From 1e27425ada352b97773730999fb0f63fab99a89e Mon Sep 17 00:00:00 2001 From: Razvan Lupusoru Date: Wed, 19 Jul 2023 11:29:46 -0700 Subject: [PATCH] [flang] Fix complex libm use logic problems Fix the various complex libm selection logic issues from D155310: - disableMlirComplex is set to false. This means that using mlir complex is enabled. Yet, the current code still selects libm. - If we enable mlir complex, we should not check if use approx is enabled. Namely, we should use mlir complex either if we enable mlir complex OR use approx is enabled. To fix the issues, we flip the logic of `disableMlirComplex` to enable instead. We set it to false by default since the intention from D155310 is to use libm by default. Then we use a logical `&&` with use approx so that we select libm when BOTH mlir complex and use approx are disabled. Reviewed By: vzakhari Differential Revision: https://reviews.llvm.org/D155737 --- flang/lib/Optimizer/Builder/IntrinsicCall.cpp | 25 ++++++++++++++++--------- flang/test/Lower/Intrinsics/abs.f90 | 4 ++-- flang/test/Lower/Intrinsics/exp.f90 | 12 +++++++----- flang/test/Lower/Intrinsics/log.f90 | 12 +++++++----- flang/test/Lower/power-operator.f90 | 4 ++-- flang/test/Lower/sqrt.f90 | 4 ++-- 6 files changed, 36 insertions(+), 25 deletions(-) diff --git a/flang/lib/Optimizer/Builder/IntrinsicCall.cpp b/flang/lib/Optimizer/Builder/IntrinsicCall.cpp index cb6bc26..3d2ae08 100644 --- a/flang/lib/Optimizer/Builder/IntrinsicCall.cpp +++ b/flang/lib/Optimizer/Builder/IntrinsicCall.cpp @@ -572,10 +572,10 @@ llvm::cl::opt mathRuntimeVersion( llvm::cl::init(fastVersion)); static llvm::cl::opt - disableMlirComplex("disable-mlir-complex", - llvm::cl::desc("Use libm instead of the MLIR complex " - "dialect to lower complex operations"), - llvm::cl::init(false)); + forceMlirComplex("force-mlir-complex", + llvm::cl::desc("Force using MLIR complex operations " + "instead of libm complex operations"), + llvm::cl::init(false)); mlir::Value genLibCall(fir::FirOpBuilder &builder, mlir::Location loc, llvm::StringRef libFuncName, @@ -734,12 +734,19 @@ mlir::Value genComplexMathOp(fir::FirOpBuilder &builder, mlir::Location loc, mlir::FunctionType mathLibFuncType, llvm::ArrayRef args) { mlir::Value result; - bool hasApproxFunc = mlir::arith::bitEnumContainsAny( + bool canUseApprox = mlir::arith::bitEnumContainsAny( builder.getFastMathFlags(), mlir::arith::FastMathFlags::afn); - if ((disableMlirComplex || !hasApproxFunc) && !mathLibFuncName.empty()) { - result = genLibCall(builder, loc, mathLibFuncName, mathLibFuncType, args); - LLVM_DEBUG(result.dump(); llvm::dbgs() << "\n"); - return result; + + // If we have libm functions, we can attempt to generate the more precise + // version of the complex math operation. + if (!mathLibFuncName.empty()) { + // If we enabled MLIR complex or can use approximate operations, we should + // NOT use libm. + if (!forceMlirComplex && !canUseApprox) { + result = genLibCall(builder, loc, mathLibFuncName, mathLibFuncType, args); + LLVM_DEBUG(result.dump(); llvm::dbgs() << "\n"); + return result; + } } LLVM_DEBUG(llvm::dbgs() << "Generating '" << mathLibFuncName diff --git a/flang/test/Lower/Intrinsics/abs.f90 b/flang/test/Lower/Intrinsics/abs.f90 index 896a146..d2288a1 100644 --- a/flang/test/Lower/Intrinsics/abs.f90 +++ b/flang/test/Lower/Intrinsics/abs.f90 @@ -1,9 +1,9 @@ ! RUN: bbc -emit-fir %s -o - | FileCheck %s --check-prefixes="CHECK,CMPLX,CMPLX-PRECISE" ! RUN: bbc -emit-fir --math-runtime=precise %s -o - | FileCheck %s --check-prefixes="CMPLX,CMPLX-PRECISE" -! RUN: bbc --disable-mlir-complex -emit-fir %s -o - | FileCheck %s --check-prefixes="CMPLX,CMPLX-PRECISE" +! RUN: bbc --force-mlir-complex -emit-fir %s -o - | FileCheck %s --check-prefixes="CMPLX,CMPLX-FAST" ! RUN: %flang_fc1 -emit-fir %s -o - | FileCheck %s --check-prefixes="CHECK,CMPLX,CMPLX-PRECISE" ! RUN: %flang_fc1 -emit-fir -mllvm --math-runtime=precise %s -o - | FileCheck %s --check-prefixes="CMPLX,CMPLX-PRECISE" -! RUN: %flang_fc1 -emit-fir -mllvm --disable-mlir-complex %s -o - | FileCheck %s --check-prefixes="CMPLX,CMPLX-PRECISE" +! RUN: %flang_fc1 -emit-fir -mllvm --force-mlir-complex %s -o - | FileCheck %s --check-prefixes="CMPLX,CMPLX-FAST" ! RUN: %flang_fc1 -fapprox-func -emit-fir %s -o - | FileCheck %s --check-prefixes="CMPLX,CMPLX-FAST" ! Test abs intrinsic for various types (int, float, complex) diff --git a/flang/test/Lower/Intrinsics/exp.f90 b/flang/test/Lower/Intrinsics/exp.f90 index 8188ba3..f128e54 100644 --- a/flang/test/Lower/Intrinsics/exp.f90 +++ b/flang/test/Lower/Intrinsics/exp.f90 @@ -1,10 +1,10 @@ ! RUN: bbc -emit-fir -outline-intrinsics %s -o - | FileCheck %s --check-prefixes="CHECK,CMPLX,CMPLX-PRECISE" ! RUN: bbc -emit-fir --math-runtime=precise -outline-intrinsics %s -o - | FileCheck %s --check-prefixes="CMPLX,CMPLX-PRECISE" -! RUN: bbc -emit-fir --disable-mlir-complex -outline-intrinsics %s -o - | FileCheck %s --check-prefixes="CMPLX,CMPLX-PRECISE" +! RUN: bbc -emit-fir --force-mlir-complex -outline-intrinsics %s -o - | FileCheck %s --check-prefixes="CMPLX,CMPLX-FAST,CMPLX-MLIR" ! RUN: %flang_fc1 -emit-fir -mllvm -outline-intrinsics %s -o - | FileCheck %s --check-prefixes="CHECK,CMPLX,CMPLX-PRECISE" -! RUN: %flang_fc1 -fapprox-func -emit-fir -mllvm -outline-intrinsics %s -o - | FileCheck %s --check-prefixes="CMPLX,CMPLX-FAST" +! RUN: %flang_fc1 -fapprox-func -emit-fir -mllvm -outline-intrinsics %s -o - | FileCheck %s --check-prefixes="CMPLX,CMPLX-FAST,CMPLX-APPROX" ! RUN: %flang_fc1 -emit-fir -mllvm -outline-intrinsics -mllvm --math-runtime=precise %s -o - | FileCheck %s --check-prefixes="CMPLX,CMPLX-PRECISE" -! RUN: %flang_fc1 -emit-fir -mllvm -outline-intrinsics -mllvm --disable-mlir-complex %s -o - | FileCheck %s --check-prefixes="CMPLX,CMPLX-PRECISE" +! RUN: %flang_fc1 -emit-fir -mllvm -outline-intrinsics -mllvm --force-mlir-complex %s -o - | FileCheck %s --check-prefixes="CMPLX,CMPLX-FAST,CMPLX-MLIR" ! CHECK-LABEL: exp_testr ! CHECK-SAME: (%[[AREF:.*]]: !fir.ref {{.*}}, %[[BREF:.*]]: !fir.ref {{.*}}) @@ -56,8 +56,9 @@ end subroutine ! CHECK: %[[RESULT64_OUTLINE:.*]] = math.exp %[[ARG64_OUTLINE]] fastmath : f64 ! CHECK: return %[[RESULT64_OUTLINE]] : f64 -! CMPLX-FAST-LABEL: private @fir.exp.contract_afn.z4.z4 +! CMPLX-APPROX-LABEL: private @fir.exp.contract_afn.z4.z4 ! CMPLX-PRECISE-LABEL: private @fir.exp.contract.z4.z4 +! CMPLX-MLIR-LABEL: private @fir.exp.contract.z4.z4 ! CMPLX-SAME: (%[[ARG32_OUTLINE:.*]]: !fir.complex<4>) -> !fir.complex<4> ! CMPLX-FAST: %[[C:.*]] = fir.convert %[[ARG32_OUTLINE]] : (!fir.complex<4>) -> complex ! CMPLX-FAST: %[[E:.*]] = complex.exp %[[C]] : complex @@ -65,8 +66,9 @@ end subroutine ! CMPLX-PRECISE: %[[RESULT32_OUTLINE:.*]] = fir.call @cexpf(%[[ARG32_OUTLINE]]) fastmath : (!fir.complex<4>) -> !fir.complex<4> ! CMPLX: return %[[RESULT32_OUTLINE]] : !fir.complex<4> -! CMPLX-FAST-LABEL: private @fir.exp.contract_afn.z8.z8 +! CMPLX-APPROX-LABEL: private @fir.exp.contract_afn.z8.z8 ! CMPLX-PRECISE-LABEL: private @fir.exp.contract.z8.z8 +! CMPLX-MLIR-LABEL: private @fir.exp.contract.z8.z8 ! CMPLX-SAME: (%[[ARG64_OUTLINE:.*]]: !fir.complex<8>) -> !fir.complex<8> ! CMPLX-FAST: %[[C:.*]] = fir.convert %[[ARG64_OUTLINE]] : (!fir.complex<8>) -> complex ! CMPLX-FAST: %[[E:.*]] = complex.exp %[[C]] : complex diff --git a/flang/test/Lower/Intrinsics/log.f90 b/flang/test/Lower/Intrinsics/log.f90 index e39972d..49be4d9 100644 --- a/flang/test/Lower/Intrinsics/log.f90 +++ b/flang/test/Lower/Intrinsics/log.f90 @@ -1,10 +1,10 @@ ! RUN: bbc -emit-fir -outline-intrinsics %s -o - | FileCheck %s --check-prefixes="CHECK,CMPLX,CMPLX-PRECISE" ! RUN: bbc -emit-fir --math-runtime=precise -outline-intrinsics %s -o - | FileCheck %s --check-prefixes="CMPLX,CMPLX-PRECISE" -! RUN: bbc -emit-fir --disable-mlir-complex -outline-intrinsics %s -o - | FileCheck %s --check-prefixes="CMPLX,CMPLX-PRECISE" +! RUN: bbc -emit-fir --force-mlir-complex -outline-intrinsics %s -o - | FileCheck %s --check-prefixes="CMPLX,CMPLX-FAST,CMPLX-MLIR" ! RUN: %flang_fc1 -emit-fir -mllvm -outline-intrinsics %s -o - | FileCheck %s --check-prefixes="CHECK,CMPLX,CMPLX-PRECISE" ! RUN: %flang_fc1 -emit-fir -mllvm -outline-intrinsics -mllvm --math-runtime=precise %s -o - | FileCheck %s --check-prefixes="CMPLX,CMPLX-PRECISE" -! RUN: %flang_fc1 -emit-fir -mllvm -outline-intrinsics -mllvm --disable-mlir-complex %s -o - | FileCheck %s --check-prefixes="CMPLX,CMPLX-PRECISE" -! RUN: %flang_fc1 -fapprox-func -emit-fir -mllvm -outline-intrinsics %s -o - | FileCheck %s --check-prefixes="CMPLX,CMPLX-FAST" +! RUN: %flang_fc1 -emit-fir -mllvm -outline-intrinsics -mllvm --force-mlir-complex %s -o - | FileCheck %s --check-prefixes="CMPLX,CMPLX-FAST,CMPLX-MLIR" +! RUN: %flang_fc1 -fapprox-func -emit-fir -mllvm -outline-intrinsics %s -o - | FileCheck %s --check-prefixes="CMPLX,CMPLX-FAST,CMPLX-APPROX" ! CHECK-LABEL: log_testr ! CHECK-SAME: (%[[AREF:.*]]: !fir.ref {{.*}}, %[[BREF:.*]]: !fir.ref {{.*}}) @@ -76,8 +76,9 @@ end subroutine ! CHECK: %[[RESULT64_OUTLINE:.*]] = math.log %[[ARG64_OUTLINE]] fastmath : f64 ! CHECK: return %[[RESULT64_OUTLINE]] : f64 -! CMPLX-FAST-LABEL: private @fir.log.contract_afn.z4.z4 +! CMPLX-APPROX-LABEL: private @fir.log.contract_afn.z4.z4 ! CMPLX-PRECISE-LABEL: private @fir.log.contract.z4.z4 +! CMPLX-MLIR-LABEL: private @fir.log.contract.z4.z4 ! CMPLX-SAME: (%[[ARG32_OUTLINE:.*]]: !fir.complex<4>) -> !fir.complex<4> ! CMPLX-FAST: %[[C:.*]] = fir.convert %[[ARG32_OUTLINE]] : (!fir.complex<4>) -> complex ! CMPLX-FAST: %[[E:.*]] = complex.log %[[C]] : complex @@ -85,8 +86,9 @@ end subroutine ! CMPLX-PRECISE: %[[RESULT32_OUTLINE:.*]] = fir.call @clogf(%[[ARG32_OUTLINE]]) fastmath : (!fir.complex<4>) -> !fir.complex<4> ! CMPLX: return %[[RESULT32_OUTLINE]] : !fir.complex<4> -! CMPLX-FAST-LABEL: private @fir.log.contract_afn.z8.z8 +! CMPLX-APPROX-LABEL: private @fir.log.contract_afn.z8.z8 ! CMPLX-PRECISE-LABEL: private @fir.log.contract.z8.z8 +! CMPLX-MLIR-LABEL: private @fir.log.contract.z8.z8 ! CMPLX-SAME: (%[[ARG64_OUTLINE:.*]]: !fir.complex<8>) -> !fir.complex<8> ! CMPLX-FAST: %[[C:.*]] = fir.convert %[[ARG64_OUTLINE]] : (!fir.complex<8>) -> complex ! CMPLX-FAST: %[[E:.*]] = complex.log %[[C]] : complex diff --git a/flang/test/Lower/power-operator.f90 b/flang/test/Lower/power-operator.f90 index 7b80bf4..7436e03 100644 --- a/flang/test/Lower/power-operator.f90 +++ b/flang/test/Lower/power-operator.f90 @@ -1,10 +1,10 @@ ! RUN: bbc -emit-fir %s -o - | FileCheck %s --check-prefixes="CHECK,PRECISE" ! RUN: bbc --math-runtime=precise -emit-fir %s -o - | FileCheck %s --check-prefixes="PRECISE" -! RUN: bbc --disable-mlir-complex -emit-fir %s -o - | FileCheck %s --check-prefixes="PRECISE" +! RUN: bbc --force-mlir-complex -emit-fir %s -o - | FileCheck %s --check-prefixes="FAST" ! RUN: %flang_fc1 -emit-fir %s -o - | FileCheck %s --check-prefixes="CHECK,PRECISE" ! RUN: %flang_fc1 -fapprox-func -emit-fir %s -o - | FileCheck %s --check-prefixes="CHECK,FAST" ! RUN: %flang_fc1 -emit-fir -mllvm --math-runtime=precise %s -o - | FileCheck %s --check-prefixes="PRECISE" -! RUN: %flang_fc1 -emit-fir -mllvm --disable-mlir-complex %s -o - | FileCheck %s --check-prefixes="PRECISE" +! RUN: %flang_fc1 -emit-fir -mllvm --force-mlir-complex %s -o - | FileCheck %s --check-prefixes="FAST" ! Test power operation lowering diff --git a/flang/test/Lower/sqrt.f90 b/flang/test/Lower/sqrt.f90 index 91cdb91..458a83b 100644 --- a/flang/test/Lower/sqrt.f90 +++ b/flang/test/Lower/sqrt.f90 @@ -1,10 +1,10 @@ ! RUN: bbc -emit-fir -outline-intrinsics %s -o - | FileCheck %s --check-prefixes="CHECK,CMPLX-PRECISE" ! RUN: bbc --math-runtime=precise -emit-fir -outline-intrinsics %s -o - | FileCheck %s --check-prefixes="CMPLX-PRECISE" -! RUN: bbc --disable-mlir-complex -emit-fir -outline-intrinsics %s -o - | FileCheck %s --check-prefixes="CMPLX-PRECISE" +! RUN: bbc --force-mlir-complex -emit-fir -outline-intrinsics %s -o - | FileCheck %s --check-prefixes="CMPLX-FAST" ! RUN: %flang_fc1 -emit-fir -mllvm -outline-intrinsics %s -o - | FileCheck %s --check-prefixes="CHECK,CMPLX-PRECISE" ! RUN: %flang_fc1 -fapprox-func -emit-fir -mllvm -outline-intrinsics %s -o - | FileCheck %s --check-prefixes="CMPLX-FAST" ! RUN: %flang_fc1 -emit-fir -mllvm --math-runtime=precise -mllvm -outline-intrinsics %s -o - | FileCheck %s --check-prefixes="CMPLX-PRECISE" -! RUN: %flang_fc1 -emit-fir -mllvm --disable-mlir-complex -mllvm -outline-intrinsics %s -o - | FileCheck %s --check-prefixes="CMPLX-PRECISE" +! RUN: %flang_fc1 -emit-fir -mllvm --force-mlir-complex -mllvm -outline-intrinsics %s -o - | FileCheck %s --check-prefixes="CMPLX-FAST" ! CHECK-LABEL: sqrt_testr subroutine sqrt_testr(a, b) -- 2.7.4