summary refs log tree commit diff stats
diff options
context:
space:
mode:
authorJiaxi Chen <jiaxi.chen@linux.intel.com>2023-03-03 14:59:09 +0800
committerPaolo Bonzini <pbonzini@redhat.com>2023-04-28 12:50:34 +0200
commit99ed8445ea27742a4df40f51a3a5fbd6f8e76fa5 (patch)
tree867e9860d0c607646a3b5bf602cb22cd43b6bffa
parenta9ce107fd0f2017af84255a9cf6542fa3eb3e214 (diff)
downloadfocaccia-qemu-99ed8445ea27742a4df40f51a3a5fbd6f8e76fa5.tar.gz
focaccia-qemu-99ed8445ea27742a4df40f51a3a5fbd6f8e76fa5.zip
target/i386: Add support for AMX-FP16 in CPUID enumeration
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. AMX-FP16 adds FP16
capability and 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]

Add CPUID definition for AMX-FP16.

Signed-off-by: Jiaxi Chen <jiaxi.chen@linux.intel.com>
Signed-off-by: Tao Su <tao1.su@linux.intel.com>
Reviewed-by: Xiaoyao Li <xiaoyao.li@intel.com>
Message-Id: <20230303065913.1246327-3-tao1.su@linux.intel.com>
Signed-off-by: Paolo Bonzini <pbonzini@redhat.com>
-rw-r--r--target/i386/cpu.c2
-rw-r--r--target/i386/cpu.h2
2 files changed, 3 insertions, 1 deletions
diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index 67210ffd79..841c407d6d 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -879,7 +879,7 @@ FeatureWordInfo feature_word_info[FEATURE_WORDS] = {
             NULL, NULL, "fzrm", "fsrs",
             "fsrc", NULL, NULL, NULL,
             NULL, NULL, NULL, NULL,
-            NULL, NULL, NULL, NULL,
+            NULL, "amx-fp16", NULL, NULL,
             NULL, NULL, NULL, NULL,
             NULL, NULL, NULL, NULL,
         },
diff --git a/target/i386/cpu.h b/target/i386/cpu.h
index d5843c1555..7deb37eca5 100644
--- a/target/i386/cpu.h
+++ b/target/i386/cpu.h
@@ -915,6 +915,8 @@ uint64_t x86_cpu_get_supported_feature_word(FeatureWord w,
 #define CPUID_7_1_EAX_FSRS              (1U << 11)
 /* Fast Short REP CMPS/SCAS */
 #define CPUID_7_1_EAX_FSRC              (1U << 12)
+/* Support Tile Computational Operations on FP16 Numbers */
+#define CPUID_7_1_EAX_AMX_FP16          (1U << 21)
 
 /* XFD Extend Feature Disabled */
 #define CPUID_D_1_EAX_XFD               (1U << 4)