Index: flang/lib/Optimizer/Transforms/SimplifyIntrinsics.cpp
===================================================================
--- flang/lib/Optimizer/Transforms/SimplifyIntrinsics.cpp
+++ flang/lib/Optimizer/Transforms/SimplifyIntrinsics.cpp
@@ -578,6 +578,22 @@
           mlir::Location loc = call.getLoc();
           fir::FirOpBuilder builder(op, kindMap);
 
+          // Inherit FastMathFlags from the call operation by configuring
+          // the builder accordingly.
+          std::string fmfString{};
+          auto fmi = mlir::dyn_cast<mlir::arith::ArithFastMathInterface>(*op);
+          if (fmi) {
+            mlir::arith::FastMathFlags flags =
+                fmi.getFastMathFlagsAttr().getValue();
+            if (flags != mlir::arith::FastMathFlags::none) {
+              builder.setFastMathFlags(flags);
+              // Stringize FastMathFlags flags for mangling the generated
+              // function name.
+              fmfString = mlir::arith::stringifyFastMathFlags(flags);
+              std::replace(fmfString.begin(), fmfString.end(), ',', '_');
+            }
+          }
+
           mlir::Type type = call.getResult(0).getType();
           if (!type.isa<mlir::FloatType>() && !type.isa<mlir::IntegerType>())
             return;
@@ -611,9 +627,13 @@
           // of the arguments.
           std::string typedFuncName(funcName);
           llvm::raw_string_ostream nameOS(typedFuncName);
-          nameOS << "_";
+          // We must mangle the generated function name with FastMathFlags
+          // value.
+          if (!fmfString.empty())
+            nameOS << '_' << fmfString;
+          nameOS << '_';
           arg1Type->print(nameOS);
-          nameOS << "_";
+          nameOS << '_';
           arg2Type->print(nameOS);
 
           mlir::func::FuncOp newFunc = getOrCreateFunction(
Index: flang/test/Transforms/simplifyintrinsics.fir
===================================================================
--- flang/test/Transforms/simplifyintrinsics.fir
+++ flang/test/Transforms/simplifyintrinsics.fir
@@ -998,3 +998,42 @@
 // CHECK-NOT: call{{.*}}_FortranASumInteger8(
 // CHECK: call @_FortranASumInteger8x2_simplified(
 // CHECK-NOT: call{{.*}}_FortranASumInteger8(
+
+// -----
+
+func.func @dot_f32_contract_reassoc(%arg0: !fir.box<!fir.array<?xf32>> {fir.bindc_name = "a"}, %arg1: !fir.box<!fir.array<?xf32>> {fir.bindc_name = "b"}) -> f32 {
+  %0 = fir.alloca f32 {bindc_name = "dot", uniq_name = "_QFdotEdot"}
+  %1 = fir.address_of(@_QQcl.2E2F646F742E66393000) : !fir.ref<!fir.char<1,10>>
+  %c3_i32 = arith.constant 3 : i32
+  %2 = fir.convert %arg0 : (!fir.box<!fir.array<?xf32>>) -> !fir.box<none>
+  %3 = fir.convert %arg1 : (!fir.box<!fir.array<?xf32>>) -> !fir.box<none>
+  %4 = fir.convert %1 : (!fir.ref<!fir.char<1,10>>) -> !fir.ref<i8>
+  %5 = fir.call @_FortranADotProductReal4(%2, %3, %4, %c3_i32) fastmath<contract,reassoc> : (!fir.box<none>, !fir.box<none>, !fir.ref<i8>, i32) -> f32
+  fir.store %5 to %0 : !fir.ref<f32>
+  %6 = fir.load %0 : !fir.ref<f32>
+  return %6 : f32
+}
+
+func.func @dot_f32_fast(%arg0: !fir.box<!fir.array<?xf32>> {fir.bindc_name = "a"}, %arg1: !fir.box<!fir.array<?xf32>> {fir.bindc_name = "b"}) -> f32 {
+  %0 = fir.alloca f32 {bindc_name = "dot", uniq_name = "_QFdotEdot"}
+  %1 = fir.address_of(@_QQcl.2E2F646F742E66393000) : !fir.ref<!fir.char<1,10>>
+  %c3_i32 = arith.constant 3 : i32
+  %2 = fir.convert %arg0 : (!fir.box<!fir.array<?xf32>>) -> !fir.box<none>
+  %3 = fir.convert %arg1 : (!fir.box<!fir.array<?xf32>>) -> !fir.box<none>
+  %4 = fir.convert %1 : (!fir.ref<!fir.char<1,10>>) -> !fir.ref<i8>
+  %5 = fir.call @_FortranADotProductReal4(%2, %3, %4, %c3_i32) fastmath<fast> : (!fir.box<none>, !fir.box<none>, !fir.ref<i8>, i32) -> f32
+  fir.store %5 to %0 : !fir.ref<f32>
+  %6 = fir.load %0 : !fir.ref<f32>
+  return %6 : f32
+}
+
+// CHECK-LABEL: @dot_f32_contract_reassoc
+// CHECK: fir.call @_FortranADotProductReal4_reassoc_contract_f32_f32_simplified(%2, %3) fastmath<reassoc,contract>
+// CHECK-LABEL: @dot_f32_fast
+// CHECK: fir.call @_FortranADotProductReal4_fast_f32_f32_simplified(%2, %3) fastmath<fast>
+// CHECK-LABEL: func.func private @_FortranADotProductReal4_reassoc_contract_f32_f32_simplified
+// CHECK: arith.mulf %{{.*}}, %{{.*}} fastmath<reassoc,contract> : f32
+// CHECK: arith.addf %{{.*}}, %{{.*}} fastmath<reassoc,contract> : f32
+// CHECK-LABEL: func.func private @_FortranADotProductReal4_fast_f32_f32_simplified
+// CHECK: arith.mulf %{{.*}}, %{{.*}} fastmath<fast> : f32
+// CHECK: arith.addf %{{.*}}, %{{.*}} fastmath<fast> : f32