Skip to contentSkip to conversation

Enumerate and expose AVX_VNNI feature

PATCH Applied Yang Zhong 3 participants 9 messages Jan 5, 2021 – Jan 22, 2021

Subsystems (3)
lore
Share & tools
lore

Yang Zhong

author
#0 lore raw

cover Enumerate and expose AVX_VNNI feature

A processor supports AVX_VNNI instructions if CPUID.(EAX=7,ECX=1):EAX[bit 4] is present.

This series includes kernel and kvm patches, kernel patch define this new cpu feature bit and kvm expose this bit to guest. When this bit is enabled on cpu or vcpu, the cpu feature flag is shown as "avx_vnni" in /proc/cpuinfo of host and guest.

Detailed information on the instruction and CPUID feature flag can be found in the latest "extensions" manual [1].

Reference:
[1]. https://software.intel.com/content/www/us/en/develop/download/intel-architecture-instruction-set-extensions-programming-reference.html

Kyung Min Park (1):
Enumerate AVX Vector Neural Network instructions

Yang Zhong (1):
KVM: Expose AVX_VNNI instruction to guset

 arch/x86/include/asm/cpufeatures.h | 1 +
 arch/x86/kvm/cpuid.c               | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)
Signature · 1 line
2.29.2.334.gfaefdd61ec
author
#1 lore raw

PATCH 1/2 Enumerate AVX Vector Neural Network instructions

From: Kyung Min Park <[email protected]>

Add AVX version of the Vector Neural Network (VNNI) Instructions.

A processor supports AVX VNNI instructions if CPUID.0x07.0x1:EAX[4] is present. The following instructions are available when this feature is present.
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

The only in-kernel usage of this is kvm passthrough. The CPU feature flag is shown as "avx_vnni" in /proc/cpuinfo.

This instruction is currently documented in the latest "extensions" manual (ISE). It will appear in the "main" manual (SDM) in the future.

---
 arch/x86/include/asm/cpufeatures.h | 1 +
 1 file changed, 1 insertion(+)
arch/x86/include/asm/cpufeatures.h +1 -0
index f5ef2d5b9231..d10d9962bd9b 100644
@@ -293,6 +293,7 @@
 #define X86_FEATURE_PER_THREAD_MBA	(11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */
 
 /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
+#define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */
 #define X86_FEATURE_AVX512_BF16		(12*32+ 5) /* AVX512 BFLOAT16 instructions */
 
 /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
Signature · 1 line
2.29.2.334.gfaefdd61ec
maintainer
#2 lore raw

Re: [PATCH 1/2] Enumerate AVX Vector Neural Network instructions

Quoted 31 lines · Yang Zhong

From: Kyung Min Park <[email protected]>

Add AVX version of the Vector Neural Network (VNNI) Instructions.

A processor supports AVX VNNI instructions if CPUID.0x07.0x1:EAX[4] is present. The following instructions are available when this feature is present.
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

The only in-kernel usage of this is kvm passthrough. The CPU feature flag is shown as "avx_vnni" in /proc/cpuinfo.

This instruction is currently documented in the latest "extensions" manual (ISE). It will appear in the "main" manual (SDM) in the future.

---
  arch/x86/include/asm/cpufeatures.h | 1 +
  1 file changed, 1 insertion(+)
arch/x86/include/asm/cpufeatures.h +0 -0
index f5ef2d5b9231..d10d9962bd9b 100644

arch/x86/include/asm/cpufeatures.h line 299

Quoted 7 lines
arch/x86/include/asm/cpufeatures.h +1 -0
@@ -293,6 +293,7 @@
  #define X86_FEATURE_PER_THREAD_MBA	(11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */
 
  /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
+#define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */
  #define X86_FEATURE_AVX512_BF16		(12*32+ 5) /* AVX512 BFLOAT16 instructions */
 
  /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */

Boris, is it possible to have a topic branch for this patch?

maintainer Acked-by
#3 lore raw

Re: [PATCH 1/2] Enumerate AVX Vector Neural Network instructions

Quoted 26 lines · Paolo Bonzini
Quoted 25 lines · Yang Zhong

From: Kyung Min Park <[email protected]>

Add AVX version of the Vector Neural Network (VNNI) Instructions.

A processor supports AVX VNNI instructions if CPUID.0x07.0x1:EAX[4] is present. The following instructions are available when this feature is present.
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

The only in-kernel usage of this is kvm passthrough. The CPU feature flag is shown as "avx_vnni" in /proc/cpuinfo.

This instruction is currently documented in the latest "extensions" manual (ISE). It will appear in the "main" manual (SDM) in the future.

---
  arch/x86/include/asm/cpufeatures.h | 1 +
  1 file changed, 1 insertion(+)
Quoted 13 lines

arch/x86/include/asm/cpufeatures.h line 298

Quoted 11 lines
arch/x86/include/asm/cpufeatures.h +1 -0
index f5ef2d5b9231..d10d9962bd9b 100644
@@ -293,6 +293,7 @@
  #define X86_FEATURE_PER_THREAD_MBA	(11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */
  /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
+#define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */
  #define X86_FEATURE_AVX512_BF16		(12*32+ 5) /* AVX512 BFLOAT16 instructions */
  /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
 

Boris, is it possible to have a topic branch for this patch?

Just take it through your tree pls.

Thx.

Signature · 4 lines
Regards/Gruss,
    Boris.

https://people.kernel.org/tglx/notes-about-netiquette
author
#4 lore raw

Re: [PATCH 1/2] Enumerate AVX Vector Neural Network instructions

Quoted 41 lines · Borislav Petkov
Quoted 26 lines · Paolo Bonzini
Quoted 25 lines · Yang Zhong

From: Kyung Min Park <[email protected]>

Add AVX version of the Vector Neural Network (VNNI) Instructions.

A processor supports AVX VNNI instructions if CPUID.0x07.0x1:EAX[4] is present. The following instructions are available when this feature is present.
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

The only in-kernel usage of this is kvm passthrough. The CPU feature flag is shown as "avx_vnni" in /proc/cpuinfo.

This instruction is currently documented in the latest "extensions" manual (ISE). It will appear in the "main" manual (SDM) in the future.

---
  arch/x86/include/asm/cpufeatures.h | 1 +
  1 file changed, 1 insertion(+)
Quoted 13 lines

arch/x86/include/asm/cpufeatures.h line 298

Quoted 11 lines
arch/x86/include/asm/cpufeatures.h +1 -0
index f5ef2d5b9231..d10d9962bd9b 100644
@@ -293,6 +293,7 @@
  #define X86_FEATURE_PER_THREAD_MBA	(11*32+ 7) /* "" Per-thread Memory Bandwidth Allocation */
  /* Intel-defined CPU features, CPUID level 0x00000007:1 (EAX), word 12 */
+#define X86_FEATURE_AVX_VNNI		(12*32+ 4) /* AVX VNNI instructions */
  #define X86_FEATURE_AVX512_BF16		(12*32+ 5) /* AVX512 BFLOAT16 instructions */
  /* AMD-defined CPU features, CPUID level 0x80000008 (EBX), word 13 */
 

Boris, is it possible to have a topic branch for this patch?

Quoted 4 lines

Just take it through your tree pls.

Paolo, Boris has acked this kernel patch, and if i need send new patchset to add this acked-by info ? or kvm tree will directly pull this patchset? thanks.

Yang

Quoted 7 lines

Thx.

Signature · 4 lines
Regards/Gruss,
    Boris.

https://people.kernel.org/tglx/notes-about-netiquette
maintainer
#5 lore raw

Re: [PATCH 1/2] Enumerate AVX Vector Neural Network instructions

Quoted 9 lines
Quoted 6 lines
Quoted 1 line

Boris, is it possible to have a topic branch for this patch?

Just take it through your tree pls.

Paolo, Boris has acked this kernel patch, and if i need send new patchset to add this acked-by info ? or kvm tree will directly pull this patchset? thanks.

I'll take care of it shortly.

Paolo

author
#6 lore raw

PATCH 2/2 KVM: Expose AVX_VNNI instruction to guset

In reply to Yang Zhong

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

This instruction is currently documented in the latest "extensions" manual (ISE). It will appear in the "main" manual (SDM) in the future.

---
 arch/x86/kvm/cpuid.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)
arch/x86/kvm/cpuid.c +1 -1
index 83637a2ff605..4229b67f0a8d 100644
@@ -433,7 +433,7 @@ void kvm_set_cpu_caps(void)
 		kvm_cpu_cap_set(X86_FEATURE_SPEC_CTRL_SSBD);
 
 	kvm_cpu_cap_mask(CPUID_7_1_EAX,
-		F(AVX512_BF16)
+		F(AVX_VNNI) | F(AVX512_BF16)
 	);
 
 	kvm_cpu_cap_mask(CPUID_D_1_EAX,
Signature · 1 line
2.29.2.334.gfaefdd61ec
maintainer Applied
#7 lore raw
In reply to Yang Zhong
Quoted 18 lines · Yang Zhong

A processor supports AVX_VNNI instructions if CPUID.(EAX=7,ECX=1):EAX[bit 4] is present.

This series includes kernel and kvm patches, kernel patch define this new cpu feature bit and kvm expose this bit to guest. When this bit is enabled on cpu or vcpu, the cpu feature flag is shown as "avx_vnni" in /proc/cpuinfo of host and guest.

Detailed information on the instruction and CPUID feature flag can be found in the latest "extensions" manual [1].

Reference:
[1]. https://software.intel.com/content/www/us/en/develop/download/intel-architecture-instruction-set-extensions-programming-reference.html

Kyung Min Park (1):
Enumerate AVX Vector Neural Network instructions

Quoted 7 lines

Yang Zhong (1):
KVM: Expose AVX_VNNI instruction to guset

  arch/x86/include/asm/cpufeatures.h | 1 +
  arch/x86/kvm/cpuid.c               | 2 +-
  2 files changed, 2 insertions(+), 1 deletion(-)

Queued, thanks.

Paolo

author
#8 lore raw
Quoted 22 lines · Paolo Bonzini
Quoted 21 lines · Yang Zhong

A processor supports AVX_VNNI instructions if CPUID.(EAX=7,ECX=1):EAX[bit 4] is present.

This series includes kernel and kvm patches, kernel patch define this new cpu feature bit and kvm expose this bit to guest. When this bit is enabled on cpu or vcpu, the cpu feature flag is shown as "avx_vnni" in /proc/cpuinfo of host and guest.

Detailed information on the instruction and CPUID feature flag can be found in the latest "extensions" manual [1].

Reference:
[1]. https://software.intel.com/content/www/us/en/develop/download/intel-architecture-instruction-set-extensions-programming-reference.html

Kyung Min Park (1):
Enumerate AVX Vector Neural Network instructions

Yang Zhong (1):
KVM: Expose AVX_VNNI instruction to guset

Quoted 8 lines
Quoted 4 lines
 arch/x86/include/asm/cpufeatures.h | 1 +
 arch/x86/kvm/cpuid.c               | 2 +-
 2 files changed, 2 insertions(+), 1 deletion(-)

Queued, thanks.

Paolo

Paolo, thanks, i will send the related Qemu patch soon.

Yang