) | F(CMPCCXADD) + F(AVX_VNNI) | F(AVX512_BF16) | F(CMPCCXADD) | F(AMX_FP16) ); kvm_cpu_cap_mask(CPUID_D_1_EAX, |