On 10/28/24 03:45, Tao Su wrote:
AVX10 state enumeration in CPUID leaf D and enabling in XCR0 register
are identical to AVX512 state regardless of the supported vector lengths.
Given that some E-cores will support AVX10 but not support AVX512, add
AVX512 state components to guest when AVX10 is enabled.
Tested-by: Xuelian Guo <xuelian....@intel.com>
Signed-off-by: Tao Su <tao1...@linux.intel.com>
---
target/i386/cpu.c | 14 ++++++++++++++
target/i386/cpu.h | 2 ++
2 files changed, 16 insertions(+)
diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index 1ff1af032e..d845ff5e4e 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -7177,6 +7177,13 @@ static void x86_cpu_reset_hold(Object *obj, ResetType
type)
}
if (env->features[esa->feature] & esa->bits) {
xcr0 |= 1ull << i;
+ continue;
+ }
+ if (i == XSTATE_OPMASK_BIT || i == XSTATE_ZMM_Hi256_BIT ||
+ i == XSTATE_Hi16_ZMM_BIT) {
Can you confirm that XSTATE_ZMM_Hi256_BIT depends on AVX10 and not
AVX10-512?
Thanks,
Paolo
+ if (env->features[FEAT_7_1_EDX] & CPUID_7_1_EDX_AVX10) {
+ xcr0 |= 1ull << i;
+ }
}
}
@@ -7315,6 +7322,13 @@ static void x86_cpu_enable_xsave_components(X86CPU *cpu)
const ExtSaveArea *esa = &x86_ext_save_areas[i];
if (env->features[esa->feature] & esa->bits) {
mask |= (1ULL << i);
+ continue;
+ }
+ if (i == XSTATE_OPMASK_BIT || i == XSTATE_ZMM_Hi256_BIT ||
+ i == XSTATE_Hi16_ZMM_BIT) {
+ if (env->features[FEAT_7_1_EDX] & CPUID_7_1_EDX_AVX10) {
+ mask |= (1ULL << i);
+ }
}
}
diff --git a/target/i386/cpu.h b/target/i386/cpu.h
index 74886d1580..280bec701c 100644
--- a/target/i386/cpu.h
+++ b/target/i386/cpu.h
@@ -972,6 +972,8 @@ uint64_t x86_cpu_get_supported_feature_word(X86CPU *cpu,
FeatureWord w);
#define CPUID_7_1_EDX_AMX_COMPLEX (1U << 8)
/* PREFETCHIT0/1 Instructions */
#define CPUID_7_1_EDX_PREFETCHITI (1U << 14)
+/* Support for Advanced Vector Extensions 10 */
+#define CPUID_7_1_EDX_AVX10 (1U << 19)
/* Flexible return and event delivery (FRED) */
#define CPUID_7_1_EAX_FRED (1U << 17)
/* Load into IA32_KERNEL_GS_BASE (LKGS) */