[flang] Fix complex libm use logic problems

[razvanlupusoru]

Summary

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.

[razvanlupusoru]

flang/lib/Optimizer/Builder/IntrinsicCall.cpp

577

Extra word "lower". Will remove.

[razvanlupusoru]

Removed extra word in command line option description.

[razvanlupusoru]

I am uploading the flang lit tests changes in a bit so we pass check-flang.

[razvanlupusoru]

Fix lit tests

[vzakhari]

Thank you, Razvan! Looks good to me.

[kiranchandramohan]

Thanks @razvanlupusoru for the fix.

flang/lib/Optimizer/Builder/IntrinsicCall.cpp

llvm::cl::opt<MathRuntimeVersion> mathRuntimeVersion(
     "math-runtime", llvm::cl::desc("Select math operations' runtime behavior:"),
     llvm::cl::values(
         clEnumValN(fastVersion, "fast", "use fast runtime behavior"),
         clEnumValN(relaxedVersion, "relaxed", "use relaxed runtime behavior"),
         clEnumValN(preciseVersion, "precise", "use precise runtime behavior")),
     llvm::cl::init(fastVersion));
 
 static llvm::cl::opt<bool>
-    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"),
 
 mlir::Value genLibCall(fir::FirOpBuilder &builder, mlir::Location loc,
                        llvm::StringRef libFuncName,
                        mlir::FunctionType libFuncType,
                        llvm::ArrayRef<mlir::Value> args) {
   LLVM_DEBUG(llvm::dbgs() << "Generating '" << libFuncName
                           << "' call with type ";
              libFuncType.dump(); llvm::dbgs() << "\n");

 }
 
 template <typename T>
 mlir::Value genComplexMathOp(fir::FirOpBuilder &builder, mlir::Location loc,
                              llvm::StringRef mathLibFuncName,
                              mlir::FunctionType mathLibFuncType,
                              llvm::ArrayRef<mlir::Value> 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()) {
+
+  // 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
                           << "' operation with type ";
              mathLibFuncType.dump(); llvm::dbgs() << "\n");
   auto type = mathLibFuncType.getInput(0).cast<fir::ComplexType>();
   auto kind = type.getElementType().cast<fir::RealType>().getFKind();
   auto realTy = builder.getRealType(kind);
   auto mComplexTy = mlir::ComplexType::get(realTy);

flang/test/Lower/Intrinsics/abs.f90

 ! 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)
 
 ! CHECK-LABEL: func @_QPabs_testi
 ! CHECK-SAME: %[[VAL_0:.*]]: !fir.ref<i32>{{.*}}, %[[VAL_1:.*]]: !fir.ref<i32>
 subroutine abs_testi(a, b)
 ! CHECK:  %[[VAL_2:.*]] = fir.load %[[VAL_0]] : !fir.ref<i32>

flang/test/Lower/Intrinsics/exp.f90

 ! 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<f32> {{.*}}, %[[BREF:.*]]: !fir.ref<f32> {{.*}})
 subroutine exp_testr(a, b)
   real :: a, b
 ! CHECK:  %[[A:.*]] = fir.load %[[AREF:.*]] : !fir.ref<f32>
 ! CHECK:  %[[RES:.*]] = fir.call @fir.exp.contract.f32.f32(%[[A]]) {{.*}}: (f32) -> f32
 ! CHECK:  fir.store %[[RES]] to %[[BREF]] : !fir.ref<f32>

 ! CHECK: %[[RESULT32_OUTLINE:.*]] = math.exp %[[ARG32_OUTLINE]] fastmath<contract> : f32
 ! CHECK: return %[[RESULT32_OUTLINE]] : f32
 
 ! CHECK-LABEL: private @fir.exp.contract.f64.f64
 ! CHECK-SAME: (%[[ARG64_OUTLINE:.*]]: f64) -> f64
 ! CHECK: %[[RESULT64_OUTLINE:.*]] = math.exp %[[ARG64_OUTLINE]] fastmath<contract> : 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<f32>
 ! CMPLX-FAST: %[[E:.*]] = complex.exp %[[C]] : complex<f32>
 ! CMPLX-FAST: %[[RESULT32_OUTLINE:.*]] = fir.convert %[[E]] : (complex<f32>) -> !fir.complex<4>
 ! CMPLX-PRECISE: %[[RESULT32_OUTLINE:.*]] = fir.call @cexpf(%[[ARG32_OUTLINE]]) fastmath<contract> : (!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<f64>
 ! CMPLX-FAST: %[[E:.*]] = complex.exp %[[C]] : complex<f64>
 ! CMPLX-FAST: %[[RESULT64_OUTLINE:.*]] = fir.convert %[[E]] : (complex<f64>) -> !fir.complex<8>
 ! CMPLX-PRECISE: %[[RESULT64_OUTLINE:.*]] = fir.call @cexp(%[[ARG64_OUTLINE]]) fastmath<contract> : (!fir.complex<8>) -> !fir.complex<8>
 ! CMPLX: return %[[RESULT64_OUTLINE]] : !fir.complex<8>

flang/test/Lower/Intrinsics/log.f90

 ! 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<f32> {{.*}}, %[[BREF:.*]]: !fir.ref<f32> {{.*}})
 subroutine log_testr(a, b)
   real :: a, b
 ! CHECK:  %[[A:.*]] = fir.load %[[AREF:.*]] : !fir.ref<f32>
 ! CHECK:  %[[RES:.*]] = fir.call @fir.log.contract.f32.f32(%[[A]]) {{.*}}: (f32) -> f32
 ! CHECK:  fir.store %[[RES]] to %[[BREF]] : !fir.ref<f32>

 ! CHECK: %[[RESULT32_OUTLINE:.*]] = math.log %[[ARG32_OUTLINE]] fastmath<contract> : f32
 ! CHECK: return %[[RESULT32_OUTLINE]] : f32
 
 ! CHECK-LABEL: private @fir.log.contract.f64.f64
 ! CHECK-SAME: (%[[ARG64_OUTLINE:.*]]: f64) -> f64
 ! CHECK: %[[RESULT64_OUTLINE:.*]] = math.log %[[ARG64_OUTLINE]] fastmath<contract> : 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<f32>
 ! CMPLX-FAST: %[[E:.*]] = complex.log %[[C]] : complex<f32>
 ! CMPLX-FAST: %[[RESULT32_OUTLINE:.*]] = fir.convert %[[E]] : (complex<f32>) -> !fir.complex<4>
 ! CMPLX-PRECISE: %[[RESULT32_OUTLINE:.*]] = fir.call @clogf(%[[ARG32_OUTLINE]]) fastmath<contract> : (!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<f64>
 ! CMPLX-FAST: %[[E:.*]] = complex.log %[[C]] : complex<f64>
 ! CMPLX-FAST: %[[RESULT64_OUTLINE:.*]] = fir.convert %[[E]] : (complex<f64>) -> !fir.complex<8>
 ! CMPLX-PRECISE: %[[RESULT64_OUTLINE:.*]] = fir.call @clog(%[[ARG64_OUTLINE]]) fastmath<contract> : (!fir.complex<8>) -> !fir.complex<8>
 ! CMPLX: return %[[RESULT64_OUTLINE]] : !fir.complex<8>
 
 ! CHECK-LABEL: private @fir.log10.contract.f32.f32
 ! CHECK-SAME: (%[[ARG32_OUTLINE:.*]]: f32) -> f32
 ! CHECK: %[[RESULT32_OUTLINE:.*]] = math.log10 %[[ARG32_OUTLINE]] fastmath<contract> : f32
 ! CHECK: return %[[RESULT32_OUTLINE]] : f32
 
 ! CHECK-LABEL: private @fir.log10.contract.f64.f64
 ! CHECK-SAME: (%[[ARG64_OUTLINE:.*]]: f64) -> f64
 ! CHECK: %[[RESULT64_OUTLINE:.*]] = math.log10 %[[ARG64_OUTLINE]] fastmath<contract> : f64
 ! CHECK: return %[[RESULT64_OUTLINE]] : f64

flang/test/Lower/power-operator.f90

 ! 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
 
 ! CHECK-LABEL: pow_r4_i4
 subroutine pow_r4_i4(x, y, z)
   real :: x, z
   integer :: y
   z = x ** y

flang/test/Lower/sqrt.f90

 ! 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)
   real :: a, b
 ! CHECK: fir.call @fir.sqrt.contract.f32.f32
   b = sqrt(a)
 end subroutine