llvmbot wrote:
<!--LLVM PR SUMMARY COMMENT--> @llvm/pr-subscribers-clang Author: Karl-Johan Karlsson (karka228) <details> <summary>Changes</summary> This is a fix for the issue #<!-- -->87758 where fast-math flags are not propagated all builtins. It seems like pragmas with fast math flags was only propagated to calls of unary floating point builtins. This patch propagate them also for binary and ternary floating point builtins. --- Full diff: https://github.com/llvm/llvm-project/pull/90377.diff 2 Files Affected: - (modified) clang/lib/CodeGen/CGBuiltin.cpp (+3-3) - (added) clang/test/CodeGen/pr87758.c (+28) ``````````diff diff --git a/clang/lib/CodeGen/CGBuiltin.cpp b/clang/lib/CodeGen/CGBuiltin.cpp index d08ab539148914..d61a63ac61572d 100644 --- a/clang/lib/CodeGen/CGBuiltin.cpp +++ b/clang/lib/CodeGen/CGBuiltin.cpp @@ -513,8 +513,8 @@ static Value *emitBinaryMaybeConstrainedFPBuiltin(CodeGenFunction &CGF, llvm::Value *Src0 = CGF.EmitScalarExpr(E->getArg(0)); llvm::Value *Src1 = CGF.EmitScalarExpr(E->getArg(1)); + CodeGenFunction::CGFPOptionsRAII FPOptsRAII(CGF, E); if (CGF.Builder.getIsFPConstrained()) { - CodeGenFunction::CGFPOptionsRAII FPOptsRAII(CGF, E); Function *F = CGF.CGM.getIntrinsic(ConstrainedIntrinsicID, Src0->getType()); return CGF.Builder.CreateConstrainedFPCall(F, { Src0, Src1 }); } else { @@ -530,8 +530,8 @@ static Value *emitBinaryExpMaybeConstrainedFPBuiltin( llvm::Value *Src0 = CGF.EmitScalarExpr(E->getArg(0)); llvm::Value *Src1 = CGF.EmitScalarExpr(E->getArg(1)); + CodeGenFunction::CGFPOptionsRAII FPOptsRAII(CGF, E); if (CGF.Builder.getIsFPConstrained()) { - CodeGenFunction::CGFPOptionsRAII FPOptsRAII(CGF, E); Function *F = CGF.CGM.getIntrinsic(ConstrainedIntrinsicID, {Src0->getType(), Src1->getType()}); return CGF.Builder.CreateConstrainedFPCall(F, {Src0, Src1}); @@ -551,8 +551,8 @@ static Value *emitTernaryMaybeConstrainedFPBuiltin(CodeGenFunction &CGF, llvm::Value *Src1 = CGF.EmitScalarExpr(E->getArg(1)); llvm::Value *Src2 = CGF.EmitScalarExpr(E->getArg(2)); + CodeGenFunction::CGFPOptionsRAII FPOptsRAII(CGF, E); if (CGF.Builder.getIsFPConstrained()) { - CodeGenFunction::CGFPOptionsRAII FPOptsRAII(CGF, E); Function *F = CGF.CGM.getIntrinsic(ConstrainedIntrinsicID, Src0->getType()); return CGF.Builder.CreateConstrainedFPCall(F, { Src0, Src1, Src2 }); } else { diff --git a/clang/test/CodeGen/pr87758.c b/clang/test/CodeGen/pr87758.c new file mode 100644 index 00000000000000..05b3232986e0a6 --- /dev/null +++ b/clang/test/CodeGen/pr87758.c @@ -0,0 +1,28 @@ +// NOTE: Assertions have been autogenerated by utils/update_cc_test_checks.py UTC_ARGS: --version 4 +// RUN: %clang_cc1 -triple x86_64-linux-gnu -O3 -emit-llvm -o - %s \ +// RUN: | FileCheck -check-prefix=CHECK %s + +// Reproducer for issue #87758 +// The testcase below verifies that the "fast" flag are set on the calls. + +float sqrtf(float x); +float powf(float x, float y); +float fmaf(float x, float y, float z); + +#pragma float_control(push) +#pragma float_control(precise, off) +// CHECK-LABEL: define dso_local float @fp_precise_libm_calls( +// CHECK-SAME: float noundef [[A:%.*]], float noundef [[B:%.*]], float noundef [[C:%.*]]) local_unnamed_addr #[[ATTR0:[0-9]+]] { +// CHECK-NEXT: entry: +// CHECK-NEXT: [[TMP0:%.*]] = tail call fast float @llvm.sqrt.f32(float [[A]]) +// CHECK-NEXT: [[TMP1:%.*]] = tail call fast float @llvm.pow.f32(float [[TMP0]], float [[B]]) +// CHECK-NEXT: [[TMP2:%.*]] = tail call fast float @llvm.fma.f32(float [[TMP1]], float [[B]], float [[C]]) +// CHECK-NEXT: ret float [[TMP2]] +// +float fp_precise_libm_calls(float a, float b, float c) { + a = sqrtf(a); + a = powf(a,b); + a = fmaf(a,b,c); + return a; +} +#pragma float_control(pop) `````````` </details> https://github.com/llvm/llvm-project/pull/90377 _______________________________________________ cfe-commits mailing list cfe-commits@lists.llvm.org https://lists.llvm.org/cgi-bin/mailman/listinfo/cfe-commits
