Use FPContractModeKind universally

FPContractModeKind is the codegen option flag which is already ternary (off,
on, fast).  This makes it universally the type for the contractable info
across the front-end:

* In FPOptions (i.e. in the Sema + in the expression nodes).
* In LangOpts::DefaultFPContractMode which is the option that initializes
FPOptions in the Sema.

Another way to look at this change is that before fp-contractable on/off were
the only states handled to the front-end:
 * For "on", FMA folding was performed by  the front-end
 * For "fast", we simply forwarded the flag to TargetOptions to handle it in
 LLVM

Now off/on/fast are all exposed because for fast we will generate
fast-math-flags during CodeGen.

This is toward moving fp-contraction=fast from an LLVM TargetOption to a
FastMathFlag in order to fix PR25721.

---
This is a recommit of r299027 with an adjustment to the test
CodeGenCUDA/fp-contract.cu.  The test assumed that even
though -ffp-contract=on is passed FE-based folding of FMA won't happen.

This is obviously wrong since the user is asking for this explicitly with the
option.  CUDA is different that -ffp-contract=fast is on by default.

The test used to "work" because contract=fast and contract=on were maintained
separately and we didn't fold in the FE because contract=fast was on due to
the target-default.  This patch consolidates the contract=on/fast/off state
into a ternary state hence the change in behavior.
---

Differential Revision: https://reviews.llvm.org/D31167

git-svn-id: https://llvm.org/svn/llvm-project/cfe/trunk@299033 91177308-0d34-0410-b5e6-96231b3b80d8

include/clang/AST/Expr.h

@@ -2920,7 +2920,7 @@ private:
 
   // This is only meaningful for operations on floating point types and 0
   // otherwise.
-  unsigned FPFeatures : 1;
+  unsigned FPFeatures : 2;
   SourceLocation OpLoc;
 
   enum { LHS, RHS, END_EXPR };
@@ -3078,8 +3078,8 @@ public:
 
   // Get the FP contractability status of this operator. Only meaningful for
   // operations on floating point types.
-  bool isFPContractable() const {
-    return FPOptions(FPFeatures).isFPContractable();
+  bool isFPContractableWithinStatement() const {
+    return FPOptions(FPFeatures).allowFPContractWithinStatement();
   }
 
 protected:

include/clang/AST/ExprCXX.h

@@ -117,7 +117,9 @@ public:
 
   // Get the FP contractability status of this operator. Only meaningful for
   // operations on floating point types.
-  bool isFPContractable() const { return FPFeatures.isFPContractable(); }
+  bool isFPContractableWithinStatement() const {
+    return FPFeatures.allowFPContractWithinStatement();
+  }
 
   friend class ASTStmtReader;
   friend class ASTStmtWriter;

include/clang/Basic/LangOptions.def

@@ -216,7 +216,8 @@ BENIGN_LANGOPT(DebuggerObjCLiteral , 1, 0, "debugger Objective-C literals and su
 BENIGN_LANGOPT(SpellChecking , 1, 1, "spell-checking")
 LANGOPT(SinglePrecisionConstants , 1, 0, "treating double-precision floating point constants as single precision constants")
 LANGOPT(FastRelaxedMath , 1, 0, "OpenCL fast relaxed math")
-LANGOPT(DefaultFPContract , 1, 0, "FP_CONTRACT")
+/// \brief FP_CONTRACT mode (on/off/fast).
+ENUM_LANGOPT(DefaultFPContractMode, FPContractModeKind, 2, FPC_Off, "FP contraction type")
 LANGOPT(NoBitFieldTypeAlign , 1, 0, "bit-field type alignment")
 LANGOPT(HexagonQdsp6Compat , 1, 0, "hexagon-qdsp6 backward compatibility")
 LANGOPT(ObjCAutoRefCount , 1, 0, "Objective-C automated reference counting")

include/clang/Basic/LangOptions.h

@@ -88,6 +88,12 @@ public:
     MSVC2015 = 19
   };
 
+  enum FPContractModeKind {
+    FPC_Off,        // Form fused FP ops only where result will not be affected.
+    FPC_On,         // Form fused FP ops according to FP_CONTRACT rules.
+    FPC_Fast        // Aggressively fuse FP ops (E.g. FMA).
+  };
+
 public:
   /// \brief Set of enabled sanitizers.
   SanitizerSet Sanitize;
@@ -180,22 +186,35 @@ public:
 /// \brief Floating point control options
 class FPOptions {
 public:
-  FPOptions() : fp_contract(0) {}
+  FPOptions() : fp_contract(LangOptions::FPC_Off) {}
 
-  explicit FPOptions(unsigned I) : fp_contract(I) {}
+  // Used for serializing.
+  explicit FPOptions(unsigned I)
+      : fp_contract(static_cast<LangOptions::FPContractModeKind>(I)) {}
 
   explicit FPOptions(const LangOptions &LangOpts)
-      : fp_contract(LangOpts.DefaultFPContract) {}
+      : fp_contract(LangOpts.getDefaultFPContractMode()) {}
 
-  void setFPContractable(bool V) { fp_contract = V; }
-  bool isFPContractable() const { return fp_contract; }
+  bool allowFPContractWithinStatement() const {
+    return fp_contract == LangOptions::FPC_On;
+  }
+  bool allowFPContractAcrossStatement() const {
+    return fp_contract == LangOptions::FPC_Fast;
+  }
+  void setAllowFPContractWithinStatement() {
+    fp_contract = LangOptions::FPC_On;
+  }
+  void setAllowFPContractAcrossStatement() {
+    fp_contract = LangOptions::FPC_Fast;
+  }
+  void setDisallowFPContract() { fp_contract = LangOptions::FPC_Off; }
 
   /// Used to serialize this.
   unsigned getInt() const { return fp_contract; }
 
 private:
   /// Adjust BinaryOperator::FPFeatures to match the bit-field size of this.
-  unsigned fp_contract : 1;
+  LangOptions::FPContractModeKind fp_contract : 2;
 };
 
 /// \brief Describes the kind of translation unit being processed.

include/clang/Frontend/CodeGenOptions.def

@@ -65,8 +65,6 @@ CODEGENOPT(EmitGcovArcs      , 1, 0) ///< Emit coverage data files, aka. GCDA.
 CODEGENOPT(EmitGcovNotes     , 1, 0) ///< Emit coverage "notes" files, aka GCNO.
 CODEGENOPT(EmitOpenCLArgMetadata , 1, 0) ///< Emit OpenCL kernel arg metadata.
 CODEGENOPT(EmulatedTLS       , 1, 0) ///< Set when -femulated-tls is enabled.
-/// \brief FP_CONTRACT mode (on/off/fast).
-ENUM_CODEGENOPT(FPContractMode, FPContractModeKind, 2, FPC_On)
 /// \brief Embed Bitcode mode (off/all/bitcode/marker).
 ENUM_CODEGENOPT(EmbedBitcode, EmbedBitcodeKind, 2, Embed_Off)
 CODEGENOPT(ForbidGuardVariables , 1, 0) ///< Issue errors if C++ guard variables

include/clang/Frontend/CodeGenOptions.h

@@ -69,12 +69,6 @@ public:
     LocalExecTLSModel
   };
 
-  enum FPContractModeKind {
-    FPC_Off,        // Form fused FP ops only where result will not be affected.
-    FPC_On,         // Form fused FP ops according to FP_CONTRACT rules.
-    FPC_Fast        // Aggressively fuse FP ops (E.g. FMA).
-  };
-
   enum StructReturnConventionKind {
     SRCK_Default,  // No special option was passed.
     SRCK_OnStack,  // Small structs on the stack (-fpcc-struct-return).

lib/CodeGen/BackendUtil.cpp

@@ -561,14 +561,14 @@ void EmitAssemblyHelper::CreateTargetMachine(bool MustCreateTM) {
           .Default(llvm::FloatABI::Default);
 
   // Set FP fusion mode.
-  switch (CodeGenOpts.getFPContractMode()) {
-  case CodeGenOptions::FPC_Off:
+  switch (LangOpts.getDefaultFPContractMode()) {
+  case LangOptions::FPC_Off:
     Options.AllowFPOpFusion = llvm::FPOpFusion::Strict;
     break;
-  case CodeGenOptions::FPC_On:
+  case LangOptions::FPC_On:
     Options.AllowFPOpFusion = llvm::FPOpFusion::Standard;
     break;
-  case CodeGenOptions::FPC_Fast:
+  case LangOptions::FPC_Fast:
     Options.AllowFPOpFusion = llvm::FPOpFusion::Fast;
     break;
   }

lib/CodeGen/CGExprScalar.cpp

@@ -2672,12 +2672,7 @@ static Value* tryEmitFMulAdd(const BinOpInfo &op,
          "Only fadd/fsub can be the root of an fmuladd.");
 
   // Check whether this op is marked as fusable.
-  if (!op.FPFeatures.isFPContractable())
-    return nullptr;
-
-  // Check whether -ffp-contract=on. (If -ffp-contract=off/fast, fusing is
-  // either disabled, or handled entirely by the LLVM backend).
-  if (CGF.CGM.getCodeGenOpts().getFPContractMode() != CodeGenOptions::FPC_On)
+  if (!op.FPFeatures.allowFPContractWithinStatement())
     return nullptr;
 
   // We have a potentially fusable op. Look for a mul on one of the operands.

lib/Frontend/CompilerInvocation.cpp

@@ -816,18 +816,6 @@ static bool ParseCodeGenArgs(CodeGenOptions &Opts, ArgList &Args, InputKind IK,
     }
   }
 
-  if (Arg *A = Args.getLastArg(OPT_ffp_contract)) {
-    StringRef Val = A->getValue();
-    if (Val == "fast")
-      Opts.setFPContractMode(CodeGenOptions::FPC_Fast);
-    else if (Val == "on")
-      Opts.setFPContractMode(CodeGenOptions::FPC_On);
-    else if (Val == "off")
-      Opts.setFPContractMode(CodeGenOptions::FPC_Off);
-    else
-      Diags.Report(diag::err_drv_invalid_value) << A->getAsString(Args) << Val;
-  }
-
   if (Arg *A = Args.getLastArg(OPT_fdenormal_fp_math_EQ)) {
     StringRef Val = A->getValue();
     if (Val == "ieee")
@@ -1647,7 +1635,7 @@ void CompilerInvocation::setLangDefaults(LangOptions &Opts, InputKind IK,
     Opts.AltiVec = 0;
     Opts.ZVector = 0;
     Opts.LaxVectorConversions = 0;
-    Opts.DefaultFPContract = 1;
+    Opts.setDefaultFPContractMode(LangOptions::FPC_On);
     Opts.NativeHalfType = 1;
     Opts.NativeHalfArgsAndReturns = 1;
     // Include default header file for OpenCL.
@@ -1658,6 +1646,9 @@ void CompilerInvocation::setLangDefaults(LangOptions &Opts, InputKind IK,
 
   Opts.CUDA = IK == IK_CUDA || IK == IK_PreprocessedCuda ||
               LangStd == LangStandard::lang_cuda;
+  if (Opts.CUDA)
+    // Set default FP_CONTRACT to FAST.
+    Opts.setDefaultFPContractMode(LangOptions::FPC_Fast);
 
   Opts.RenderScript = IK == IK_RenderScript;
   if (Opts.RenderScript) {
@@ -2282,6 +2273,18 @@ static void ParseLangArgs(LangOptions &Opts, ArgList &Args, InputKind IK,
                       Args.hasArg(OPT_cl_unsafe_math_optimizations) ||
                       Args.hasArg(OPT_cl_fast_relaxed_math);
 
+  if (Arg *A = Args.getLastArg(OPT_ffp_contract)) {
+    StringRef Val = A->getValue();
+    if (Val == "fast")
+      Opts.setDefaultFPContractMode(LangOptions::FPC_Fast);
+    else if (Val == "on")
+      Opts.setDefaultFPContractMode(LangOptions::FPC_On);
+    else if (Val == "off")
+      Opts.setDefaultFPContractMode(LangOptions::FPC_Off);
+    else
+      Diags.Report(diag::err_drv_invalid_value) << A->getAsString(Args) << Val;
+  }
+
   Opts.RetainCommentsFromSystemHeaders =
       Args.hasArg(OPT_fretain_comments_from_system_headers);
 
@@ -2536,10 +2539,6 @@ bool CompilerInvocation::CreateFromArgs(CompilerInvocation &Res,
     // triple used for host compilation.
     if (LangOpts.CUDAIsDevice)
       Res.getTargetOpts().HostTriple = Res.getFrontendOpts().AuxTriple;
-
-    // Set default FP_CONTRACT to FAST.
-    if (!Args.hasArg(OPT_ffp_contract))
-      Res.getCodeGenOpts().setFPContractMode(CodeGenOptions::FPC_Fast);
   }
 
   // FIXME: Override value name discarding when asan or msan is used because the

lib/Sema/SemaAttr.cpp

@@ -450,13 +450,16 @@ void Sema::ActOnPragmaVisibility(const IdentifierInfo* VisType,
 void Sema::ActOnPragmaFPContract(tok::OnOffSwitch OOS) {
   switch (OOS) {
   case tok::OOS_ON:
-    FPFeatures.setFPContractable(true);
+    FPFeatures.setAllowFPContractWithinStatement();
     break;
   case tok::OOS_OFF:
-    FPFeatures.setFPContractable(false);
+    FPFeatures.setDisallowFPContract();
     break;
   case tok::OOS_DEFAULT:
-    FPFeatures.setFPContractable(getLangOpts().DefaultFPContract);
+    if (getLangOpts().getDefaultFPContractMode() == LangOptions::FPC_On)
+      FPFeatures.setAllowFPContractWithinStatement();
+    else
+      FPFeatures.setDisallowFPContract();
     break;
   }
 }

test/CodeGenCUDA/fp-contract.cu

@@ -10,10 +10,10 @@
 // RUN:   -ffp-contract=fast -disable-llvm-passes -o - %s \
 // RUN:   | FileCheck -check-prefix ENABLED %s
 
-// Explicit -ffp-contract=on -- fusing by front-end (disabled).
+// Explicit -ffp-contract=on -- fusing by front-end.
 // RUN: %clang_cc1 -fcuda-is-device -triple nvptx-nvidia-cuda -S \
 // RUN:   -ffp-contract=on -disable-llvm-passes -o - %s \
-// RUN:   | FileCheck -check-prefix DISABLED %s
+// RUN:   | FileCheck -check-prefix ENABLED %s
 
 // Explicit -ffp-contract=off should disable instruction fusing.
 // RUN: %clang_cc1 -fcuda-is-device -triple nvptx-nvidia-cuda -S \