From: Jiaxi Chen <jiaxi.chen@linux.intel.com>
To: kvm@vger.kernel.org
Cc: tglx@linutronix.de, mingo@redhat.com, bp@alien8.de,
dave.hansen@linux.intel.com, x86@kernel.org, hpa@zytor.com,
seanjc@google.com, pbonzini@redhat.com, ndesaulniers@google.com,
alexandre.belloni@bootlin.com, peterz@infradead.org,
jiaxi.chen@linux.intel.com, jpoimboe@kernel.org,
chang.seok.bae@intel.com, pawan.kumar.gupta@linux.intel.com,
babu.moger@amd.com, jmattson@google.com, sandipan.das@amd.com,
tony.luck@intel.com, sathyanarayanan.kuppuswamy@linux.intel.com,
fenghua.yu@intel.com, keescook@chromium.org,
jane.malalane@citrix.com, nathan@kernel.org,
linux-kernel@vger.kernel.org
Subject: [PATCH 2/6] x86: KVM: Enable AMX-FP16 CPUID and expose it to guest
Date: Wed, 19 Oct 2022 16:47:30 +0800 [thread overview]
Message-ID: <20221019084734.3590760-3-jiaxi.chen@linux.intel.com> (raw)
In-Reply-To: <20221019084734.3590760-1-jiaxi.chen@linux.intel.com>
From: "Chang S. Bae" <chang.seok.bae@intel.com>
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. This instruction 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]
This patch enables this CPUID in the kernel feature bits and expose it
to guest OS.
Signed-off-by: Chang S. Bae <chang.seok.bae@intel.com>
Signed-off-by: Jiaxi Chen <jiaxi.chen@linux.intel.com>
---
arch/x86/include/asm/cpufeatures.h | 1 +
arch/x86/kvm/cpuid.c | 2 +-
2 files changed, 2 insertions(+), 1 deletion(-)
diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h
index 445626cb5779..9313240e3cdd 100644
--- a/arch/x86/include/asm/cpufeatures.h
+++ b/arch/x86/include/asm/cpufeatures.h
@@ -309,6 +309,7 @@
#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_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 */
#define X86_FEATURE_CLZERO (13*32+ 0) /* CLZERO instruction */
diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c
index 3f745f6fdc43..d983ddb974ba 100644
--- a/arch/x86/kvm/cpuid.c
+++ b/arch/x86/kvm/cpuid.c
@@ -657,7 +657,7 @@ 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,
--
2.27.0
next prev parent reply other threads:[~2022-10-19 8:53 UTC|newest]
Thread overview: 24+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-10-19 8:47 [PATCH 0/6] x86: KVM: Expose CPUID to guest for new Intel platform instructions Jiaxi Chen
2022-10-19 8:47 ` [PATCH 1/6] x86: KVM: Enable CMPccXADD CPUID and expose it to guest Jiaxi Chen
2022-10-19 15:15 ` Sean Christopherson
2022-10-20 7:27 ` Chen, Jiaxi
2022-10-26 3:40 ` Jiaxi Chen
2022-10-26 17:15 ` Borislav Petkov
2022-10-27 2:27 ` Jiaxi Chen
2022-11-01 9:07 ` Jiaxi Chen
2022-11-01 15:07 ` Sean Christopherson
2022-11-03 2:35 ` Jiaxi Chen
2022-10-19 8:47 ` Jiaxi Chen [this message]
2022-11-02 18:14 ` [PATCH 2/6] x86: KVM: Enable AMX-FP16 " Dave Hansen
2022-11-02 18:16 ` Paolo Bonzini
2022-11-02 18:21 ` Dave Hansen
2022-11-03 2:38 ` Jiaxi Chen
2022-10-19 8:47 ` [PATCH 3/6] x86: KVM: Enable AVX-IFMA " Jiaxi Chen
2022-10-19 8:47 ` [PATCH 4/6] x86: KVM: Enable AVX-VNNI-INT8 " Jiaxi Chen
2022-10-19 8:52 ` Borislav Petkov
2022-10-19 14:57 ` Sean Christopherson
2022-10-19 15:09 ` Sean Christopherson
2022-10-26 3:33 ` Jiaxi Chen
2022-10-20 7:13 ` Chen, Jiaxi
2022-10-19 8:47 ` [PATCH 5/6] x86: KVM: Enable AVX-NE-CONVERT " Jiaxi Chen
2022-10-19 8:47 ` [PATCH 6/6] x86: KVM: Enable PREFETCHIT0/1 " Jiaxi Chen
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20221019084734.3590760-3-jiaxi.chen@linux.intel.com \
--to=jiaxi.chen@linux.intel.com \
--cc=alexandre.belloni@bootlin.com \
--cc=babu.moger@amd.com \
--cc=bp@alien8.de \
--cc=chang.seok.bae@intel.com \
--cc=dave.hansen@linux.intel.com \
--cc=fenghua.yu@intel.com \
--cc=hpa@zytor.com \
--cc=jane.malalane@citrix.com \
--cc=jmattson@google.com \
--cc=jpoimboe@kernel.org \
--cc=keescook@chromium.org \
--cc=kvm@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@redhat.com \
--cc=nathan@kernel.org \
--cc=ndesaulniers@google.com \
--cc=pawan.kumar.gupta@linux.intel.com \
--cc=pbonzini@redhat.com \
--cc=peterz@infradead.org \
--cc=sandipan.das@amd.com \
--cc=sathyanarayanan.kuppuswamy@linux.intel.com \
--cc=seanjc@google.com \
--cc=tglx@linutronix.de \
--cc=tony.luck@intel.com \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).