[flang] Use libm functions for complex operations by default

[DavidTruby]

Summary

This patch changes the default lowering for complex operations to use
the more accurate libm operations as opposed to the mlir complex
operations. This is necessary due to precision issues in the mlir
complex dialect that cause failures in e.g. the LAPACK tests.

The mlir complex dialect lowering will still be used when
-fapprox-func is set (and by extension -ffast-math and -Ofast)

[kiranchandramohan]

LG.

Could you announce in https://discourse.llvm.org/t/rfc-proposal-for-complex-math-intrinsic-lowering-through-the-mlir-complex-dialect/65420 about this change when you submit? Please specify that complex intrinsic lowering now follows -fapprox-func and disableMlirComplex. It will not follow math-runtime option. Also, mark this as fixing https://github.com/llvm/llvm-project/issues/58799. Also, include a comment in issue 58799.

[vzakhari]

LGTM except for one minor issue. Thank you!

flang/lib/Optimizer/Builder/IntrinsicCall.cpp

51

This looks out of style :)

flang/lib/Optimizer/Builder/IntrinsicCall.cpp

 #include "mlir/Dialect/Complex/IR/Complex.h"
 #include "mlir/Dialect/LLVMIR/LLVMDialect.h"
 #include "mlir/Dialect/Math/IR/Math.h"
 #include "mlir/Dialect/Vector/IR/VectorOps.h"
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Debug.h"
 #include "llvm/Support/MathExtras.h"
 #include "llvm/Support/raw_ostream.h"
 #include <optional>
 
 #define DEBUG_TYPE "flang-lower-intrinsic"
 
 /// This file implements lowering of Fortran intrinsic procedures and Fortran
 /// intrinsic module procedures.  A call may be inlined with a mix of FIR and
 /// MLIR operations, or as a call to a runtime function or LLVM intrinsic.
 
 /// Lowering of intrinsic procedure calls is based on a map that associates

 }
 
 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;
-  if (disableMlirComplex ||
-      (mathRuntimeVersion == preciseVersion && !mathLibFuncName.empty())) {
+  bool hasApproxFunc = 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;
   }
 
   LLVM_DEBUG(llvm::dbgs() << "Generating '" << mathLibFuncName
                           << "' operation with type ";
              mathLibFuncType.dump(); llvm::dbgs() << "\n");
searchMathOperation(fir::FirOpBuilder &builder, llvm::StringRef name,
 
   // Search ppcMathOps only if targetting PowerPC arch
   if (fir::getTargetTriple(mod).isPPC() && range.first == range.second) {
     range = checkPPCMathOperationsRange(name);
   }
   for (auto iter = range.first; iter != range.second && iter; ++iter) {
     const auto &impl = *iter;
     auto implType = impl.typeGenerator(builder.getContext(), builder);
-    if (funcType == implType)
+    if (funcType == implType) {
       return &impl; // exact match
+    }
 
     FunctionDistance distance(funcType, implType);
     if (distance.isSmallerThan(bestMatchDistance)) {
       *bestNearMatch = &impl;
       bestMatchDistance = std::move(distance);
     }
   }
   return nullptr;

flang/test/Lower/HLFIR/binary-ops.f90

subroutine complex_power(x, y, z)
   complex :: x, y, z
   x = y**z
 end subroutine
 ! CHECK-LABEL: func.func @_QPcomplex_power(
 ! CHECK:  %[[VAL_4:.*]]:2 = hlfir.declare %{{.*}}y"} : (!fir.ref<!fir.complex<4>>) -> (!fir.ref<!fir.complex<4>>, !fir.ref<!fir.complex<4>>)
 ! CHECK:  %[[VAL_5:.*]]:2 = hlfir.declare %{{.*}}z"} : (!fir.ref<!fir.complex<4>>) -> (!fir.ref<!fir.complex<4>>, !fir.ref<!fir.complex<4>>)
 ! CHECK:  %[[VAL_6:.*]] = fir.load %[[VAL_4]]#0 : !fir.ref<!fir.complex<4>>
 ! CHECK:  %[[VAL_7:.*]] = fir.load %[[VAL_5]]#0 : !fir.ref<!fir.complex<4>>
-! CHECK:  %[[VAL_8:.*]] = fir.convert %[[VAL_6]] : (!fir.complex<4>) -> complex<f32>
-! CHECK:  %[[VAL_9:.*]] = fir.convert %[[VAL_7]] : (!fir.complex<4>) -> complex<f32>
-! CHECK:  %[[VAL_10:.*]] = complex.pow %[[VAL_8]], %[[VAL_9]] : complex<f32>
-! CHECK:  %[[VAL_11:.*]] = fir.convert %[[VAL_10]] : (complex<f32>) -> !fir.complex<4>
+! CHECK:  %[[VAL_8:.*]] = fir.call @cpowf(%[[VAL_6]], %[[VAL_7]]) fastmath<contract> : (!fir.complex<4>, !fir.complex<4>) -> !fir.complex<4>
+
 
 subroutine real_to_int_power(x, y, z)
   real :: x, y
   integer :: z
   x = y**z
 end subroutine
 ! CHECK-LABEL: func.func @_QPreal_to_int_power(
 ! CHECK:  %[[VAL_4:.*]]:2 = hlfir.declare %{{.*}}y"} : (!fir.ref<f32>) -> (!fir.ref<f32>, !fir.ref<f32>)

flang/test/Lower/Intrinsics/abs.f90

-! RUN: bbc -emit-fir %s -o - | FileCheck %s --check-prefixes="CHECK,CMPLX,CMPLX-FAST"
+! 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: %flang_fc1 -emit-fir %s -o - | FileCheck %s --check-prefixes="CHECK,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 -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>
 ! CHECK:  %[[VAL_3:.*]] = arith.constant 31 : i32

flang/test/Lower/Intrinsics/exp.f90

-! RUN: bbc -emit-fir -outline-intrinsics %s -o - | FileCheck %s --check-prefixes="CHECK,CMPLX,CMPLX-FAST"
+! 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: %flang_fc1 -emit-fir -mllvm -outline-intrinsics %s -o - | FileCheck %s --check-prefixes="CHECK,CMPLX,CMPLX-FAST"
+! 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 -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"
 
 ! 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: %[[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-LABEL: private @fir.exp.contract.z4.z4
+! CMPLX-FAST-LABEL: private @fir.exp.contract_afn.z4.z4
+! CMPLX-PRECISE-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-LABEL: private @fir.exp.contract.z8.z8
+! CMPLX-FAST-LABEL: private @fir.exp.contract_afn.z8.z8
+! CMPLX-PRECISE-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-FAST"
+! 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: %flang_fc1 -emit-fir -mllvm -outline-intrinsics %s -o - | FileCheck %s --check-prefixes="CHECK,CMPLX,CMPLX-FAST"
+! 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"
 
 ! 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-LABEL: private @fir.log.contract.z4.z4
+! CMPLX-FAST-LABEL: private @fir.log.contract_afn.z4.z4
+! CMPLX-PRECISE-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-LABEL: private @fir.log.contract.z8.z8
+! CMPLX-FAST-LABEL: private @fir.log.contract_afn.z8.z8
+! CMPLX-PRECISE-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/math-lowering.f90

 ! FAST: {{%[A-Za-z0-9._]+}} = math.absf {{%[A-Za-z0-9._]+}} {{.*}}: f128
 ! RELAXED: {{%[A-Za-z0-9._]+}} = math.absf {{%[A-Za-z0-9._]+}} {{.*}}: f128
 ! PRECISE: {{%[A-Za-z0-9._]+}} = fir.call @llvm.fabs.f128({{%[A-Za-z0-9._]+}}) {{.*}}: (f128) -> f128
 
 function test_complex4(c)
   complex(4) :: c, test_complex4
   test_complex4 = abs(c)
 end function
-
 ! ALL-LABEL: @_QPtest_complex4
-! FAST: {{%[A-Za-z0-9._]+}} = complex.abs {{%[A-Za-z0-9._]+}} : complex<f32>
-! RELAXED: {{%[A-Za-z0-9._]+}} = complex.abs {{%[A-Za-z0-9._]+}} : complex<f32>
-! PRECISE: {{%[A-Za-z0-9._]+}} = fir.call @cabsf({{%[A-Za-z0-9._]+}}) {{.*}}: (!fir.complex<4>) -> f32
+! ALL: {{%[A-Za-z0-9._]+}} = fir.call @cabsf({{%[A-Za-z0-9._]+}}) {{.*}}: (!fir.complex<4>) -> f32
 
 function test_complex8(c)
   complex(8) :: c, test_complex8
   test_complex8 = abs(c)
 end function
-
 ! ALL-LABEL: @_QPtest_complex8
-! FAST: {{%[A-Za-z0-9._]+}} = complex.abs {{%[A-Za-z0-9._]+}} : complex<f64>
-! RELAXED: {{%[A-Za-z0-9._]+}} = complex.abs {{%[A-Za-z0-9._]+}} : complex<f64>
-! PRECISE: {{%[A-Za-z0-9._]+}} = fir.call @cabs({{%[A-Za-z0-9._]+}}) {{.*}}: (!fir.complex<8>) -> f64
+! ALL: {{%[A-Za-z0-9._]+}} = fir.call @cabs({{%[A-Za-z0-9._]+}}) {{.*}}: (!fir.complex<8>) -> f64
 
 ! PRECISE-DAG: func.func private @fabsf(f32) -> f32 attributes {fir.bindc_name = "fabsf", fir.runtime}
 ! PRECISE-DAG: func.func private @fabs(f64) -> f64 attributes {fir.bindc_name = "fabs", fir.runtime}
 ! PRECISE-DAG: func.func private @llvm.fabs.f128(f128) -> f128 attributes {fir.bindc_name = "llvm.fabs.f128", fir.runtime}
 ! PRECISE-DAG: func.func private @cabsf(!fir.complex<4>) -> f32 attributes {fir.bindc_name = "cabsf", fir.runtime}
 ! PRECISE-DAG: func.func private @cabs(!fir.complex<8>) -> f64 attributes {fir.bindc_name = "cabs", fir.runtime}
 
 //--- aint.f90

flang/test/Lower/power-operator.f90

-! RUN: bbc -emit-fir %s -o - | FileCheck %s --check-prefixes="CHECK,FAST"
+! 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: %flang_fc1 -emit-fir %s -o - | FileCheck %s --check-prefixes="CHECK,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"
 
 ! Test power operation lowering
 
 ! CHECK-LABEL: pow_r4_i4
 subroutine pow_r4_i4(x, y, z)
   real :: x, z

flang/test/Lower/sqrt.f90

-! RUN: bbc -emit-fir -outline-intrinsics %s -o - | FileCheck %s --check-prefixes="CHECK,CMPLX-FAST"
+! 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: %flang_fc1 -emit-fir -mllvm -outline-intrinsics %s -o - | FileCheck %s --check-prefixes="CHECK,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"
 
 ! CHECK-LABEL: sqrt_testr
 subroutine sqrt_testr(a, b)
   real :: a, b
 ! CHECK: fir.call @fir.sqrt.contract.f32.f32
   b = sqrt(a)

flang/test/Lower/trigonometric-intrinsics.f90

-! RUN: bbc -emit-fir -outline-intrinsics %s -o - | FileCheck %s --check-prefixes="CHECK,CMPLX-FAST"
+! 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: %flang_fc1 -emit-fir -mllvm -outline-intrinsics %s -o - | FileCheck %s
+! RUN: %flang_fc1 -fapprox-func -emit-fir -mllvm -outline-intrinsics %s -o - | FileCheck %s --check-prefixes="CMPLX-FAST"
 
 ! CHECK-LABEL: tan_testr
 subroutine tan_testr(a, b)
   real :: a, b
 ! CHECK: fir.call @fir.tan.contract.f32.f32
   b = tan(a)
 end subroutine