On 2020-12-16 at 23:40 CET, Cathy Zhang wrote... > AVX512 Half-precision floating point (FP16) has better performance > compared to FP32 if the presicion or magnitude requirements are met.
spelling: precision > It's defined as CPUID.(EAX=7,ECX=0):EDX[bit 23]. > > Refer to > https://software.intel.com/content/www/us/en/develop/download/\ > intel-architecture-instruction-set-extensions-programming-reference.html > > Signed-off-by: Cathy Zhang <cathy.zh...@intel.com> > --- > target/i386/cpu.c | 2 +- > target/i386/cpu.h | 2 ++ > 2 files changed, 3 insertions(+), 1 deletion(-) > > diff --git a/target/i386/cpu.c b/target/i386/cpu.c > index ca997a68cd..c4d623b8b9 100644 > --- a/target/i386/cpu.c > +++ b/target/i386/cpu.c > @@ -979,7 +979,7 @@ static FeatureWordInfo feature_word_info[FEATURE_WORDS] = > { > "avx512-vp2intersect", NULL, "md-clear", NULL, > NULL, NULL, "serialize", NULL, > "tsx-ldtrk", NULL, NULL /* pconfig */, NULL, > - NULL, NULL, NULL, NULL, > + NULL, NULL, NULL, "avx512-fp16", > NULL, NULL, "spec-ctrl", "stibp", > NULL, "arch-capabilities", "core-capability", "ssbd", > }, > diff --git a/target/i386/cpu.h b/target/i386/cpu.h > index c4a49c06a8..6fd675c654 100644 > --- a/target/i386/cpu.h > +++ b/target/i386/cpu.h > @@ -784,6 +784,8 @@ typedef uint64_t FeatureWordArray[FEATURE_WORDS]; > #define CPUID_7_0_EDX_SERIALIZE (1U << 14) > /* TSX Suspend Load Address Tracking instruction */ > #define CPUID_7_0_EDX_TSX_LDTRK (1U << 16) > +/* AVX512_FP16 instruction */ > +#define CPUID_7_0_EDX_AVX512_FP16 (1U << 23) > /* Speculation Control */ > #define CPUID_7_0_EDX_SPEC_CTRL (1U << 26) > /* Single Thread Indirect Branch Predictors */ -- Cheers, Christophe de Dinechin (IRC c3d)
