Merged main:381efa496000 into amd-gfx:df4f5070dfea

Local branch amd-gfx df4f507 Merged main:0bc7cd4d5122 into amd-gfx:94601047c932
Remote branch main 381efa4 Revert rG67275263b3b781a "[X86] X86DAGToDAGISel - attempt to merge XMM/YMM loads with YMM/ZMM loads of the same ptr (llvm#73126)"

Author: SC llvm team

clang/include/clang/Basic/Cuda.h

@@ -113,6 +113,8 @@ enum class CudaArch {
   GFX1103,
   GFX1150,
   GFX1151,
+  GFX1200,
+  GFX1201,
   Generic, // A processor model named 'generic' if the target backend defines a
            // public one.
   LAST,

clang/lib/Basic/Cuda.cpp

@@ -135,6 +135,8 @@ static const CudaArchToStringMap arch_names[] = {
     GFX(1103), // gfx1103
     GFX(1150), // gfx1150
     GFX(1151), // gfx1151
+    GFX(1200), // gfx1200
+    GFX(1201), // gfx1201
     {CudaArch::Generic, "generic", ""},
     // clang-format on
 };

clang/lib/Basic/Targets/NVPTX.cpp

@@ -214,6 +214,8 @@ void NVPTXTargetInfo::getTargetDefines(const LangOptions &Opts,
       case CudaArch::GFX1103:
       case CudaArch::GFX1150:
       case CudaArch::GFX1151:
+      case CudaArch::GFX1200:
+      case CudaArch::GFX1201:
       case CudaArch::Generic:
       case CudaArch::LAST:
         break;

clang/lib/CodeGen/CGBuiltin.cpp

@@ -5745,12 +5745,8 @@ RValue CodeGenFunction::EmitBuiltinExpr(const GlobalDecl GD, unsigned BuiltinID,
     Address DestAddr = EmitMSVAListRef(E->getArg(0));
     Address SrcAddr = EmitMSVAListRef(E->getArg(1));
 
-    llvm::Type *BPP = Int8PtrPtrTy;
-
-    DestAddr = Address(Builder.CreateBitCast(DestAddr.getPointer(), BPP, "cp"),
-                       Int8PtrTy, DestAddr.getAlignment());
-    SrcAddr = Address(Builder.CreateBitCast(SrcAddr.getPointer(), BPP, "ap"),
-                      Int8PtrTy, SrcAddr.getAlignment());
+    DestAddr = DestAddr.withElementType(Int8PtrTy);
+    SrcAddr = SrcAddr.withElementType(Int8PtrTy);
 
     Value *ArgPtr = Builder.CreateLoad(SrcAddr, "ap.val");
     return RValue::get(Builder.CreateStore(ArgPtr, DestAddr));
@@ -8424,8 +8420,7 @@ Value *CodeGenFunction::EmitARMBuiltinExpr(unsigned BuiltinID,
     }
 
     Value *LdPtr = EmitScalarExpr(E->getArg(0));
-    Value *Val = Builder.CreateCall(F, Builder.CreateBitCast(LdPtr, Int8PtrTy),
-                                    "ldrexd");
+    Value *Val = Builder.CreateCall(F, LdPtr, "ldrexd");
 
     Value *Val0 = Builder.CreateExtractValue(Val, 1);
     Value *Val1 = Builder.CreateExtractValue(Val, 0);
@@ -8483,7 +8478,7 @@ Value *CodeGenFunction::EmitARMBuiltinExpr(unsigned BuiltinID,
 
     Value *Arg0 = Builder.CreateExtractValue(Val, 0);
     Value *Arg1 = Builder.CreateExtractValue(Val, 1);
-    Value *StPtr = Builder.CreateBitCast(EmitScalarExpr(E->getArg(1)), Int8PtrTy);
+    Value *StPtr = EmitScalarExpr(E->getArg(1));
     return Builder.CreateCall(F, {Arg0, Arg1, StPtr}, "strexd");
   }
 

clang/lib/CodeGen/CGDecl.cpp

@@ -1244,29 +1244,24 @@ static void emitStoresForConstant(CodeGenModule &CGM, const VarDecl &D,
   // If the initializer is small, use a handful of stores.
   if (shouldSplitConstantStore(CGM, ConstantSize)) {
     if (auto *STy = dyn_cast<llvm::StructType>(Ty)) {
-      // FIXME: handle the case when STy != Loc.getElementType().
-      if (STy == Loc.getElementType()) {
-        for (unsigned i = 0; i != constant->getNumOperands(); i++) {
-          Address EltPtr = Builder.CreateStructGEP(Loc, i);
-          emitStoresForConstant(
-              CGM, D, EltPtr, isVolatile, Builder,
-              cast<llvm::Constant>(Builder.CreateExtractValue(constant, i)),
-              IsAutoInit);
-        }
-        return;
+      const llvm::StructLayout *Layout =
+          CGM.getDataLayout().getStructLayout(STy);
+      for (unsigned i = 0; i != constant->getNumOperands(); i++) {
+        CharUnits CurOff = CharUnits::fromQuantity(Layout->getElementOffset(i));
+        Address EltPtr = Builder.CreateConstInBoundsByteGEP(
+            Loc.withElementType(CGM.Int8Ty), CurOff);
+        emitStoresForConstant(CGM, D, EltPtr, isVolatile, Builder,
+                              constant->getAggregateElement(i), IsAutoInit);
       }
+      return;
     } else if (auto *ATy = dyn_cast<llvm::ArrayType>(Ty)) {
-      // FIXME: handle the case when ATy != Loc.getElementType().
-      if (ATy == Loc.getElementType()) {
-        for (unsigned i = 0; i != ATy->getNumElements(); i++) {
-          Address EltPtr = Builder.CreateConstArrayGEP(Loc, i);
-          emitStoresForConstant(
-              CGM, D, EltPtr, isVolatile, Builder,
-              cast<llvm::Constant>(Builder.CreateExtractValue(constant, i)),
-              IsAutoInit);
-        }
-        return;
+      for (unsigned i = 0; i != ATy->getNumElements(); i++) {
+        Address EltPtr = Builder.CreateConstGEP(
+            Loc.withElementType(ATy->getElementType()), i);
+        emitStoresForConstant(CGM, D, EltPtr, isVolatile, Builder,
+                              constant->getAggregateElement(i), IsAutoInit);
       }
+      return;
     }
   }
 

clang/lib/CodeGen/CGExprConstant.cpp

@@ -1861,10 +1861,7 @@ class ConstantLValueEmitter : public ConstStmtVisitor<ConstantLValueEmitter,
     if (!hasNonZeroOffset())
       return C;
 
-    llvm::Type *origPtrTy = C->getType();
-    C = llvm::ConstantExpr::getGetElementPtr(CGM.Int8Ty, C, getOffset());
-    C = llvm::ConstantExpr::getPointerCast(C, origPtrTy);
-    return C;
+    return llvm::ConstantExpr::getGetElementPtr(CGM.Int8Ty, C, getOffset());
   }
 };
 

clang/lib/CodeGen/CGOpenMPRuntimeGPU.cpp

@@ -3540,6 +3540,8 @@ void CGOpenMPRuntimeGPU::processRequiresDirective(
       case CudaArch::GFX1103:
       case CudaArch::GFX1150:
       case CudaArch::GFX1151:
+      case CudaArch::GFX1200:
+      case CudaArch::GFX1201:
       case CudaArch::Generic:
       case CudaArch::UNUSED:
       case CudaArch::UNKNOWN:

clang/lib/CodeGen/CGStmt.cpp

@@ -1299,8 +1299,7 @@ void CodeGenFunction::EmitReturnStmt(const ReturnStmt &S) {
     SLocPtr->setUnnamedAddr(llvm::GlobalValue::UnnamedAddr::Global);
     CGM.getSanitizerMetadata()->disableSanitizerForGlobal(SLocPtr);
     assert(ReturnLocation.isValid() && "No valid return location");
-    Builder.CreateStore(Builder.CreateBitCast(SLocPtr, Int8PtrTy),
-                        ReturnLocation);
+    Builder.CreateStore(SLocPtr, ReturnLocation);
   }
 
   // Returning from an outlined SEH helper is UB, and we already warn on it.

clang/lib/StaticAnalyzer/Checkers/StreamChecker.cpp

@@ -250,9 +250,12 @@ class StreamChecker : public Checker<check::PreCall, eval::Call,
       {{{"fwrite"}, 4},
        {std::bind(&StreamChecker::preReadWrite, _1, _2, _3, _4, false),
         std::bind(&StreamChecker::evalFreadFwrite, _1, _2, _3, _4, false), 3}},
+      {{{"fgetc"}, 1},
+       {std::bind(&StreamChecker::preReadWrite, _1, _2, _3, _4, true),
+        std::bind(&StreamChecker::evalFgetcFputc, _1, _2, _3, _4, true), 0}},
       {{{"fputc"}, 2},
        {std::bind(&StreamChecker::preReadWrite, _1, _2, _3, _4, false),
-        &StreamChecker::evalFputc, 1}},
+        std::bind(&StreamChecker::evalFgetcFputc, _1, _2, _3, _4, false), 1}},
       {{{"fseek"}, 3},
        {&StreamChecker::preFseek, &StreamChecker::evalFseek, 0}},
       {{{"ftell"}, 1},
@@ -314,8 +317,8 @@ class StreamChecker : public Checker<check::PreCall, eval::Call,
   void evalFreadFwrite(const FnDescription *Desc, const CallEvent &Call,
                        CheckerContext &C, bool IsFread) const;
 
-  void evalFputc(const FnDescription *Desc, const CallEvent &Call,
-                 CheckerContext &C) const;
+  void evalFgetcFputc(const FnDescription *Desc, const CallEvent &Call,
+                      CheckerContext &C, bool IsRead) const;
 
   void preFseek(const FnDescription *Desc, const CallEvent &Call,
                 CheckerContext &C) const;
@@ -751,8 +754,9 @@ void StreamChecker::evalFreadFwrite(const FnDescription *Desc,
     C.addTransition(StateFailed);
 }
 
-void StreamChecker::evalFputc(const FnDescription *Desc, const CallEvent &Call,
-                              CheckerContext &C) const {
+void StreamChecker::evalFgetcFputc(const FnDescription *Desc,
+                                   const CallEvent &Call, CheckerContext &C,
+                                   bool IsRead) const {
   ProgramStateRef State = C.getState();
   SymbolRef StreamSym = getStreamArg(Desc, Call).getAsSymbol();
   if (!StreamSym)
@@ -768,26 +772,70 @@ void StreamChecker::evalFputc(const FnDescription *Desc, const CallEvent &Call,
 
   assertStreamStateOpened(OldSS);
 
+  // `fgetc` returns the read character on success, otherwise returns EOF.
   // `fputc` returns the written character on success, otherwise returns EOF.
 
-  // Generate a transition for the success state.
-  std::optional<NonLoc> PutVal = Call.getArgSVal(0).getAs<NonLoc>();
-  if (!PutVal)
-    return;
-  ProgramStateRef StateNotFailed =
-      State->BindExpr(CE, C.getLocationContext(), *PutVal);
-  StateNotFailed =
-      StateNotFailed->set<StreamMap>(StreamSym, StreamState::getOpened(Desc));
-  C.addTransition(StateNotFailed);
+  // Generate a transition for the success state of fputc.
+  if (!IsRead) {
+    std::optional<NonLoc> PutVal = Call.getArgSVal(0).getAs<NonLoc>();
+    if (!PutVal)
+      return;
+    ProgramStateRef StateNotFailed =
+        State->BindExpr(CE, C.getLocationContext(), *PutVal);
+    StateNotFailed =
+        StateNotFailed->set<StreamMap>(StreamSym, StreamState::getOpened(Desc));
+    C.addTransition(StateNotFailed);
+  }
+  // Generate a transition for the success state of fgetc.
+  // If we know the state to be FEOF at fgetc, do not add a success state.
+  else if (OldSS->ErrorState != ErrorFEof) {
+    NonLoc RetVal = makeRetVal(C, CE).castAs<NonLoc>();
+    ProgramStateRef StateNotFailed =
+        State->BindExpr(CE, C.getLocationContext(), RetVal);
+    SValBuilder &SVB = C.getSValBuilder();
+    auto &ASTC = C.getASTContext();
+    // The returned 'unsigned char' of `fgetc` is converted to 'int',
+    // so we need to check if it is in range [0, 255].
+    auto CondLow =
+        SVB.evalBinOp(State, BO_GE, RetVal, SVB.makeZeroVal(ASTC.IntTy),
+                      SVB.getConditionType())
+            .getAs<DefinedOrUnknownSVal>();
+    auto CondHigh =
+        SVB.evalBinOp(State, BO_LE, RetVal,
+                      SVB.makeIntVal(SVB.getBasicValueFactory()
+                                         .getMaxValue(ASTC.UnsignedCharTy)
+                                         .getLimitedValue(),
+                                     ASTC.IntTy),
+                      SVB.getConditionType())
+            .getAs<DefinedOrUnknownSVal>();
+    if (!CondLow || !CondHigh)
+      return;
+    StateNotFailed = StateNotFailed->assume(*CondLow, true);
+    if (!StateNotFailed)
+      return;
+    StateNotFailed = StateNotFailed->assume(*CondHigh, true);
+    if (!StateNotFailed)
+      return;
+    C.addTransition(StateNotFailed);
+  }
 
   // Add transition for the failed state.
+  ProgramStateRef StateFailed = bindInt(*EofVal, State, C, CE);
+
   // If a (non-EOF) error occurs, the resulting value of the file position
   // indicator for the stream is indeterminate.
-  ProgramStateRef StateFailed = bindInt(*EofVal, State, C, CE);
-  StreamState NewSS = StreamState::getOpened(
-      Desc, ErrorFError, /*IsFilePositionIndeterminate*/ true);
+  StreamErrorState NewES;
+  if (IsRead)
+    NewES =
+        OldSS->ErrorState == ErrorFEof ? ErrorFEof : ErrorFEof | ErrorFError;
+  else
+    NewES = ErrorFError;
+  StreamState NewSS = StreamState::getOpened(Desc, NewES, !NewES.isFEof());
   StateFailed = StateFailed->set<StreamMap>(StreamSym, NewSS);
-  C.addTransition(StateFailed);
+  if (IsRead && OldSS->ErrorState != ErrorFEof)
+    C.addTransition(StateFailed, constructSetEofNoteTag(C, StreamSym));
+  else
+    C.addTransition(StateFailed);
 }
 
 void StreamChecker::preFseek(const FnDescription *Desc, const CallEvent &Call,

clang/test/Analysis/Inputs/system-header-simulator.h

@@ -48,6 +48,7 @@ FILE *freopen(const char *restrict pathname, const char *restrict mode, FILE *re
 int fclose(FILE *fp);
 size_t fread(void *restrict, size_t, size_t, FILE *restrict);
 size_t fwrite(const void *restrict, size_t, size_t, FILE *restrict);
+int fgetc(FILE *stream);
 int fputc(int ch, FILE *stream);
 int fseek(FILE *__stream, long int __off, int __whence);
 long int ftell(FILE *__stream);