[v2,1/6] i386: Introduce FeatureWordInfo for AMX CPUID leaf 0x1D and 0x1E

Commit Message

Wang, Lei Nov. 2, 2022, 8:54 a.m. UTC

CPUID leaf 0x1D and 0x1E enumerate tile and TMUL information for AMX.

Introduce FeatureWord FEAT_1D_1_EAX, FEAT_1D_1_EBX, FEAT_1D_1_ECX and
FEAT_1E_0_EBX. Thus these features of AMX can be expanded when
"-cpu host/max" and can be configured in named CPU model.

Signed-off-by: Wang, Lei <[e-mail]>
---
 target/i386/cpu.c | 55 +++++++++++++++++++++++++++++++++++++++++++++++
 target/i386/cpu.h | 12 +++++++++++
 2 files changed, 67 insertions(+)

Patch

diff --git a/target/i386/cpu.c b/target/i386/cpu.c
index 8a11470507..e98780773c 100644
--- a/target/i386/cpu.c
+++ b/target/i386/cpu.c
@@ -1002,6 +1002,45 @@  FeatureWordInfo feature_word_info[FEATURE_WORDS] = {
         },
         .tcg_features = ~0U,
     },
+    [FEAT_1D_1_EAX] = {
+        .type = CPUID_FEATURE_WORD,
+        .cpuid = {
+            .eax = 0x1D,
+            .needs_ecx = true, .ecx = 1,
+            .reg = R_EAX,
+        },
+        .migratable_flags = CPUID_AMX_PALETTE_1_TOTAL_TILE_BYTES_MASK |
+            CPUID_AMX_PALETTE_1_BYTES_PER_TILE_MASK,
+    },
+    [FEAT_1D_1_EBX] = {
+        .type = CPUID_FEATURE_WORD,
+        .cpuid = {
+            .eax = 0x1D,
+            .needs_ecx = true, .ecx = 1,
+            .reg = R_EBX,
+        },
+        .migratable_flags = CPUID_AMX_PALETTE_1_BYTES_PER_ROW_MASK |
+            CPUID_AMX_PALETTE_1_MAX_NAMES_MASK,
+    },
+    [FEAT_1D_1_ECX] = {
+        .type = CPUID_FEATURE_WORD,
+        .cpuid = {
+            .eax = 0x1D,
+            .needs_ecx = true, .ecx = 1,
+            .reg = R_ECX,
+        },
+        .migratable_flags = CPUID_AMX_PALETTE_1_MAX_ROWS_MASK,
+    },
+    [FEAT_1E_0_EBX] = {
+        .type = CPUID_FEATURE_WORD,
+        .cpuid = {
+            .eax = 0x1E,
+            .needs_ecx = true, .ecx = 0,
+            .reg = R_EBX,
+        },
+        .migratable_flags = CPUID_AMX_TMUL_MAX_K_MASK |
+            CPUID_AMX_TMUL_MAX_N_MASK,
+    },
     /*Below are MSR exposed features*/
     [FEAT_ARCH_CAPABILITIES] = {
         .type = MSR_FEATURE_WORD,
@@ -1371,6 +1410,22 @@  static FeatureDep feature_dependencies[] = {
         .from = { FEAT_7_0_EBX,             CPUID_7_0_EBX_INTEL_PT },
         .to = { FEAT_14_0_ECX,              ~0ull },
     },
+    {
+        .from = { FEAT_7_0_EDX,             CPUID_7_0_EDX_AMX_TILE },
+        .to = { FEAT_1D_1_EAX,              ~0ull },
+    },
+    {
+        .from = { FEAT_7_0_EDX,             CPUID_7_0_EDX_AMX_TILE },
+        .to = { FEAT_1D_1_EBX,              ~0ull },
+    },
+    {
+        .from = { FEAT_7_0_EDX,             CPUID_7_0_EDX_AMX_TILE },
+        .to = { FEAT_1D_1_ECX,              ~0ull },
+    },
+    {
+        .from = { FEAT_7_0_EDX,             CPUID_7_0_EDX_AMX_TILE },
+        .to = { FEAT_1E_0_EBX,              ~0ull },
+    },
     {
         .from = { FEAT_8000_0001_EDX,       CPUID_EXT2_RDTSCP },
         .to = { FEAT_VMX_SECONDARY_CTLS,    VMX_SECONDARY_EXEC_RDTSCP },
diff --git a/target/i386/cpu.h b/target/i386/cpu.h
index 7edf5dfac3..1c90fb6c9d 100644
--- a/target/i386/cpu.h
+++ b/target/i386/cpu.h
@@ -583,6 +583,14 @@  typedef enum X86Seg {
                                  XSTATE_Hi16_ZMM_MASK | XSTATE_PKRU_MASK | \
                                  XSTATE_XTILE_CFG_MASK | XSTATE_XTILE_DATA_MASK)
 
+#define CPUID_AMX_PALETTE_1_TOTAL_TILE_BYTES_MASK 0xffffU
+#define CPUID_AMX_PALETTE_1_BYTES_PER_TILE_MASK   (0xffffU << 16)
+#define CPUID_AMX_PALETTE_1_BYTES_PER_ROW_MASK    0xffffU
+#define CPUID_AMX_PALETTE_1_MAX_NAMES_MASK        (0xffffU << 16)
+#define CPUID_AMX_PALETTE_1_MAX_ROWS_MASK         0xffffU
+#define CPUID_AMX_TMUL_MAX_K_MASK                 0xffU
+#define CPUID_AMX_TMUL_MAX_N_MASK                 (0xffffU << 8)
+
 /* CPUID feature words */
 typedef enum FeatureWord {
     FEAT_1_EDX,         /* CPUID[1].EDX */
@@ -603,6 +611,10 @@  typedef enum FeatureWord {
     FEAT_6_EAX,         /* CPUID[6].EAX */
     FEAT_XSAVE_XCR0_LO, /* CPUID[EAX=0xd,ECX=0].EAX */
     FEAT_XSAVE_XCR0_HI, /* CPUID[EAX=0xd,ECX=0].EDX */
+    FEAT_1D_1_EAX,      /* CPUID[EAX=0x1d,ECX=1].EAX */
+    FEAT_1D_1_EBX,      /* CPUID[EAX=0x1d,ECX=1].EBX */
+    FEAT_1D_1_ECX,      /* CPUID[EAX=0x1d,ECX=1].ECX */
+    FEAT_1E_0_EBX,      /* CPUID[EAX=0x1e,ECX=0].EBX */
     FEAT_ARCH_CAPABILITIES,
     FEAT_CORE_CAPABILITY,
     FEAT_PERF_CAPABILITIES,