[clang] 7fac1ac - Set the LLVM FP optimization flags conservatively.
John McCall via cfe-commits
cfe-commits at lists.llvm.org
Thu Jun 11 15:16:58 PDT 2020
Author: John McCall
Date: 2020-06-11T18:16:41-04:00
New Revision: 7fac1acc617113b7a3276ee0f0664bedca978292
URL: https://github.com/llvm/llvm-project/commit/7fac1acc617113b7a3276ee0f0664bedca978292
DIFF: https://github.com/llvm/llvm-project/commit/7fac1acc617113b7a3276ee0f0664bedca978292.diff
LOG: Set the LLVM FP optimization flags conservatively.
Functions can have local pragmas that override the global settings.
We set the flags eagerly based on global settings, but if we emit
an expression under the influence of a pragma, we clear the
appropriate flags from the function.
In order to avoid doing a ton of redundant work whenever we emit
an FP expression, configure the IRBuilder to default to global
settings, and only reconfigure it when we see an FP expression
that's not using the global settings.
Patch by Michele Scandale!
https://reviews.llvm.org/D80462
Added:
clang/test/CodeGen/fp-function-attrs.cpp
Modified:
clang/include/clang/Basic/LangOptions.h
clang/lib/CodeGen/CGExprScalar.cpp
clang/lib/CodeGen/CodeGenFunction.cpp
clang/lib/CodeGen/CodeGenFunction.h
Removed:
################################################################################
diff --git a/clang/include/clang/Basic/LangOptions.h b/clang/include/clang/Basic/LangOptions.h
index ef56a78b7d48..7b92a8964862 100644
--- a/clang/include/clang/Basic/LangOptions.h
+++ b/clang/include/clang/Basic/LangOptions.h
@@ -529,6 +529,13 @@ class FPOptions {
unsigned approx_func : 1;
};
+inline bool operator==(FPOptions LHS, FPOptions RHS) {
+ return LHS.getAsOpaqueInt() == RHS.getAsOpaqueInt();
+}
+inline bool operator!=(FPOptions LHS, FPOptions RHS) {
+ return LHS.getAsOpaqueInt() != RHS.getAsOpaqueInt();
+}
+
/// Describes the kind of translation unit being processed.
enum TranslationUnitKind {
/// The translation unit is a complete translation unit.
diff --git a/clang/lib/CodeGen/CGExprScalar.cpp b/clang/lib/CodeGen/CGExprScalar.cpp
index b2bc38b329ef..83614b031543 100644
--- a/clang/lib/CodeGen/CGExprScalar.cpp
+++ b/clang/lib/CodeGen/CGExprScalar.cpp
@@ -215,23 +215,6 @@ static bool CanElideOverflowCheck(const ASTContext &Ctx, const BinOpInfo &Op) {
(2 * Ctx.getTypeSize(RHSTy)) < PromotedSize;
}
-static void setBuilderFlagsFromFPFeatures(CGBuilderTy &Builder,
- CodeGenFunction &CGF,
- FPOptions FPFeatures) {
- auto NewRoundingBehavior = FPFeatures.getRoundingMode();
- Builder.setDefaultConstrainedRounding(NewRoundingBehavior);
- auto NewExceptionBehavior =
- ToConstrainedExceptMD(FPFeatures.getExceptionMode());
- Builder.setDefaultConstrainedExcept(NewExceptionBehavior);
- CGF.SetFastMathFlags(FPFeatures);
- assert((CGF.CurFuncDecl == nullptr || Builder.getIsFPConstrained() ||
- isa<CXXConstructorDecl>(CGF.CurFuncDecl) ||
- isa<CXXDestructorDecl>(CGF.CurFuncDecl) ||
- (NewExceptionBehavior == llvm::fp::ebIgnore &&
- NewRoundingBehavior == llvm::RoundingMode::NearestTiesToEven)) &&
- "FPConstrained should be enabled on entire function");
-}
-
class ScalarExprEmitter
: public StmtVisitor<ScalarExprEmitter, Value*> {
CodeGenFunction &CGF;
@@ -764,8 +747,7 @@ class ScalarExprEmitter
if (Ops.LHS->getType()->isFPOrFPVectorTy()) {
// Preserve the old values
- llvm::IRBuilder<>::FastMathFlagGuard FMFG(Builder);
- setBuilderFlagsFromFPFeatures(Builder, CGF, Ops.FPFeatures);
+ CodeGenFunction::CGFPOptionsRAII FPOptsRAII(CGF, Ops.FPFeatures);
return Builder.CreateFMul(Ops.LHS, Ops.RHS, "mul");
}
if (Ops.isFixedPointOp())
@@ -2769,9 +2751,8 @@ Value *ScalarExprEmitter::VisitUnaryLNot(const UnaryOperator *E) {
Value *Zero = llvm::Constant::getNullValue(Oper->getType());
Value *Result;
if (Oper->getType()->isFPOrFPVectorTy()) {
- llvm::IRBuilder<>::FastMathFlagGuard FMFG(Builder);
- setBuilderFlagsFromFPFeatures(Builder, CGF,
- E->getFPFeatures(CGF.getLangOpts()));
+ CodeGenFunction::CGFPOptionsRAII FPOptsRAII(
+ CGF, E->getFPFeatures(CGF.getLangOpts()));
Result = Builder.CreateFCmp(llvm::CmpInst::FCMP_OEQ, Oper, Zero, "cmp");
} else
Result = Builder.CreateICmp(llvm::CmpInst::ICMP_EQ, Oper, Zero, "cmp");
@@ -3183,8 +3164,7 @@ Value *ScalarExprEmitter::EmitDiv(const BinOpInfo &Ops) {
if (Ops.LHS->getType()->isFPOrFPVectorTy()) {
llvm::Value *Val;
- llvm::IRBuilder<>::FastMathFlagGuard FMFG(Builder);
- setBuilderFlagsFromFPFeatures(Builder, CGF, Ops.FPFeatures);
+ CodeGenFunction::CGFPOptionsRAII FPOptsRAII(CGF, Ops.FPFeatures);
Val = Builder.CreateFDiv(Ops.LHS, Ops.RHS, "div");
if (CGF.getLangOpts().OpenCL &&
!CGF.CGM.getCodeGenOpts().CorrectlyRoundedDivSqrt) {
@@ -3562,8 +3542,7 @@ Value *ScalarExprEmitter::EmitAdd(const BinOpInfo &op) {
return EmitOverflowCheckedBinOp(op);
if (op.LHS->getType()->isFPOrFPVectorTy()) {
- llvm::IRBuilder<>::FastMathFlagGuard FMFG(Builder);
- setBuilderFlagsFromFPFeatures(Builder, CGF, op.FPFeatures);
+ CodeGenFunction::CGFPOptionsRAII FPOptsRAII(CGF, op.FPFeatures);
// Try to form an fmuladd.
if (Value *FMulAdd = tryEmitFMulAdd(op, CGF, Builder))
return FMulAdd;
@@ -3750,8 +3729,7 @@ Value *ScalarExprEmitter::EmitSub(const BinOpInfo &op) {
return EmitOverflowCheckedBinOp(op);
if (op.LHS->getType()->isFPOrFPVectorTy()) {
- llvm::IRBuilder<>::FastMathFlagGuard FMFG(Builder);
- setBuilderFlagsFromFPFeatures(Builder, CGF, op.FPFeatures);
+ CodeGenFunction::CGFPOptionsRAII FPOptsRAII(CGF, op.FPFeatures);
// Try to form an fmuladd.
if (Value *FMulAdd = tryEmitFMulAdd(op, CGF, Builder, true))
return FMulAdd;
@@ -4077,8 +4055,7 @@ Value *ScalarExprEmitter::EmitCompare(const BinaryOperator *E,
if (BOInfo.isFixedPointOp()) {
Result = EmitFixedPointBinOp(BOInfo);
} else if (LHS->getType()->isFPOrFPVectorTy()) {
- llvm::IRBuilder<>::FastMathFlagGuard FMFG(Builder);
- setBuilderFlagsFromFPFeatures(Builder, CGF, BOInfo.FPFeatures);
+ CodeGenFunction::CGFPOptionsRAII FPOptsRAII(CGF, BOInfo.FPFeatures);
if (!IsSignaling)
Result = Builder.CreateFCmp(FCmpOpc, LHS, RHS, "cmp");
else
@@ -4231,9 +4208,8 @@ Value *ScalarExprEmitter::VisitBinLAnd(const BinaryOperator *E) {
Value *RHS = Visit(E->getRHS());
Value *Zero = llvm::ConstantAggregateZero::get(LHS->getType());
if (LHS->getType()->isFPOrFPVectorTy()) {
- llvm::IRBuilder<>::FastMathFlagGuard FMFG(Builder);
- setBuilderFlagsFromFPFeatures(Builder, CGF,
- E->getFPFeatures(CGF.getLangOpts()));
+ CodeGenFunction::CGFPOptionsRAII FPOptsRAII(
+ CGF, E->getFPFeatures(CGF.getLangOpts()));
LHS = Builder.CreateFCmp(llvm::CmpInst::FCMP_UNE, LHS, Zero, "cmp");
RHS = Builder.CreateFCmp(llvm::CmpInst::FCMP_UNE, RHS, Zero, "cmp");
} else {
@@ -4318,9 +4294,8 @@ Value *ScalarExprEmitter::VisitBinLOr(const BinaryOperator *E) {
Value *RHS = Visit(E->getRHS());
Value *Zero = llvm::ConstantAggregateZero::get(LHS->getType());
if (LHS->getType()->isFPOrFPVectorTy()) {
- llvm::IRBuilder<>::FastMathFlagGuard FMFG(Builder);
- setBuilderFlagsFromFPFeatures(Builder, CGF,
- E->getFPFeatures(CGF.getLangOpts()));
+ CodeGenFunction::CGFPOptionsRAII FPOptsRAII(
+ CGF, E->getFPFeatures(CGF.getLangOpts()));
LHS = Builder.CreateFCmp(llvm::CmpInst::FCMP_UNE, LHS, Zero, "cmp");
RHS = Builder.CreateFCmp(llvm::CmpInst::FCMP_UNE, RHS, Zero, "cmp");
} else {
diff --git a/clang/lib/CodeGen/CodeGenFunction.cpp b/clang/lib/CodeGen/CodeGenFunction.cpp
index 0fa795d696e5..24fcd7246d4d 100644
--- a/clang/lib/CodeGen/CodeGenFunction.cpp
+++ b/clang/lib/CodeGen/CodeGenFunction.cpp
@@ -65,13 +65,14 @@ CodeGenFunction::CodeGenFunction(CodeGenModule &cgm, bool suppressNewContext)
: CodeGenTypeCache(cgm), CGM(cgm), Target(cgm.getTarget()),
Builder(cgm, cgm.getModule().getContext(), llvm::ConstantFolder(),
CGBuilderInserterTy(this)),
- SanOpts(CGM.getLangOpts().Sanitize), DebugInfo(CGM.getModuleDebugInfo()),
- PGO(cgm), ShouldEmitLifetimeMarkers(shouldEmitLifetimeMarkers(
- CGM.getCodeGenOpts(), CGM.getLangOpts())) {
+ SanOpts(CGM.getLangOpts().Sanitize), CurFPFeatures(CGM.getLangOpts()),
+ DebugInfo(CGM.getModuleDebugInfo()), PGO(cgm),
+ ShouldEmitLifetimeMarkers(
+ shouldEmitLifetimeMarkers(CGM.getCodeGenOpts(), CGM.getLangOpts())) {
if (!suppressNewContext)
CGM.getCXXABI().getMangleContext().startNewFunction();
- SetFastMathFlags(FPOptions(CGM.getLangOpts()));
+ SetFastMathFlags(CurFPFeatures);
SetFPModel();
}
@@ -132,6 +133,51 @@ void CodeGenFunction::SetFastMathFlags(FPOptions FPFeatures) {
Builder.setFastMathFlags(FMF);
}
+CodeGenFunction::CGFPOptionsRAII::CGFPOptionsRAII(CodeGenFunction &CGF,
+ FPOptions FPFeatures)
+ : CGF(CGF), OldFPFeatures(CGF.CurFPFeatures) {
+ CGF.CurFPFeatures = FPFeatures;
+
+ if (OldFPFeatures == FPFeatures)
+ return;
+
+ FMFGuard.emplace(CGF.Builder);
+
+ auto NewRoundingBehavior = FPFeatures.getRoundingMode();
+ CGF.Builder.setDefaultConstrainedRounding(NewRoundingBehavior);
+ auto NewExceptionBehavior =
+ ToConstrainedExceptMD(FPFeatures.getExceptionMode());
+ CGF.Builder.setDefaultConstrainedExcept(NewExceptionBehavior);
+
+ CGF.SetFastMathFlags(FPFeatures);
+
+ assert((CGF.CurFuncDecl == nullptr || CGF.Builder.getIsFPConstrained() ||
+ isa<CXXConstructorDecl>(CGF.CurFuncDecl) ||
+ isa<CXXDestructorDecl>(CGF.CurFuncDecl) ||
+ (NewExceptionBehavior == llvm::fp::ebIgnore &&
+ NewRoundingBehavior == llvm::RoundingMode::NearestTiesToEven)) &&
+ "FPConstrained should be enabled on entire function");
+
+ auto mergeFnAttrValue = [&](StringRef Name, bool Value) {
+ auto OldValue =
+ CGF.CurFn->getFnAttribute(Name).getValueAsString() == "true";
+ auto NewValue = OldValue & Value;
+ if (OldValue != NewValue)
+ CGF.CurFn->addFnAttr(Name, llvm::toStringRef(NewValue));
+ };
+ mergeFnAttrValue("no-infs-fp-math", FPFeatures.noHonorInfs());
+ mergeFnAttrValue("no-nans-fp-math", FPFeatures.noHonorNaNs());
+ mergeFnAttrValue("no-signed-zeros-fp-math", FPFeatures.noSignedZeros());
+ mergeFnAttrValue(
+ "unsafe-fp-math",
+ FPFeatures.allowAssociativeMath() && FPFeatures.allowReciprocalMath() &&
+ FPFeatures.allowApproximateFunctions() && FPFeatures.noSignedZeros());
+}
+
+CodeGenFunction::CGFPOptionsRAII::~CGFPOptionsRAII() {
+ CGF.CurFPFeatures = OldFPFeatures;
+}
+
LValue CodeGenFunction::MakeNaturalAlignAddrLValue(llvm::Value *V, QualType T) {
LValueBaseInfo BaseInfo;
TBAAAccessInfo TBAAInfo;
diff --git a/clang/lib/CodeGen/CodeGenFunction.h b/clang/lib/CodeGen/CodeGenFunction.h
index 8ce5c008d2a3..ed344bfac2c6 100644
--- a/clang/lib/CodeGen/CodeGenFunction.h
+++ b/clang/lib/CodeGen/CodeGenFunction.h
@@ -706,6 +706,18 @@ class CodeGenFunction : public CodeGenTypeCache {
return DominatingValue<T>::save(*this, value);
}
+ class CGFPOptionsRAII {
+ public:
+ CGFPOptionsRAII(CodeGenFunction &CGF, FPOptions FPFeatures);
+ ~CGFPOptionsRAII();
+
+ private:
+ CodeGenFunction &CGF;
+ FPOptions OldFPFeatures;
+ Optional<CGBuilderTy::FastMathFlagGuard> FMFGuard;
+ };
+ FPOptions CurFPFeatures;
+
public:
/// ObjCEHValueStack - Stack of Objective-C exception values, used for
/// rethrows.
diff --git a/clang/test/CodeGen/fp-function-attrs.cpp b/clang/test/CodeGen/fp-function-attrs.cpp
new file mode 100644
index 000000000000..7fbae1c75251
--- /dev/null
+++ b/clang/test/CodeGen/fp-function-attrs.cpp
@@ -0,0 +1,44 @@
+// RUN: %clang_cc1 -triple x86_64-linux-gnu -ffast-math -ffp-contract=fast -emit-llvm -o - %s | FileCheck %s
+
+float test_default(float a, float b, float c) {
+ float tmp = a;
+ tmp += b;
+ tmp += c;
+ return tmp;
+}
+
+// CHECK: define float @_Z12test_defaultfff(float %a, float %b, float %c) [[FAST_ATTRS:#[0-9]+]]
+// CHECK: fadd fast float {{%.+}}, {{%.+}}
+// CHECK: fadd fast float {{%.+}}, {{%.+}}
+
+float test_precise_on_pragma(float a, float b, float c) {
+ float tmp = a;
+ {
+ #pragma float_control(precise, on)
+ tmp += b;
+ }
+ tmp += c;
+ return tmp;
+}
+
+// CHECK: define float @_Z22test_precise_on_pragmafff(float %a, float %b, float %c) [[PRECISE_ATTRS:#[0-9]+]]
+// CHECK: fadd float {{%.+}}, {{%.+}}
+// CHECK: fadd fast float {{%.+}}, {{%.+}}
+
+float test_reassociate_off_pragma(float a, float b, float c) {
+ float tmp = a;
+ {
+ #pragma clang fp reassociate(off)
+ tmp += b;
+ }
+ tmp += c;
+ return tmp;
+}
+
+// CHECK: define float @_Z27test_reassociate_off_pragmafff(float %a, float %b, float %c) [[NOREASSOC_ATTRS:#[0-9]+]]
+// CHECK: fadd nnan ninf nsz arcp contract afn float {{%.+}}, {{%.+}}
+// CHECK: fadd fast float {{%.+}}, {{%.+}}
+
+// CHECK: attributes [[FAST_ATTRS]] = { {{.*}}"no-infs-fp-math"="true" {{.*}}"no-nans-fp-math"="true" "no-signed-zeros-fp-math"="true" {{.*}}"unsafe-fp-math"="true"{{.*}} }
+// CHECK: attributes [[PRECISE_ATTRS]] = { {{.*}}"no-infs-fp-math"="false" {{.*}}"no-nans-fp-math"="false" "no-signed-zeros-fp-math"="false" {{.*}}"unsafe-fp-math"="false"{{.*}} }
+// CHECK: attributes [[NOREASSOC_ATTRS]] = { {{.*}}"no-infs-fp-math"="true" {{.*}}"no-nans-fp-math"="true" "no-signed-zeros-fp-math"="true" {{.*}}"unsafe-fp-math"="false"{{.*}} }
More information about the cfe-commits
mailing list