On Mon, Dec 07, 2020 at 07:34:40PM -0800, Kyung Min Park wrote: > Enumerate AVX512 Half-precision floating point (FP16) CPUID feature > flag. Compared with using FP32, using FP16 cut the number of bits > required for storage in half, reducing the exponent from 8 bits to 5, > and the mantissa from 23 bits to 10. Using FP16 also enables developers > to train and run inference on deep learning models fast when all > precision or magnitude (FP32) is not needed. > > A processor supports AVX512 FP16 if CPUID.(EAX=7,ECX=0):EDX[bit 23] > is present. The AVX512 FP16 requires AVX512BW feature be implemented > since the instructions for manipulating 32bit masks are associated with > AVX512BW. > > The only in-kernel usage of this is kvm passthrough. The CPU feature > flag is shown as "avx512_fp16" in /proc/cpuinfo. > > Signed-off-by: Kyung Min Park <kyung.min.park@xxxxxxxxx> > Acked-by: Dave Hansen <dave.hansen@xxxxxxxxx> > Reviewed-by: Tony Luck <tony.luck@xxxxxxxxx> > --- > arch/x86/include/asm/cpufeatures.h | 1 + > arch/x86/kernel/cpu/cpuid-deps.c | 1 + > 2 files changed, 2 insertions(+) > > diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h > index b6b9b3407c22..bec37ec7101e 100644 > --- a/arch/x86/include/asm/cpufeatures.h > +++ b/arch/x86/include/asm/cpufeatures.h > @@ -375,6 +375,7 @@ > #define X86_FEATURE_TSXLDTRK (18*32+16) /* TSX Suspend Load Address Tracking */ > #define X86_FEATURE_PCONFIG (18*32+18) /* Intel PCONFIG */ > #define X86_FEATURE_ARCH_LBR (18*32+19) /* Intel ARCH LBR */ > +#define X86_FEATURE_AVX512_FP16 (18*32+23) /* AVX512 FP16 */ > #define X86_FEATURE_SPEC_CTRL (18*32+26) /* "" Speculation Control (IBRS + IBPB) */ > #define X86_FEATURE_INTEL_STIBP (18*32+27) /* "" Single Thread Indirect Branch Predictors */ > #define X86_FEATURE_FLUSH_L1D (18*32+28) /* Flush L1D cache */ > diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c > index d502241995a3..42af31b64c2c 100644 > --- a/arch/x86/kernel/cpu/cpuid-deps.c > +++ b/arch/x86/kernel/cpu/cpuid-deps.c > @@ -69,6 +69,7 @@ static const struct cpuid_dep cpuid_deps[] = { > { X86_FEATURE_CQM_MBM_TOTAL, X86_FEATURE_CQM_LLC }, > { X86_FEATURE_CQM_MBM_LOCAL, X86_FEATURE_CQM_LLC }, > { X86_FEATURE_AVX512_BF16, X86_FEATURE_AVX512VL }, > + { X86_FEATURE_AVX512_FP16, X86_FEATURE_AVX512BW }, > { X86_FEATURE_ENQCMD, X86_FEATURE_XSAVES }, > { X86_FEATURE_PER_THREAD_MBA, X86_FEATURE_MBA }, > {} > -- Acked-by: Borislav Petkov <bp@xxxxxxx> Paolo, you can pick those up if you prefer. Thx. -- Regards/Gruss, Boris. https://people.kernel.org/tglx/notes-about-netiquette