kvm: x86: Add AVX512_4VNNIW and AVX512_4FMAPS support
authorLuwei Kang <luwei.kang@intel.com>
Mon, 7 Nov 2016 06:03:20 +0000 (14:03 +0800)
committerRadim Krčmář <rkrcmar@redhat.com>
Wed, 16 Nov 2016 21:20:02 +0000 (22:20 +0100)
commit4504b5c9414c55da37f26b1faf49c09a2acbf255
treed5995df6a9eaa842c2317d516ae31c6255e478a3
parent283c95d0e3891b64087706b344a4b545d04a6e62
kvm: x86: Add AVX512_4VNNIW and AVX512_4FMAPS support

Add two new AVX512 subfeatures support for KVM guest.

AVX512_4VNNIW:
Vector instructions for deep learning enhanced word variable precision.

AVX512_4FMAPS:
Vector instructions for deep learning floating-point single precision.

Reviewed-by: Borislav Petkov <bp@suse.de>
Signed-off-by: He Chen <he.chen@linux.intel.com>
Signed-off-by: Luwei Kang <luwei.kang@intel.com>
[Changed subject tags.]
Signed-off-by: Radim Krčmář <rkrcmar@redhat.com>
arch/x86/kvm/cpuid.c