Merge branch 'main' into users/mingmingl-llvm/samplefdo-profile-formatusers/mingmingl-llvm/samplefdo-profile-format

5 files changed, 408 insertions, 412 deletions

diff --git a/llvm/lib/TargetParser/Host.cpp b/llvm/lib/TargetParser/Host.cpp
index 24827537eb19..63848160636a 100644
--- a/llvm/lib/TargetParser/Host.cpp
+++ b/llvm/lib/TargetParser/Host.cpp
@@ -1396,7 +1396,6 @@ static void getAvailableFeatures(unsigned ECX, unsigned EDX, unsigned MaxLeaf,
     setFeature(X86::FEATURE_BMI2);
   if (HasLeaf7 && ((EBX >> 16) & 1) && HasAVX512Save) {
     setFeature(X86::FEATURE_AVX512F);
-    setFeature(X86::FEATURE_EVEX512);
   }
   if (HasLeaf7 && ((EBX >> 17) & 1) && HasAVX512Save)
     setFeature(X86::FEATURE_AVX512DQ);
@@ -2063,8 +2062,6 @@ StringMap<bool> sys::getHostCPUFeatures() {
   Features["rtm"]        = HasLeaf7 && ((EBX >> 11) & 1);
   // AVX512 is only supported if the OS supports the context save for it.
   Features["avx512f"]    = HasLeaf7 && ((EBX >> 16) & 1) && HasAVX512Save;
-  if (Features["avx512f"])
-    Features["evex512"]  = true;
   Features["avx512dq"]   = HasLeaf7 && ((EBX >> 17) & 1) && HasAVX512Save;
   Features["rdseed"]     = HasLeaf7 && ((EBX >> 18) & 1);
   Features["adx"]        = HasLeaf7 && ((EBX >> 19) & 1);
@@ -2176,11 +2173,8 @@ StringMap<bool> sys::getHostCPUFeatures() {
       MaxLevel >= 0x24 && !getX86CpuIDAndInfo(0x24, &EAX, &EBX, &ECX, &EDX);
 
   int AVX10Ver = HasLeaf24 && (EBX & 0xff);
-  int Has512Len = HasLeaf24 && ((EBX >> 18) & 1);
-  Features["avx10.1-256"] = HasAVX10 && AVX10Ver >= 1;
-  Features["avx10.1-512"] = HasAVX10 && AVX10Ver >= 1 && Has512Len;
-  Features["avx10.2-256"] = HasAVX10 && AVX10Ver >= 2;
-  Features["avx10.2-512"] = HasAVX10 && AVX10Ver >= 2 && Has512Len;
+  Features["avx10.1"] = HasAVX10 && AVX10Ver >= 1;
+  Features["avx10.2"] = HasAVX10 && AVX10Ver >= 2;
 
   return Features;
 }
diff --git a/llvm/lib/TargetParser/RISCVTargetParser.cpp b/llvm/lib/TargetParser/RISCVTargetParser.cpp
index 9957ec0c28d8..b53a1b95431a 100644
--- a/llvm/lib/TargetParser/RISCVTargetParser.cpp
+++ b/llvm/lib/TargetParser/RISCVTargetParser.cpp
@@ -153,12 +153,13 @@ namespace RISCVVType {
 //
 // Bits | Name       | Description
 // -----+------------+------------------------------------------------
+// 8    | altfmt     | Alternative format for bf16
 // 7    | vma        | Vector mask agnostic
 // 6    | vta        | Vector tail agnostic
 // 5:3  | vsew[2:0]  | Standard element width (SEW) setting
 // 2:0  | vlmul[2:0] | Vector register group multiplier (LMUL) setting
 unsigned encodeVTYPE(VLMUL VLMul, unsigned SEW, bool TailAgnostic,
-                     bool MaskAgnostic) {
+                     bool MaskAgnostic, bool AltFmt) {
   assert(isValidSEW(SEW) && "Invalid SEW");
   unsigned VLMulBits = static_cast<unsigned>(VLMul);
   unsigned VSEWBits = encodeSEW(SEW);
@@ -167,6 +168,8 @@ unsigned encodeVTYPE(VLMUL VLMul, unsigned SEW, bool TailAgnostic,
     VTypeI |= 0x40;
   if (MaskAgnostic)
     VTypeI |= 0x80;
+  if (AltFmt)
+    VTypeI |= 0x100;
 
   return VTypeI;
 }
@@ -200,6 +203,10 @@ void printVType(unsigned VType, raw_ostream &OS) {
   unsigned Sew = getSEW(VType);
   OS << "e" << Sew;
 
+  bool AltFmt = RISCVVType::isAltFmt(VType);
+  if (AltFmt)
+    OS << "alt";
+
   unsigned LMul;
   bool Fractional;
   std::tie(LMul, Fractional) = decodeVLMUL(getVLMUL(VType));
diff --git a/llvm/lib/TargetParser/TargetParser.cpp b/llvm/lib/TargetParser/TargetParser.cpp
index 50b97d325754..2194ef4df14d 100644
--- a/llvm/lib/TargetParser/TargetParser.cpp
+++ b/llvm/lib/TargetParser/TargetParser.cpp
@@ -364,8 +364,326 @@ StringRef AMDGPU::getCanonicalArchName(const Triple &T, StringRef Arch) {
   return T.isAMDGCN() ? getArchNameAMDGCN(ProcKind) : getArchNameR600(ProcKind);
 }
 
-void AMDGPU::fillAMDGPUFeatureMap(StringRef GPU, const Triple &T,
-                                  StringMap<bool> &Features) {
+static std::pair<FeatureError, StringRef>
+insertWaveSizeFeature(StringRef GPU, const Triple &T,
+                      const StringMap<bool> &DefaultFeatures,
+                      StringMap<bool> &Features) {
+  const bool IsNullGPU = GPU.empty();
+  const bool TargetHasWave32 = DefaultFeatures.count("wavefrontsize32");
+  const bool TargetHasWave64 = DefaultFeatures.count("wavefrontsize64");
+  const bool HaveWave32 = Features.count("wavefrontsize32");
+  const bool HaveWave64 = Features.count("wavefrontsize64");
+  if (HaveWave32 && HaveWave64)
+    return {AMDGPU::INVALID_FEATURE_COMBINATION,
+            "'wavefrontsize32' and 'wavefrontsize64' are mutually exclusive"};
+
+  if (HaveWave32 && !IsNullGPU && TargetHasWave64)
+    return {AMDGPU::UNSUPPORTED_TARGET_FEATURE, "wavefrontsize32"};
+
+  if (HaveWave64 && !IsNullGPU && TargetHasWave32)
+    return {AMDGPU::UNSUPPORTED_TARGET_FEATURE, "wavefrontsize64"};
+
+  // Don't assume any wavesize with an unknown subtarget.
+  // Default to wave32 if target supports both.
+  if (!IsNullGPU && !HaveWave32 && !HaveWave64 && !TargetHasWave32 &&
+      !TargetHasWave64)
+    Features.insert(std::make_pair("wavefrontsize32", true));
+
+  for (const auto &Entry : DefaultFeatures) {
+    if (!Features.count(Entry.getKey()))
+      Features[Entry.getKey()] = Entry.getValue();
+  }
+
+  return {NO_ERROR, StringRef()};
+}
+
+/// Fills Features map with default values for given target GPU.
+/// \p Features contains overriding target features and this function returns
+/// default target features with entries overridden by \p Features.
+static void fillAMDGCNFeatureMap(StringRef GPU, const Triple &T,
+                                 StringMap<bool> &Features) {
+  AMDGPU::GPUKind Kind = parseArchAMDGCN(GPU);
+  switch (Kind) {
+  case GK_GFX1250:
+    Features["ci-insts"] = true;
+    Features["dot7-insts"] = true;
+    Features["dot8-insts"] = true;
+    Features["dl-insts"] = true;
+    Features["16-bit-insts"] = true;
+    Features["dpp"] = true;
+    Features["gfx8-insts"] = true;
+    Features["gfx9-insts"] = true;
+    Features["gfx10-insts"] = true;
+    Features["gfx10-3-insts"] = true;
+    Features["gfx11-insts"] = true;
+    Features["gfx12-insts"] = true;
+    Features["gfx1250-insts"] = true;
+    Features["bitop3-insts"] = true;
+    Features["prng-inst"] = true;
+    Features["tanh-insts"] = true;
+    Features["tensor-cvt-lut-insts"] = true;
+    Features["transpose-load-f4f6-insts"] = true;
+    Features["bf16-trans-insts"] = true;
+    Features["bf16-cvt-insts"] = true;
+    Features["fp8-conversion-insts"] = true;
+    Features["fp8e5m3-insts"] = true;
+    Features["permlane16-swap"] = true;
+    Features["ashr-pk-insts"] = true;
+    Features["atomic-buffer-pk-add-bf16-inst"] = true;
+    Features["vmem-pref-insts"] = true;
+    Features["atomic-fadd-rtn-insts"] = true;
+    Features["atomic-buffer-global-pk-add-f16-insts"] = true;
+    Features["atomic-flat-pk-add-16-insts"] = true;
+    Features["atomic-global-pk-add-bf16-inst"] = true;
+    Features["atomic-ds-pk-add-16-insts"] = true;
+    Features["setprio-inc-wg-inst"] = true;
+    Features["atomic-fmin-fmax-global-f32"] = true;
+    Features["atomic-fmin-fmax-global-f64"] = true;
+    Features["wavefrontsize32"] = true;
+    break;
+  case GK_GFX1201:
+  case GK_GFX1200:
+  case GK_GFX12_GENERIC:
+    Features["ci-insts"] = true;
+    Features["dot7-insts"] = true;
+    Features["dot8-insts"] = true;
+    Features["dot9-insts"] = true;
+    Features["dot10-insts"] = true;
+    Features["dot11-insts"] = true;
+    Features["dot12-insts"] = true;
+    Features["dl-insts"] = true;
+    Features["atomic-ds-pk-add-16-insts"] = true;
+    Features["atomic-flat-pk-add-16-insts"] = true;
+    Features["atomic-buffer-global-pk-add-f16-insts"] = true;
+    Features["atomic-buffer-pk-add-bf16-inst"] = true;
+    Features["atomic-global-pk-add-bf16-inst"] = true;
+    Features["16-bit-insts"] = true;
+    Features["dpp"] = true;
+    Features["gfx8-insts"] = true;
+    Features["gfx9-insts"] = true;
+    Features["gfx10-insts"] = true;
+    Features["gfx10-3-insts"] = true;
+    Features["gfx11-insts"] = true;
+    Features["gfx12-insts"] = true;
+    Features["atomic-fadd-rtn-insts"] = true;
+    Features["image-insts"] = true;
+    Features["fp8-conversion-insts"] = true;
+    Features["atomic-fmin-fmax-global-f32"] = true;
+    break;
+  case GK_GFX1153:
+  case GK_GFX1152:
+  case GK_GFX1151:
+  case GK_GFX1150:
+  case GK_GFX1103:
+  case GK_GFX1102:
+  case GK_GFX1101:
+  case GK_GFX1100:
+  case GK_GFX11_GENERIC:
+    Features["ci-insts"] = true;
+    Features["dot5-insts"] = true;
+    Features["dot7-insts"] = true;
+    Features["dot8-insts"] = true;
+    Features["dot9-insts"] = true;
+    Features["dot10-insts"] = true;
+    Features["dot12-insts"] = true;
+    Features["dl-insts"] = true;
+    Features["16-bit-insts"] = true;
+    Features["dpp"] = true;
+    Features["gfx8-insts"] = true;
+    Features["gfx9-insts"] = true;
+    Features["gfx10-insts"] = true;
+    Features["gfx10-3-insts"] = true;
+    Features["gfx11-insts"] = true;
+    Features["atomic-fadd-rtn-insts"] = true;
+    Features["image-insts"] = true;
+    Features["gws"] = true;
+    Features["atomic-fmin-fmax-global-f32"] = true;
+    break;
+  case GK_GFX1036:
+  case GK_GFX1035:
+  case GK_GFX1034:
+  case GK_GFX1033:
+  case GK_GFX1032:
+  case GK_GFX1031:
+  case GK_GFX1030:
+  case GK_GFX10_3_GENERIC:
+    Features["ci-insts"] = true;
+    Features["dot1-insts"] = true;
+    Features["dot2-insts"] = true;
+    Features["dot5-insts"] = true;
+    Features["dot6-insts"] = true;
+    Features["dot7-insts"] = true;
+    Features["dot10-insts"] = true;
+    Features["dl-insts"] = true;
+    Features["16-bit-insts"] = true;
+    Features["dpp"] = true;
+    Features["gfx8-insts"] = true;
+    Features["gfx9-insts"] = true;
+    Features["gfx10-insts"] = true;
+    Features["gfx10-3-insts"] = true;
+    Features["image-insts"] = true;
+    Features["s-memrealtime"] = true;
+    Features["s-memtime-inst"] = true;
+    Features["gws"] = true;
+    Features["vmem-to-lds-load-insts"] = true;
+    Features["atomic-fmin-fmax-global-f32"] = true;
+    Features["atomic-fmin-fmax-global-f64"] = true;
+    break;
+  case GK_GFX1012:
+  case GK_GFX1011:
+    Features["dot1-insts"] = true;
+    Features["dot2-insts"] = true;
+    Features["dot5-insts"] = true;
+    Features["dot6-insts"] = true;
+    Features["dot7-insts"] = true;
+    Features["dot10-insts"] = true;
+    [[fallthrough]];
+  case GK_GFX1013:
+  case GK_GFX1010:
+  case GK_GFX10_1_GENERIC:
+    Features["dl-insts"] = true;
+    Features["ci-insts"] = true;
+    Features["16-bit-insts"] = true;
+    Features["dpp"] = true;
+    Features["gfx8-insts"] = true;
+    Features["gfx9-insts"] = true;
+    Features["gfx10-insts"] = true;
+    Features["image-insts"] = true;
+    Features["s-memrealtime"] = true;
+    Features["s-memtime-inst"] = true;
+    Features["gws"] = true;
+    Features["vmem-to-lds-load-insts"] = true;
+    Features["atomic-fmin-fmax-global-f32"] = true;
+    Features["atomic-fmin-fmax-global-f64"] = true;
+    break;
+  case GK_GFX950:
+    Features["bitop3-insts"] = true;
+    Features["fp6bf6-cvt-scale-insts"] = true;
+    Features["fp4-cvt-scale-insts"] = true;
+    Features["bf8-cvt-scale-insts"] = true;
+    Features["fp8-cvt-scale-insts"] = true;
+    Features["f16bf16-to-fp6bf6-cvt-scale-insts"] = true;
+    Features["f32-to-f16bf16-cvt-sr-insts"] = true;
+    Features["prng-inst"] = true;
+    Features["permlane16-swap"] = true;
+    Features["permlane32-swap"] = true;
+    Features["ashr-pk-insts"] = true;
+    Features["dot12-insts"] = true;
+    Features["dot13-insts"] = true;
+    Features["atomic-buffer-pk-add-bf16-inst"] = true;
+    Features["gfx950-insts"] = true;
+    [[fallthrough]];
+  case GK_GFX942:
+    Features["fp8-insts"] = true;
+    Features["fp8-conversion-insts"] = true;
+    if (Kind != GK_GFX950)
+      Features["xf32-insts"] = true;
+    [[fallthrough]];
+  case GK_GFX9_4_GENERIC:
+    Features["gfx940-insts"] = true;
+    Features["atomic-ds-pk-add-16-insts"] = true;
+    Features["atomic-flat-pk-add-16-insts"] = true;
+    Features["atomic-global-pk-add-bf16-inst"] = true;
+    Features["gfx90a-insts"] = true;
+    Features["atomic-buffer-global-pk-add-f16-insts"] = true;
+    Features["atomic-fadd-rtn-insts"] = true;
+    Features["dot3-insts"] = true;
+    Features["dot4-insts"] = true;
+    Features["dot5-insts"] = true;
+    Features["dot6-insts"] = true;
+    Features["mai-insts"] = true;
+    Features["dl-insts"] = true;
+    Features["dot1-insts"] = true;
+    Features["dot2-insts"] = true;
+    Features["dot7-insts"] = true;
+    Features["dot10-insts"] = true;
+    Features["gfx9-insts"] = true;
+    Features["gfx8-insts"] = true;
+    Features["16-bit-insts"] = true;
+    Features["dpp"] = true;
+    Features["s-memrealtime"] = true;
+    Features["ci-insts"] = true;
+    Features["s-memtime-inst"] = true;
+    Features["gws"] = true;
+    Features["vmem-to-lds-load-insts"] = true;
+    Features["atomic-fmin-fmax-global-f64"] = true;
+    Features["wavefrontsize64"] = true;
+    break;
+  case GK_GFX90A:
+    Features["gfx90a-insts"] = true;
+    Features["atomic-buffer-global-pk-add-f16-insts"] = true;
+    Features["atomic-fadd-rtn-insts"] = true;
+    Features["atomic-fmin-fmax-global-f64"] = true;
+    [[fallthrough]];
+  case GK_GFX908:
+    Features["dot3-insts"] = true;
+    Features["dot4-insts"] = true;
+    Features["dot5-insts"] = true;
+    Features["dot6-insts"] = true;
+    Features["mai-insts"] = true;
+    [[fallthrough]];
+  case GK_GFX906:
+    Features["dl-insts"] = true;
+    Features["dot1-insts"] = true;
+    Features["dot2-insts"] = true;
+    Features["dot7-insts"] = true;
+    Features["dot10-insts"] = true;
+    [[fallthrough]];
+  case GK_GFX90C:
+  case GK_GFX909:
+  case GK_GFX904:
+  case GK_GFX902:
+  case GK_GFX900:
+  case GK_GFX9_GENERIC:
+    Features["gfx9-insts"] = true;
+    Features["vmem-to-lds-load-insts"] = true;
+    [[fallthrough]];
+  case GK_GFX810:
+  case GK_GFX805:
+  case GK_GFX803:
+  case GK_GFX802:
+  case GK_GFX801:
+    Features["gfx8-insts"] = true;
+    Features["16-bit-insts"] = true;
+    Features["dpp"] = true;
+    Features["s-memrealtime"] = true;
+    Features["ci-insts"] = true;
+    Features["image-insts"] = true;
+    Features["s-memtime-inst"] = true;
+    Features["gws"] = true;
+    Features["wavefrontsize64"] = true;
+    break;
+  case GK_GFX705:
+  case GK_GFX704:
+  case GK_GFX703:
+  case GK_GFX702:
+  case GK_GFX701:
+  case GK_GFX700:
+    Features["ci-insts"] = true;
+    [[fallthrough]];
+  case GK_GFX602:
+  case GK_GFX601:
+  case GK_GFX600:
+    Features["image-insts"] = true;
+    Features["s-memtime-inst"] = true;
+    Features["gws"] = true;
+    Features["atomic-fmin-fmax-global-f32"] = true;
+    Features["atomic-fmin-fmax-global-f64"] = true;
+    Features["wavefrontsize64"] = true;
+    break;
+  case GK_NONE:
+    break;
+  default:
+    llvm_unreachable("Unhandled GPU!");
+  }
+}
+
+/// Fills Features map with default values for given target GPU.
+/// \p Features contains overriding target features and this function returns
+/// default target features with entries overridden by \p Features.
+std::pair<FeatureError, StringRef>
+AMDGPU::fillAMDGPUFeatureMap(StringRef GPU, const Triple &T,
+                             StringMap<bool> &Features) {
   // XXX - What does the member GPU mean if device name string passed here?
   if (T.isSPIRV() && T.getOS() == Triple::OSType::AMDHSA) {
     // AMDGCN SPIRV must support the union of all AMDGCN features. This list
@@ -434,276 +752,9 @@ void AMDGPU::fillAMDGPUFeatureMap(StringRef GPU, const Triple &T,
     Features["wavefrontsize32"] = true;
     Features["wavefrontsize64"] = true;
   } else if (T.isAMDGCN()) {
-    AMDGPU::GPUKind Kind = parseArchAMDGCN(GPU);
-    switch (Kind) {
-    case GK_GFX1250:
-      Features["ci-insts"] = true;
-      Features["dot7-insts"] = true;
-      Features["dot8-insts"] = true;
-      Features["dl-insts"] = true;
-      Features["16-bit-insts"] = true;
-      Features["dpp"] = true;
-      Features["gfx8-insts"] = true;
-      Features["gfx9-insts"] = true;
-      Features["gfx10-insts"] = true;
-      Features["gfx10-3-insts"] = true;
-      Features["gfx11-insts"] = true;
-      Features["gfx12-insts"] = true;
-      Features["gfx1250-insts"] = true;
-      Features["bitop3-insts"] = true;
-      Features["prng-inst"] = true;
-      Features["tanh-insts"] = true;
-      Features["tensor-cvt-lut-insts"] = true;
-      Features["transpose-load-f4f6-insts"] = true;
-      Features["bf16-trans-insts"] = true;
-      Features["bf16-cvt-insts"] = true;
-      Features["fp8-conversion-insts"] = true;
-      Features["fp8e5m3-insts"] = true;
-      Features["permlane16-swap"] = true;
-      Features["ashr-pk-insts"] = true;
-      Features["atomic-buffer-pk-add-bf16-inst"] = true;
-      Features["vmem-pref-insts"] = true;
-      Features["atomic-fadd-rtn-insts"] = true;
-      Features["atomic-buffer-global-pk-add-f16-insts"] = true;
-      Features["atomic-flat-pk-add-16-insts"] = true;
-      Features["atomic-global-pk-add-bf16-inst"] = true;
-      Features["atomic-ds-pk-add-16-insts"] = true;
-      Features["setprio-inc-wg-inst"] = true;
-      Features["atomic-fmin-fmax-global-f32"] = true;
-      Features["atomic-fmin-fmax-global-f64"] = true;
-      break;
-    case GK_GFX1201:
-    case GK_GFX1200:
-    case GK_GFX12_GENERIC:
-      Features["ci-insts"] = true;
-      Features["dot7-insts"] = true;
-      Features["dot8-insts"] = true;
-      Features["dot9-insts"] = true;
-      Features["dot10-insts"] = true;
-      Features["dot11-insts"] = true;
-      Features["dot12-insts"] = true;
-      Features["dl-insts"] = true;
-      Features["atomic-ds-pk-add-16-insts"] = true;
-      Features["atomic-flat-pk-add-16-insts"] = true;
-      Features["atomic-buffer-global-pk-add-f16-insts"] = true;
-      Features["atomic-buffer-pk-add-bf16-inst"] = true;
-      Features["atomic-global-pk-add-bf16-inst"] = true;
-      Features["16-bit-insts"] = true;
-      Features["dpp"] = true;
-      Features["gfx8-insts"] = true;
-      Features["gfx9-insts"] = true;
-      Features["gfx10-insts"] = true;
-      Features["gfx10-3-insts"] = true;
-      Features["gfx11-insts"] = true;
-      Features["gfx12-insts"] = true;
-      Features["atomic-fadd-rtn-insts"] = true;
-      Features["image-insts"] = true;
-      Features["fp8-conversion-insts"] = true;
-      Features["atomic-fmin-fmax-global-f32"] = true;
-      break;
-    case GK_GFX1153:
-    case GK_GFX1152:
-    case GK_GFX1151:
-    case GK_GFX1150:
-    case GK_GFX1103:
-    case GK_GFX1102:
-    case GK_GFX1101:
-    case GK_GFX1100:
-    case GK_GFX11_GENERIC:
-      Features["ci-insts"] = true;
-      Features["dot5-insts"] = true;
-      Features["dot7-insts"] = true;
-      Features["dot8-insts"] = true;
-      Features["dot9-insts"] = true;
-      Features["dot10-insts"] = true;
-      Features["dot12-insts"] = true;
-      Features["dl-insts"] = true;
-      Features["16-bit-insts"] = true;
-      Features["dpp"] = true;
-      Features["gfx8-insts"] = true;
-      Features["gfx9-insts"] = true;
-      Features["gfx10-insts"] = true;
-      Features["gfx10-3-insts"] = true;
-      Features["gfx11-insts"] = true;
-      Features["atomic-fadd-rtn-insts"] = true;
-      Features["image-insts"] = true;
-      Features["gws"] = true;
-      Features["atomic-fmin-fmax-global-f32"] = true;
-      break;
-    case GK_GFX1036:
-    case GK_GFX1035:
-    case GK_GFX1034:
-    case GK_GFX1033:
-    case GK_GFX1032:
-    case GK_GFX1031:
-    case GK_GFX1030:
-    case GK_GFX10_3_GENERIC:
-      Features["ci-insts"] = true;
-      Features["dot1-insts"] = true;
-      Features["dot2-insts"] = true;
-      Features["dot5-insts"] = true;
-      Features["dot6-insts"] = true;
-      Features["dot7-insts"] = true;
-      Features["dot10-insts"] = true;
-      Features["dl-insts"] = true;
-      Features["16-bit-insts"] = true;
-      Features["dpp"] = true;
-      Features["gfx8-insts"] = true;
-      Features["gfx9-insts"] = true;
-      Features["gfx10-insts"] = true;
-      Features["gfx10-3-insts"] = true;
-      Features["image-insts"] = true;
-      Features["s-memrealtime"] = true;
-      Features["s-memtime-inst"] = true;
-      Features["gws"] = true;
-      Features["vmem-to-lds-load-insts"] = true;
-      Features["atomic-fmin-fmax-global-f32"] = true;
-      Features["atomic-fmin-fmax-global-f64"] = true;
-      break;
-    case GK_GFX1012:
-    case GK_GFX1011:
-      Features["dot1-insts"] = true;
-      Features["dot2-insts"] = true;
-      Features["dot5-insts"] = true;
-      Features["dot6-insts"] = true;
-      Features["dot7-insts"] = true;
-      Features["dot10-insts"] = true;
-      [[fallthrough]];
-    case GK_GFX1013:
-    case GK_GFX1010:
-    case GK_GFX10_1_GENERIC:
-      Features["dl-insts"] = true;
-      Features["ci-insts"] = true;
-      Features["16-bit-insts"] = true;
-      Features["dpp"] = true;
-      Features["gfx8-insts"] = true;
-      Features["gfx9-insts"] = true;
-      Features["gfx10-insts"] = true;
-      Features["image-insts"] = true;
-      Features["s-memrealtime"] = true;
-      Features["s-memtime-inst"] = true;
-      Features["gws"] = true;
-      Features["vmem-to-lds-load-insts"] = true;
-      Features["atomic-fmin-fmax-global-f32"] = true;
-      Features["atomic-fmin-fmax-global-f64"] = true;
-      break;
-    case GK_GFX950:
-      Features["bitop3-insts"] = true;
-      Features["fp6bf6-cvt-scale-insts"] = true;
-      Features["fp4-cvt-scale-insts"] = true;
-      Features["bf8-cvt-scale-insts"] = true;
-      Features["fp8-cvt-scale-insts"] = true;
-      Features["f16bf16-to-fp6bf6-cvt-scale-insts"] = true;
-      Features["f32-to-f16bf16-cvt-sr-insts"] = true;
-      Features["prng-inst"] = true;
-      Features["permlane16-swap"] = true;
-      Features["permlane32-swap"] = true;
-      Features["ashr-pk-insts"] = true;
-      Features["dot12-insts"] = true;
-      Features["dot13-insts"] = true;
-      Features["atomic-buffer-pk-add-bf16-inst"] = true;
-      Features["gfx950-insts"] = true;
-      [[fallthrough]];
-    case GK_GFX942:
-      Features["fp8-insts"] = true;
-      Features["fp8-conversion-insts"] = true;
-      if (Kind != GK_GFX950)
-        Features["xf32-insts"] = true;
-      [[fallthrough]];
-    case GK_GFX9_4_GENERIC:
-      Features["gfx940-insts"] = true;
-      Features["atomic-ds-pk-add-16-insts"] = true;
-      Features["atomic-flat-pk-add-16-insts"] = true;
-      Features["atomic-global-pk-add-bf16-inst"] = true;
-      Features["gfx90a-insts"] = true;
-      Features["atomic-buffer-global-pk-add-f16-insts"] = true;
-      Features["atomic-fadd-rtn-insts"] = true;
-      Features["dot3-insts"] = true;
-      Features["dot4-insts"] = true;
-      Features["dot5-insts"] = true;
-      Features["dot6-insts"] = true;
-      Features["mai-insts"] = true;
-      Features["dl-insts"] = true;
-      Features["dot1-insts"] = true;
-      Features["dot2-insts"] = true;
-      Features["dot7-insts"] = true;
-      Features["dot10-insts"] = true;
-      Features["gfx9-insts"] = true;
-      Features["gfx8-insts"] = true;
-      Features["16-bit-insts"] = true;
-      Features["dpp"] = true;
-      Features["s-memrealtime"] = true;
-      Features["ci-insts"] = true;
-      Features["s-memtime-inst"] = true;
-      Features["gws"] = true;
-      Features["vmem-to-lds-load-insts"] = true;
-      Features["atomic-fmin-fmax-global-f64"] = true;
-      break;
-    case GK_GFX90A:
-      Features["gfx90a-insts"] = true;
-      Features["atomic-buffer-global-pk-add-f16-insts"] = true;
-      Features["atomic-fadd-rtn-insts"] = true;
-      Features["atomic-fmin-fmax-global-f64"] = true;
-      [[fallthrough]];
-    case GK_GFX908:
-      Features["dot3-insts"] = true;
-      Features["dot4-insts"] = true;
-      Features["dot5-insts"] = true;
-      Features["dot6-insts"] = true;
-      Features["mai-insts"] = true;
-      [[fallthrough]];
-    case GK_GFX906:
-      Features["dl-insts"] = true;
-      Features["dot1-insts"] = true;
-      Features["dot2-insts"] = true;
-      Features["dot7-insts"] = true;
-      Features["dot10-insts"] = true;
-      [[fallthrough]];
-    case GK_GFX90C:
-    case GK_GFX909:
-    case GK_GFX904:
-    case GK_GFX902:
-    case GK_GFX900:
-    case GK_GFX9_GENERIC:
-      Features["gfx9-insts"] = true;
-      Features["vmem-to-lds-load-insts"] = true;
-      [[fallthrough]];
-    case GK_GFX810:
-    case GK_GFX805:
-    case GK_GFX803:
-    case GK_GFX802:
-    case GK_GFX801:
-      Features["gfx8-insts"] = true;
-      Features["16-bit-insts"] = true;
-      Features["dpp"] = true;
-      Features["s-memrealtime"] = true;
-      Features["ci-insts"] = true;
-      Features["image-insts"] = true;
-      Features["s-memtime-inst"] = true;
-      Features["gws"] = true;
-      break;
-    case GK_GFX705:
-    case GK_GFX704:
-    case GK_GFX703:
-    case GK_GFX702:
-    case GK_GFX701:
-    case GK_GFX700:
-      Features["ci-insts"] = true;
-      [[fallthrough]];
-    case GK_GFX602:
-    case GK_GFX601:
-    case GK_GFX600:
-      Features["image-insts"] = true;
-      Features["s-memtime-inst"] = true;
-      Features["gws"] = true;
-      Features["atomic-fmin-fmax-global-f32"] = true;
-      Features["atomic-fmin-fmax-global-f64"] = true;
-      break;
-    case GK_NONE:
-      break;
-    default:
-      llvm_unreachable("Unhandled GPU!");
-    }
+    StringMap<bool> DefaultFeatures;
+    fillAMDGCNFeatureMap(GPU, T, DefaultFeatures);
+    return insertWaveSizeFeature(GPU, T, DefaultFeatures, Features);
   } else {
     if (GPU.empty())
       GPU = "r600";
@@ -732,70 +783,5 @@ void AMDGPU::fillAMDGPUFeatureMap(StringRef GPU, const Triple &T,
       llvm_unreachable("Unhandled GPU!");
     }
   }
-}
-
-static bool isWave32Capable(StringRef GPU, const Triple &T) {
-  bool IsWave32Capable = false;
-  // XXX - What does the member GPU mean if device name string passed here?
-  if (T.isAMDGCN()) {
-    switch (parseArchAMDGCN(GPU)) {
-    case GK_GFX1250:
-    case GK_GFX1201:
-    case GK_GFX1200:
-    case GK_GFX1153:
-    case GK_GFX1152:
-    case GK_GFX1151:
-    case GK_GFX1150:
-    case GK_GFX1103:
-    case GK_GFX1102:
-    case GK_GFX1101:
-    case GK_GFX1100:
-    case GK_GFX1036:
-    case GK_GFX1035:
-    case GK_GFX1034:
-    case GK_GFX1033:
-    case GK_GFX1032:
-    case GK_GFX1031:
-    case GK_GFX1030:
-    case GK_GFX1012:
-    case GK_GFX1011:
-    case GK_GFX1013:
-    case GK_GFX1010:
-    case GK_GFX12_GENERIC:
-    case GK_GFX11_GENERIC:
-    case GK_GFX10_3_GENERIC:
-    case GK_GFX10_1_GENERIC:
-      IsWave32Capable = true;
-      break;
-    default:
-      break;
-    }
-  }
-  return IsWave32Capable;
-}
-
-std::pair<FeatureError, StringRef>
-AMDGPU::insertWaveSizeFeature(StringRef GPU, const Triple &T,
-                              StringMap<bool> &Features) {
-  bool IsWave32Capable = isWave32Capable(GPU, T);
-  const bool IsNullGPU = GPU.empty();
-  const bool HaveWave32 = Features.count("wavefrontsize32");
-  const bool HaveWave64 = Features.count("wavefrontsize64");
-  if (HaveWave32 && HaveWave64) {
-    return {AMDGPU::INVALID_FEATURE_COMBINATION,
-            "'wavefrontsize32' and 'wavefrontsize64' are mutually exclusive"};
-  }
-  if (HaveWave32 && !IsNullGPU && !IsWave32Capable) {
-    return {AMDGPU::UNSUPPORTED_TARGET_FEATURE, "wavefrontsize32"};
-  }
-  // Don't assume any wavesize with an unknown subtarget.
-  if (!IsNullGPU) {
-    // Default to wave32 if available, or wave64 if not
-    if (!HaveWave32 && !HaveWave64) {
-      StringRef DefaultWaveSizeFeature =
-          IsWave32Capable ? "wavefrontsize32" : "wavefrontsize64";
-      Features.insert(std::make_pair(DefaultWaveSizeFeature, true));
-    }
-  }
   return {NO_ERROR, StringRef()};
 }
diff --git a/llvm/lib/TargetParser/Triple.cpp b/llvm/lib/TargetParser/Triple.cpp
index 6acb0bc49ecf..ac3626db46ea 100644
--- a/llvm/lib/TargetParser/Triple.cpp
+++ b/llvm/lib/TargetParser/Triple.cpp
@@ -158,6 +158,8 @@ StringRef Triple::getArchName(ArchType Kind, SubArchType SubArch) {
       return "dxilv1.7";
     case Triple::DXILSubArch_v1_8:
       return "dxilv1.8";
+    case Triple::DXILSubArch_v1_9:
+      return "dxilv1.9";
     default:
       break;
     }
@@ -329,6 +331,8 @@ StringRef Triple::getOSTypeName(OSType Kind) {
   case LiteOS: return "liteos";
   case XROS: return "xros";
   case Vulkan: return "vulkan";
+  case CheriotRTOS:
+    return "cheriotrtos";
   }
 
   llvm_unreachable("Invalid OSType");
@@ -387,6 +391,8 @@ StringRef Triple::getEnvironmentTypeName(EnvironmentType Kind) {
   case Callable: return "callable";
   case Mesh: return "mesh";
   case Amplification: return "amplification";
+  case RootSignature:
+    return "rootsignature";
   case OpenCL:
     return "opencl";
   case OpenHOS: return "ohos";
@@ -648,6 +654,8 @@ static Triple::ArchType parseArch(StringRef ArchName) {
                 .Cases("dxil", "dxilv1.0", "dxilv1.1", "dxilv1.2", "dxilv1.3",
                        "dxilv1.4", "dxilv1.5", "dxilv1.6", "dxilv1.7",
                        "dxilv1.8", Triple::dxil)
+                // Note: Cases has max limit of 10.
+                .Case("dxilv1.9", Triple::dxil)
                 .Case("xtensa", Triple::xtensa)
                 .Default(Triple::UnknownArch);
 
@@ -687,49 +695,50 @@ static Triple::VendorType parseVendor(StringRef VendorName) {
 
 static Triple::OSType parseOS(StringRef OSName) {
   return StringSwitch<Triple::OSType>(OSName)
-    .StartsWith("darwin", Triple::Darwin)
-    .StartsWith("dragonfly", Triple::DragonFly)
-    .StartsWith("freebsd", Triple::FreeBSD)
-    .StartsWith("fuchsia", Triple::Fuchsia)
-    .StartsWith("ios", Triple::IOS)
-    .StartsWith("kfreebsd", Triple::KFreeBSD)
-    .StartsWith("linux", Triple::Linux)
-    .StartsWith("lv2", Triple::Lv2)
-    .StartsWith("macos", Triple::MacOSX)
-    .StartsWith("managarm", Triple::Managarm)
-    .StartsWith("netbsd", Triple::NetBSD)
-    .StartsWith("openbsd", Triple::OpenBSD)
-    .StartsWith("solaris", Triple::Solaris)
-    .StartsWith("uefi", Triple::UEFI)
-    .StartsWith("win32", Triple::Win32)
-    .StartsWith("windows", Triple::Win32)
-    .StartsWith("zos", Triple::ZOS)
-    .StartsWith("haiku", Triple::Haiku)
-    .StartsWith("rtems", Triple::RTEMS)
-    .StartsWith("aix", Triple::AIX)
-    .StartsWith("cuda", Triple::CUDA)
-    .StartsWith("nvcl", Triple::NVCL)
-    .StartsWith("amdhsa", Triple::AMDHSA)
-    .StartsWith("ps4", Triple::PS4)
-    .StartsWith("ps5", Triple::PS5)
-    .StartsWith("elfiamcu", Triple::ELFIAMCU)
-    .StartsWith("tvos", Triple::TvOS)
-    .StartsWith("watchos", Triple::WatchOS)
-    .StartsWith("bridgeos", Triple::BridgeOS)
-    .StartsWith("driverkit", Triple::DriverKit)
-    .StartsWith("xros", Triple::XROS)
-    .StartsWith("visionos", Triple::XROS)
-    .StartsWith("mesa3d", Triple::Mesa3D)
-    .StartsWith("amdpal", Triple::AMDPAL)
-    .StartsWith("hermit", Triple::HermitCore)
-    .StartsWith("hurd", Triple::Hurd)
-    .StartsWith("wasi", Triple::WASI)
-    .StartsWith("emscripten", Triple::Emscripten)
-    .StartsWith("shadermodel", Triple::ShaderModel)
-    .StartsWith("liteos", Triple::LiteOS)
-    .StartsWith("serenity", Triple::Serenity)
-    .StartsWith("vulkan", Triple::Vulkan)
-    .Default(Triple::UnknownOS);
+      .StartsWith("darwin", Triple::Darwin)
+      .StartsWith("dragonfly", Triple::DragonFly)
+      .StartsWith("freebsd", Triple::FreeBSD)
+      .StartsWith("fuchsia", Triple::Fuchsia)
+      .StartsWith("ios", Triple::IOS)
+      .StartsWith("kfreebsd", Triple::KFreeBSD)
+      .StartsWith("linux", Triple::Linux)
+      .StartsWith("lv2", Triple::Lv2)
+      .StartsWith("macos", Triple::MacOSX)
+      .StartsWith("managarm", Triple::Managarm)
+      .StartsWith("netbsd", Triple::NetBSD)
+      .StartsWith("openbsd", Triple::OpenBSD)
+      .StartsWith("solaris", Triple::Solaris)
+      .StartsWith("uefi", Triple::UEFI)
+      .StartsWith("win32", Triple::Win32)
+      .StartsWith("windows", Triple::Win32)
+      .StartsWith("zos", Triple::ZOS)
+      .StartsWith("haiku", Triple::Haiku)
+      .StartsWith("rtems", Triple::RTEMS)
+      .StartsWith("aix", Triple::AIX)
+      .StartsWith("cuda", Triple::CUDA)
+      .StartsWith("nvcl", Triple::NVCL)
+      .StartsWith("amdhsa", Triple::AMDHSA)
+      .StartsWith("ps4", Triple::PS4)
+      .StartsWith("ps5", Triple::PS5)
+      .StartsWith("elfiamcu", Triple::ELFIAMCU)
+      .StartsWith("tvos", Triple::TvOS)
+      .StartsWith("watchos", Triple::WatchOS)
+      .StartsWith("bridgeos", Triple::BridgeOS)
+      .StartsWith("driverkit", Triple::DriverKit)
+      .StartsWith("xros", Triple::XROS)
+      .StartsWith("visionos", Triple::XROS)
+      .StartsWith("mesa3d", Triple::Mesa3D)
+      .StartsWith("amdpal", Triple::AMDPAL)
+      .StartsWith("hermit", Triple::HermitCore)
+      .StartsWith("hurd", Triple::Hurd)
+      .StartsWith("wasi", Triple::WASI)
+      .StartsWith("emscripten", Triple::Emscripten)
+      .StartsWith("shadermodel", Triple::ShaderModel)
+      .StartsWith("liteos", Triple::LiteOS)
+      .StartsWith("serenity", Triple::Serenity)
+      .StartsWith("vulkan", Triple::Vulkan)
+      .StartsWith("cheriotrtos", Triple::CheriotRTOS)
+      .Default(Triple::UnknownOS);
 }
 
 static Triple::EnvironmentType parseEnvironment(StringRef EnvironmentName) {
@@ -780,6 +789,7 @@ static Triple::EnvironmentType parseEnvironment(StringRef EnvironmentName) {
       .StartsWith("callable", Triple::Callable)
       .StartsWith("mesh", Triple::Mesh)
       .StartsWith("amplification", Triple::Amplification)
+      .StartsWith("rootsignature", Triple::RootSignature)
       .StartsWith("opencl", Triple::OpenCL)
       .StartsWith("ohos", Triple::OpenHOS)
       .StartsWith("pauthtest", Triple::PAuthTest)
@@ -839,6 +849,7 @@ static Triple::SubArchType parseSubArch(StringRef SubArchName) {
         .EndsWith("v1.6", Triple::DXILSubArch_v1_6)
         .EndsWith("v1.7", Triple::DXILSubArch_v1_7)
         .EndsWith("v1.8", Triple::DXILSubArch_v1_8)
+        .EndsWith("v1.9", Triple::DXILSubArch_v1_9)
         .Default(Triple::NoSubArch);
 
   StringRef ARMSubArch = ARM::getCanonicalArchName(SubArchName);
@@ -1108,7 +1119,7 @@ static StringRef getDXILArchNameFromShaderModel(StringRef ShaderModelStr) {
   VersionTuple Ver =
       parseVersionFromName(ShaderModelStr.drop_front(strlen("shadermodel")));
   // Default DXIL minor version when Shader Model version is anything other
-  // than 6.[0...8] or 6.x (which translates to latest current SM version)
+  // than 6.[0...9] or 6.x (which translates to latest current SM version)
   const unsigned SMMajor = 6;
   if (!Ver.empty()) {
     if (Ver.getMajor() == SMMajor) {
@@ -1132,6 +1143,8 @@ static StringRef getDXILArchNameFromShaderModel(StringRef ShaderModelStr) {
           return Triple::getArchName(Triple::dxil, Triple::DXILSubArch_v1_7);
         case 8:
           return Triple::getArchName(Triple::dxil, Triple::DXILSubArch_v1_8);
+        case 9:
+          return Triple::getArchName(Triple::dxil, Triple::DXILSubArch_v1_9);
         default:
           report_fatal_error("Unsupported Shader Model version", false);
         }
diff --git a/llvm/lib/TargetParser/X86TargetParser.cpp b/llvm/lib/TargetParser/X86TargetParser.cpp
index b72096553ad9..edca7c18062a 100644
--- a/llvm/lib/TargetParser/X86TargetParser.cpp
+++ b/llvm/lib/TargetParser/X86TargetParser.cpp
@@ -72,7 +72,7 @@ constexpr FeatureBitset FeaturesX86_64_V2 = FeaturesX86_64 | FeatureSAHF |
 constexpr FeatureBitset FeaturesX86_64_V3 =
     FeaturesX86_64_V2 | FeatureAVX2 | FeatureBMI | FeatureBMI2 | FeatureF16C |
     FeatureFMA | FeatureLZCNT | FeatureMOVBE | FeatureXSAVE;
-constexpr FeatureBitset FeaturesX86_64_V4 = FeaturesX86_64_V3 | FeatureEVEX512 |
+constexpr FeatureBitset FeaturesX86_64_V4 = FeaturesX86_64_V3 |
                                             FeatureAVX512BW | FeatureAVX512CD |
                                             FeatureAVX512DQ | FeatureAVX512VL;
 
@@ -95,9 +95,8 @@ constexpr FeatureBitset FeaturesBroadwell =
 
 // Intel Knights Landing and Knights Mill
 // Knights Landing has feature parity with Broadwell.
-constexpr FeatureBitset FeaturesKNL = FeaturesBroadwell | FeatureAES |
-                                      FeatureAVX512F | FeatureEVEX512 |
-                                      FeatureAVX512CD;
+constexpr FeatureBitset FeaturesKNL =
+    FeaturesBroadwell | FeatureAES | FeatureAVX512F | FeatureAVX512CD;
 constexpr FeatureBitset FeaturesKNM = FeaturesKNL | FeatureAVX512VPOPCNTDQ;
 
 // Intel Skylake processors.
@@ -107,9 +106,9 @@ constexpr FeatureBitset FeaturesSkylakeClient =
 // SkylakeServer inherits all SkylakeClient features except SGX.
 // FIXME: That doesn't match gcc.
 constexpr FeatureBitset FeaturesSkylakeServer =
-    (FeaturesSkylakeClient & ~FeatureSGX) | FeatureAVX512F | FeatureEVEX512 |
-    FeatureAVX512CD | FeatureAVX512DQ | FeatureAVX512BW | FeatureAVX512VL |
-    FeatureCLWB | FeaturePKU;
+    (FeaturesSkylakeClient & ~FeatureSGX) | FeatureAVX512F | FeatureAVX512CD |
+    FeatureAVX512DQ | FeatureAVX512BW | FeatureAVX512VL | FeatureCLWB |
+    FeaturePKU;
 constexpr FeatureBitset FeaturesCascadeLake =
     FeaturesSkylakeServer | FeatureAVX512VNNI;
 constexpr FeatureBitset FeaturesCooperLake =
@@ -117,9 +116,9 @@ constexpr FeatureBitset FeaturesCooperLake =
 
 // Intel 10nm processors.
 constexpr FeatureBitset FeaturesCannonlake =
-    FeaturesSkylakeClient | FeatureAVX512F | FeatureEVEX512 | FeatureAVX512CD |
-    FeatureAVX512DQ | FeatureAVX512BW | FeatureAVX512VL | FeatureAVX512IFMA |
-    FeatureAVX512VBMI | FeaturePKU | FeatureSHA;
+    FeaturesSkylakeClient | FeatureAVX512F | FeatureAVX512CD | FeatureAVX512DQ |
+    FeatureAVX512BW | FeatureAVX512VL | FeatureAVX512IFMA | FeatureAVX512VBMI |
+    FeaturePKU | FeatureSHA;
 constexpr FeatureBitset FeaturesICLClient =
     FeaturesCannonlake | FeatureAVX512BITALG | FeatureAVX512VBMI2 |
     FeatureAVX512VNNI | FeatureAVX512VPOPCNTDQ | FeatureGFNI | FeatureRDPID |
@@ -139,7 +138,7 @@ constexpr FeatureBitset FeaturesSapphireRapids =
 constexpr FeatureBitset FeaturesGraniteRapids =
     FeaturesSapphireRapids | FeatureAMX_FP16 | FeaturePREFETCHI;
 constexpr FeatureBitset FeaturesDiamondRapids =
-    FeaturesGraniteRapids | FeatureAMX_COMPLEX | FeatureAVX10_2_512 |
+    FeaturesGraniteRapids | FeatureAMX_COMPLEX | FeatureAVX10_2 |
     FeatureCMPCCXADD | FeatureAVXIFMA | FeatureAVXNECONVERT |
     FeatureAVXVNNIINT8 | FeatureAVXVNNIINT16 | FeatureSHA512 | FeatureSM3 |
     FeatureSM4 | FeatureEGPR | FeatureZU | FeatureCCMP | FeaturePush2Pop2 |
@@ -244,11 +243,10 @@ static constexpr FeatureBitset FeaturesZNVER3 = FeaturesZNVER2 |
                                                 FeatureINVPCID | FeaturePKU |
                                                 FeatureVAES | FeatureVPCLMULQDQ;
 static constexpr FeatureBitset FeaturesZNVER4 =
-    FeaturesZNVER3 | FeatureAVX512F | FeatureEVEX512 | FeatureAVX512CD |
-    FeatureAVX512DQ | FeatureAVX512BW | FeatureAVX512VL | FeatureAVX512IFMA |
-    FeatureAVX512VBMI | FeatureAVX512VBMI2 | FeatureAVX512VNNI |
-    FeatureAVX512BITALG | FeatureAVX512VPOPCNTDQ | FeatureAVX512BF16 |
-    FeatureGFNI | FeatureSHSTK;
+    FeaturesZNVER3 | FeatureAVX512F | FeatureAVX512CD | FeatureAVX512DQ |
+    FeatureAVX512BW | FeatureAVX512VL | FeatureAVX512IFMA | FeatureAVX512VBMI |
+    FeatureAVX512VBMI2 | FeatureAVX512VNNI | FeatureAVX512BITALG |
+    FeatureAVX512VPOPCNTDQ | FeatureAVX512BF16 | FeatureGFNI | FeatureSHSTK;
 
 static constexpr FeatureBitset FeaturesZNVER5 =
     FeaturesZNVER4 | FeatureAVXVNNI | FeatureMOVDIRI | FeatureMOVDIR64B |
@@ -394,7 +392,7 @@ constexpr ProcInfo Processors[] = {
   // Clearwaterforest microarchitecture based processors.
   { {"clearwaterforest"}, CK_Lunarlake, FEATURE_AVX2, FeaturesClearwaterforest, 'p', false },
   // Diamond Rapids microarchitecture based processors.
-  { {"diamondrapids"}, CK_Diamondrapids, FEATURE_AVX10_2_512, FeaturesDiamondRapids, 'z', false },
+  { {"diamondrapids"}, CK_Diamondrapids, FEATURE_AVX10_2, FeaturesDiamondRapids, 'z', false },
   // Knights Landing processor.
   { {"knl"}, CK_KNL, FEATURE_AVX512F, FeaturesKNL, 'Z', false },
   { {"mic_avx512"}, CK_KNL, FEATURE_AVX512F, FeaturesKNL, 'Z', true },
@@ -616,7 +614,7 @@ constexpr FeatureBitset ImpliedFeaturesAMX_FP8 = FeatureAMX_TILE;
 constexpr FeatureBitset ImpliedFeaturesAMX_TRANSPOSE = FeatureAMX_TILE;
 constexpr FeatureBitset ImpliedFeaturesAMX_MOVRS = FeatureAMX_TILE;
 constexpr FeatureBitset ImpliedFeaturesAMX_AVX512 =
-    FeatureAMX_TILE | FeatureAVX10_2_512;
+    FeatureAMX_TILE | FeatureAVX10_2;
 constexpr FeatureBitset ImpliedFeaturesAMX_TF32 = FeatureAMX_TILE;
 constexpr FeatureBitset ImpliedFeaturesHRESET = {};
 
@@ -642,11 +640,9 @@ constexpr FeatureBitset ImpliedFeaturesAVX10_1 =
     FeatureAVX512VNNI | FeatureAVX512BF16 | FeatureAVX512VPOPCNTDQ |
     FeatureAVX512VBMI2 | FeatureAVX512BITALG | FeatureAVX512FP16 |
     FeatureAVX512DQ | FeatureAVX512VL;
-constexpr FeatureBitset ImpliedFeaturesAVX10_1_512 =
-    FeatureAVX10_1 | FeatureEVEX512;
 constexpr FeatureBitset ImpliedFeaturesAVX10_2 = FeatureAVX10_1;
-constexpr FeatureBitset ImpliedFeaturesAVX10_2_512 =
-    FeatureAVX10_2 | FeatureAVX10_1_512;
+constexpr FeatureBitset ImpliedFeaturesAVX10_1_512 = FeatureAVX10_1;
+constexpr FeatureBitset ImpliedFeaturesAVX10_2_512 = FeatureAVX10_2;
 
 // APX Features
 constexpr FeatureBitset ImpliedFeaturesEGPR = {};