merge main into amd-staging (llvm#3244)

Author: z1_cciauto

.github/workflows/premerge.yaml

@@ -88,11 +88,6 @@ jobs:
         uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # v4.2.2
         with:
           fetch-depth: 2
-      - name: Setup ccache
-        uses: hendrikmuhs/ccache-action@a1209f81afb8c005c13b4296c32e363431bffea5 # v1.2.17
-        with:
-          variant: "sccache"
-          max-size: "2000M"
       - name: Compute Projects
         id: vars
         run: |
@@ -115,7 +110,7 @@ jobs:
         shell: cmd
         run: |
           call C:\\BuildTools\\Common7\\Tools\\VsDevCmd.bat -arch=amd64 -host_arch=amd64
-          bash .ci/monolithic-windows.sh "${{ steps.vars.outputs.windows-projects }}" "${{ steps.vars.outputs.windows-check-targets }}"
+          bash -c "export SCCACHE_GCS_BUCKET=$CACHE_GCS_BUCKET; export SCCACHE_GCS_RW_MODE=READ_WRITE; sccache --start-server; .ci/monolithic-windows.sh \"${{ steps.vars.outputs.windows-projects }}\" \"${{ steps.vars.outputs.windows-check-targets }}\""
       - name: Upload Artifacts
         if: '!cancelled()'
         uses: actions/upload-artifact@65c4c4a1ddee5b72f698fdd19549f0f0fb45cf08 # v4.6.0

clang/docs/LanguageExtensions.rst

@@ -848,6 +848,14 @@ of different sizes and signs is forbidden in binary and ternary builtins.
                                                 semantics, see `LangRef
                                                 <http://llvm.org/docs/LangRef.html#llvm-min-intrinsics-comparation>`_
                                                 for the comparison.
+ T __builtin_elementwise_maximumnum(T x, T y)   return x or y, whichever is larger. Follows IEEE 754-2019              floating point types
+                                                semantics, see `LangRef
+                                                <http://llvm.org/docs/LangRef.html#llvm-min-intrinsics-comparation>`_
+                                                for the comparison.
+ T __builtin_elementwise_minimumnum(T x, T y)   return x or y, whichever is smaller. Follows IEEE 754-2019             floating point types
+                                                semantics, see `LangRef
+                                                <http://llvm.org/docs/LangRef.html#llvm-min-intrinsics-comparation>`_
+                                                for the comparison.
 ============================================== ====================================================================== =========================================
 
 

clang/docs/ReleaseNotes.rst

@@ -344,6 +344,7 @@ Non-comprehensive list of changes in this release
 - Added `__builtin_elementwise_exp10`.
 - For AMDPGU targets, added `__builtin_v_cvt_off_f32_i4` that maps to the `v_cvt_off_f32_i4` instruction.
 - Added `__builtin_elementwise_minnum` and `__builtin_elementwise_maxnum`.
+- Added `__builtin_elementwise_minnumnum` and `__builtin_elementwise_maxnumnum`.
 - No longer crashing on invalid Objective-C categories and extensions when
   dumping the AST as JSON. (#GH137320)
 - Clang itself now uses split stacks instead of threads for allocating more
@@ -830,6 +831,8 @@ Bug Fixes in This Version
 - Fixed a failed assertion with an operator call expression which comes from a
   macro expansion when performing analysis for nullability attributes. (#GH138371)
 - Fixed a concept equivalent checking crash due to untransformed constraint expressions. (#GH146614)
+- Fixed a crash in `clang-scan-deps` when a module with the same name is found
+  in different locations (#GH134404, #GH146976).
 - Fix a crash when marco name is empty in ``#pragma push_macro("")`` or
   ``#pragma pop_macro("")``. (GH149762).
 

clang/include/clang/Basic/Builtins.td

@@ -1334,6 +1334,18 @@ def ElementwiseMinimum : Builtin {
   let Prototype = "void(...)";
 }
 
+def ElementwiseMaximumNum : Builtin {
+  let Spellings = ["__builtin_elementwise_maximumnum"];
+  let Attributes = [NoThrow, Const, CustomTypeChecking];
+  let Prototype = "void(...)";
+}
+
+def ElementwiseMinimumNum : Builtin {
+  let Spellings = ["__builtin_elementwise_minimumnum"];
+  let Attributes = [NoThrow, Const, CustomTypeChecking];
+  let Prototype = "void(...)";
+}
+
 def ElementwiseCeil : Builtin {
   let Spellings = ["__builtin_elementwise_ceil"];
   let Attributes = [NoThrow, Const, CustomTypeChecking];

clang/include/clang/Basic/CodeGenOptions.def

@@ -313,9 +313,10 @@ CODEGENOPT(SpeculativeLoadHardening, 1, 0, Benign) ///< Enable speculative load
 CODEGENOPT(FineGrainedBitfieldAccesses, 1, 0, Benign) ///< Enable fine-grained bitfield accesses.
 CODEGENOPT(StrictEnums       , 1, 0, Benign) ///< Optimize based on strict enum definition.
 CODEGENOPT(StrictVTablePointers, 1, 0, Benign) ///< Optimize based on the strict vtable pointers
-CODEGENOPT(TimePasses        , 1, 0, Benign) ///< Set when -ftime-report or -ftime-report= or -ftime-report-json is enabled.
+CODEGENOPT(TimePasses        , 1, 0, Benign) ///< Set when -ftime-report, -ftime-report=, -ftime-report-json, or -stats-file-timers is enabled.
 CODEGENOPT(TimePassesPerRun  , 1, 0, Benign) ///< Set when -ftime-report=per-pass-run is enabled.
 CODEGENOPT(TimePassesJson    , 1, 0, Benign) ///< Set when -ftime-report-json is enabled.
+CODEGENOPT(TimePassesStatsFile     , 1, 0, Benign) ///< Set when -stats-file-timers is enabled.
 CODEGENOPT(TimeTrace         , 1, 0, Benign) ///< Set when -ftime-trace is enabled.
 VALUE_CODEGENOPT(TimeTraceGranularity, 32, 500, Benign) ///< Minimum time granularity (in microseconds),
                                                         ///< traced by time profiler

clang/include/clang/Driver/Options.td

@@ -8439,6 +8439,9 @@ def stats_file : Joined<["-"], "stats-file=">,
 def stats_file_append : Flag<["-"], "stats-file-append">,
   HelpText<"If stats should be appended to stats-file instead of overwriting it">,
   MarshallingInfoFlag<FrontendOpts<"AppendStats">>;
+def stats_file_timers : Flag<["-"], "stats-file-timers">,
+                        HelpText<"If stats should include timers.">,
+                        MarshallingInfoFlag<CodeGenOpts<"TimePassesStatsFile">>;
 def fdump_record_layouts_simple : Flag<["-"], "fdump-record-layouts-simple">,
   HelpText<"Dump record layout information in a simple form used for testing">,
   MarshallingInfoFlag<LangOpts<"DumpRecordLayoutsSimple">>;

clang/lib/AST/ByteCode/Compiler.cpp

@@ -25,11 +25,18 @@ using APSInt = llvm::APSInt;
 namespace clang {
 namespace interp {
 
+static bool hasTrivialDefaultCtorParent(const FieldDecl *FD) {
+  assert(FD);
+  assert(FD->getParent()->isUnion());
+  const auto *CXXRD = dyn_cast<CXXRecordDecl>(FD->getParent());
+  return !CXXRD || CXXRD->hasTrivialDefaultConstructor();
+}
+
 static bool refersToUnion(const Expr *E) {
   for (;;) {
     if (const auto *ME = dyn_cast<MemberExpr>(E)) {
       if (const auto *FD = dyn_cast<FieldDecl>(ME->getMemberDecl());
-          FD && FD->getParent()->isUnion())
+          FD && FD->getParent()->isUnion() && hasTrivialDefaultCtorParent(FD))
         return true;
       E = ME->getBase();
       continue;

clang/lib/Basic/TargetInfo.cpp

@@ -172,7 +172,7 @@ TargetInfo::TargetInfo(const llvm::Triple &T) : Triple(T) {
   ComplexLongDoubleUsesFP2Ret = false;
 
   // Set the C++ ABI based on the triple.
-  TheCXXABI.set(Triple.isKnownWindowsMSVCEnvironment()
+  TheCXXABI.set(Triple.isKnownWindowsMSVCEnvironment() || Triple.isUEFI()
                     ? TargetCXXABI::Microsoft
                     : TargetCXXABI::GenericItanium);
 

clang/lib/CodeGen/CGBuiltin.cpp

@@ -4108,6 +4108,22 @@ RValue CodeGenFunction::EmitBuiltinExpr(const GlobalDecl GD, unsigned BuiltinID,
     return RValue::get(Result);
   }
 
+  case Builtin::BI__builtin_elementwise_maximumnum: {
+    Value *Op0 = EmitScalarExpr(E->getArg(0));
+    Value *Op1 = EmitScalarExpr(E->getArg(1));
+    Value *Result = Builder.CreateBinaryIntrinsic(
+        Intrinsic::maximumnum, Op0, Op1, nullptr, "elt.maximumnum");
+    return RValue::get(Result);
+  }
+
+  case Builtin::BI__builtin_elementwise_minimumnum: {
+    Value *Op0 = EmitScalarExpr(E->getArg(0));
+    Value *Op1 = EmitScalarExpr(E->getArg(1));
+    Value *Result = Builder.CreateBinaryIntrinsic(
+        Intrinsic::minimumnum, Op0, Op1, nullptr, "elt.minimumnum");
+    return RValue::get(Result);
+  }
+
   case Builtin::BI__builtin_reduce_max: {
     auto GetIntrinsicID = [this](QualType QT) {
       if (auto *VecTy = QT->getAs<VectorType>())

clang/lib/Driver/Driver.cpp

@@ -1016,6 +1016,7 @@ inferOffloadToolchains(Compilation &C, Action::OffloadKind Kind) {
                      C.getArgs().MakeArgString(Triple.split("-").first),
                      C.getArgs().MakeArgString("--offload-arch=" + Arch));
     C.getArgs().append(A);
+    C.getArgs().AddSynthesizedArg(A);
     Triples.insert(Triple);
   }