mirrors/linux
1
0
Fork 1
mirror of https://github.com/torvalds/linux.git synced 2025-11-04 10:40:15 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions

x86: KVM: Advertise AMX-FP16 CPUID to user space

Browse source 
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>
This commit is contained in:
Chang S. Bae 2022-11-25 20:58:41 +08:00 committed by Paolo Bonzini
parent 6a19d7aa58
commit af2872f622
2 changed files with 2 additions and 1 deletions
repo.diff.show_diff_stats Download patch file Download diff file Expand all files Collapse all files

1
arch/x86/include/asm/cpufeatures.h
View file

@ -309,6 +309,7 @@
#define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */ #define X86_FEATURE_AVX_VNNI (12*32+ 4) /* AVX VNNI instructions */
#define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */ #define X86_FEATURE_AVX512_BF16 (12*32+ 5) /* AVX512 BFLOAT16 instructions */
#define X86_FEATURE_CMPCCXADD (12*32+ 7) /* "" CMPccXADD instructions */ #define X86_FEATURE_CMPCCXADD (12*32+ 7) /* "" CMPccXADD instructions */
#define X86_FEATURE_AMX_FP16 (12*32+21) /* "" AMX fp16 Support */
/* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */ /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
#define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */ #define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */

2
arch/x86/kvm/cpuid.c
View file

@ -663,7 +663,7 @@ void kvm_set_cpu_caps(void)
kvm_cpu_cap_set(X86_FEATURE_SPEC_CTRL_SSBD); kvm_cpu_cap_set(X86_FEATURE_SPEC_CTRL_SSBD);
kvm_cpu_cap_mask(CPUID_7_1_EAX, 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, kvm_cpu_cap_mask(CPUID_D_1_EAX,