[fir] Add fir reduction builder

This patch introduces a bunch of builder functions
to create function calls to runtime reduction functions.

This patch is part of the upstreaming effort from fir-dev branch.

Co-authored-by: Jean Perier <jperier@nvidia.com>
Co-authored-by: mleair <leairmark@gmail.com>

Differential Revision: https://reviews.llvm.org/D114460

Reviewed By: awarzynski
diff --git a/flang/include/flang/Optimizer/Builder/Runtime/Reduction.h b/flang/include/flang/Optimizer/Builder/Runtime/Reduction.h
new file mode 100644
index 0000000..5aa8522
--- /dev/null
+++ b/flang/include/flang/Optimizer/Builder/Runtime/Reduction.h
@@ -0,0 +1,155 @@
+//===-- Reduction.h -- generate calls to reduction runtime API --*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// The runtime routines generated in this file are generally storing the result
+// in a descriptor (represented as a `box` in FIR). Some function might
+// have a specialization where the value is returned as a scalar value, e.g.
+// `genAll` is a specialization of `genAllDescriptor`.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef FORTRAN_OPTIMIZER_BUILDER_RUNTIME_REDUCTION_H
+#define FORTRAN_OPTIMIZER_BUILDER_RUNTIME_REDUCTION_H
+
+#include "mlir/Dialect/StandardOps/IR/Ops.h"
+
+namespace fir {
+class ExtendedValue;
+class FirOpBuilder;
+} // namespace fir
+
+namespace fir::runtime {
+
+/// Generate call to `all` runtime routine.
+/// This calls the descriptor based runtime call implementation of the `all`
+/// intrinsic.
+void genAllDescriptor(fir::FirOpBuilder &builder, mlir::Location loc,
+                      mlir::Value resultBox, mlir::Value maskBox,
+                      mlir::Value dim);
+
+/// Generate call to `any` runtime routine.
+/// This calls the descriptor based runtime call implementation of the `any`
+/// intrinsic.
+void genAnyDescriptor(fir::FirOpBuilder &builder, mlir::Location loc,
+                      mlir::Value resultBox, mlir::Value maskBox,
+                      mlir::Value dim);
+
+/// Generate call to `all` runtime routine. This version of `all` is specialized
+/// for rank 1 mask arguments.
+/// This calls the version that returns a scalar logical value.
+mlir::Value genAll(fir::FirOpBuilder &builder, mlir::Location loc,
+                   mlir::Value maskBox, mlir::Value dim);
+
+/// Generate call to `any` runtime routine. This version of `any` is specialized
+/// for rank 1 mask arguments.
+/// This calls the version that returns a scalar logical value.
+mlir::Value genAny(fir::FirOpBuilder &builder, mlir::Location loc,
+                   mlir::Value maskBox, mlir::Value dim);
+
+/// Generate call to `count` runtime routine. This routine is a specialized
+/// version when mask is a rank one array or the dim argument is not
+/// specified by the user.
+mlir::Value genCount(fir::FirOpBuilder &builder, mlir::Location loc,
+                     mlir::Value maskBox, mlir::Value dim);
+
+/// Generate call to general CountDim runtime routine. This routine has a
+/// descriptor result.
+void genCountDim(fir::FirOpBuilder &builder, mlir::Location loc,
+                 mlir::Value resultBox, mlir::Value maskBox, mlir::Value dim,
+                 mlir::Value kind);
+
+/// Generate call to `dot_product` intrinsic runtime routine.
+mlir::Value genDotProduct(fir::FirOpBuilder &builder, mlir::Location loc,
+                          mlir::Value vectorABox, mlir::Value vectorBBox,
+                          mlir::Value resultBox);
+
+/// Generate call to `maxloc` intrinsic runtime routine. This is the version
+/// that does not take a dim argument.
+void genMaxloc(fir::FirOpBuilder &builder, mlir::Location loc,
+               mlir::Value resultBox, mlir::Value arrayBox, mlir::Value maskBox,
+               mlir::Value kind, mlir::Value back);
+
+/// Generate call to `maxloc` intrinsic runtime routine. This is the version
+/// that takes a dim argument.
+void genMaxlocDim(fir::FirOpBuilder &builder, mlir::Location loc,
+                  mlir::Value resultBox, mlir::Value arrayBox, mlir::Value dim,
+                  mlir::Value maskBox, mlir::Value kind, mlir::Value back);
+
+/// Generate call to `minloc` intrinsic runtime routine. This is the version
+/// that does not take a dim argument.
+void genMinloc(fir::FirOpBuilder &builder, mlir::Location loc,
+               mlir::Value resultBox, mlir::Value arrayBox, mlir::Value maskBox,
+               mlir::Value kind, mlir::Value back);
+
+/// Generate call to `minloc` intrinsic runtime routine. This is the version
+/// that takes a dim argument.
+void genMinlocDim(fir::FirOpBuilder &builder, mlir::Location loc,
+                  mlir::Value resultBox, mlir::Value arrayBox, mlir::Value dim,
+                  mlir::Value maskBox, mlir::Value kind, mlir::Value back);
+
+/// Generate call to `maxval` intrinsic runtime routine. This is the version
+/// that does not take a dim argument.
+mlir::Value genMaxval(fir::FirOpBuilder &builder, mlir::Location loc,
+                      mlir::Value arrayBox, mlir::Value maskBox);
+
+/// Generate call to `maxval` intrinsic runtime routine. This is the version
+/// that that handles 1 dimensional character arrays  with no DIM argument.
+void genMaxvalChar(fir::FirOpBuilder &builder, mlir::Location loc,
+                   mlir::Value resultBox, mlir::Value arrayBox,
+                   mlir::Value maskBox);
+
+/// Generate call to `maxval` intrinsic runtime routine. This is the version
+/// that takes arrays of any rank with a dim argument specified.
+void genMaxvalDim(fir::FirOpBuilder &builder, mlir::Location loc,
+                  mlir::Value resultBox, mlir::Value arrayBox, mlir::Value dim,
+                  mlir::Value maskBox);
+
+/// Generate call to `minval` intrinsic runtime routine. This is the version
+/// that does not take a dim argument.
+mlir::Value genMinval(fir::FirOpBuilder &builder, mlir::Location loc,
+                      mlir::Value arrayBox, mlir::Value maskBox);
+
+/// Generate call to `minval` intrinsic runtime routine. This is the version
+/// that that handles 1 dimensional character arrays with no DIM argument.
+void genMinvalChar(fir::FirOpBuilder &builder, mlir::Location loc,
+                   mlir::Value resultBox, mlir::Value arrayBox,
+                   mlir::Value maskBox);
+
+/// Generate call to `minval` intrinsic runtime routine. This is the version
+/// that takes arrays of any rank with a dim argument specified.
+void genMinvalDim(fir::FirOpBuilder &builder, mlir::Location loc,
+                  mlir::Value resultBox, mlir::Value arrayBox, mlir::Value dim,
+                  mlir::Value maskBox);
+
+/// Generate call to `product` intrinsic runtime routine. This is the version
+/// that does not take a dim argument.
+mlir::Value genProduct(fir::FirOpBuilder &builder, mlir::Location loc,
+                       mlir::Value arrayBox, mlir::Value maskBox,
+                       mlir::Value resultBox);
+
+/// Generate call to `product` intrinsic runtime routine. This is the version
+/// that takes arrays of any rank with a dim argument specified.
+void genProductDim(fir::FirOpBuilder &builder, mlir::Location loc,
+                   mlir::Value resultBox, mlir::Value arrayBox, mlir::Value dim,
+                   mlir::Value maskBox);
+
+/// Generate call to `sum` intrinsic runtime routine. This is the version
+/// that does not take a dim argument.
+mlir::Value genSum(fir::FirOpBuilder &builder, mlir::Location loc,
+                   mlir::Value arrayBox, mlir::Value maskBox,
+                   mlir::Value resultBox);
+
+/// Generate call to `sum` intrinsic runtime routine. This is the version
+/// that takes arrays of any rank with a dim argument specified.
+void genSumDim(fir::FirOpBuilder &builder, mlir::Location loc,
+               mlir::Value resultBox, mlir::Value arrayBox, mlir::Value dim,
+               mlir::Value maskBox);
+
+} // namespace fir::runtime
+
+#endif // FORTRAN_OPTIMIZER_BUILDER_RUNTIME_REDUCTION_H
diff --git a/flang/lib/Optimizer/Builder/CMakeLists.txt b/flang/lib/Optimizer/Builder/CMakeLists.txt
index 58f0e28..8d95558 100644
--- a/flang/lib/Optimizer/Builder/CMakeLists.txt
+++ b/flang/lib/Optimizer/Builder/CMakeLists.txt
@@ -8,6 +8,7 @@
   FIRBuilder.cpp
   MutableBox.cpp
   Runtime/Assign.cpp
+  Runtime/Reduction.cpp
   Runtime/Transformational.cpp
 
   DEPENDS
diff --git a/flang/lib/Optimizer/Builder/Runtime/Reduction.cpp b/flang/lib/Optimizer/Builder/Runtime/Reduction.cpp
new file mode 100644
index 0000000..21b4e2b
--- /dev/null
+++ b/flang/lib/Optimizer/Builder/Runtime/Reduction.cpp
@@ -0,0 +1,928 @@
+//===-- Reduction.cpp -- generate reduction intrinsics runtime calls- -----===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include "flang/Optimizer/Builder/Runtime/Reduction.h"
+#include "flang/Lower/Todo.h"
+#include "flang/Optimizer/Builder/BoxValue.h"
+#include "flang/Optimizer/Builder/Character.h"
+#include "flang/Optimizer/Builder/FIRBuilder.h"
+#include "flang/Optimizer/Builder/Runtime/RTBuilder.h"
+#include "flang/Runtime/reduction.h"
+#include "mlir/Dialect/StandardOps/IR/Ops.h"
+
+using namespace Fortran::runtime;
+
+/// Placeholder for real*10 version of Maxval Intrinsic
+struct ForcedMaxvalReal10 {
+  static constexpr const char *name = ExpandAndQuoteKey(RTNAME(MaxvalReal10));
+  static constexpr fir::runtime::FuncTypeBuilderFunc getTypeModel() {
+    return [](mlir::MLIRContext *ctx) {
+      auto ty = mlir::FloatType::getF80(ctx);
+      auto boxTy =
+          fir::runtime::getModel<const Fortran::runtime::Descriptor &>()(ctx);
+      auto strTy = fir::ReferenceType::get(mlir::IntegerType::get(ctx, 8));
+      auto intTy = mlir::IntegerType::get(ctx, 8 * sizeof(int));
+      return mlir::FunctionType::get(ctx, {boxTy, strTy, intTy, intTy, boxTy},
+                                     {ty});
+    };
+  }
+};
+
+/// Placeholder for real*16 version of Maxval Intrinsic
+struct ForcedMaxvalReal16 {
+  static constexpr const char *name = ExpandAndQuoteKey(RTNAME(MaxvalReal16));
+  static constexpr fir::runtime::FuncTypeBuilderFunc getTypeModel() {
+    return [](mlir::MLIRContext *ctx) {
+      auto ty = mlir::FloatType::getF128(ctx);
+      auto boxTy =
+          fir::runtime::getModel<const Fortran::runtime::Descriptor &>()(ctx);
+      auto strTy = fir::ReferenceType::get(mlir::IntegerType::get(ctx, 8));
+      auto intTy = mlir::IntegerType::get(ctx, 8 * sizeof(int));
+      return mlir::FunctionType::get(ctx, {boxTy, strTy, intTy, intTy, boxTy},
+                                     {ty});
+    };
+  }
+};
+
+/// Placeholder for integer*16 version of Maxval Intrinsic
+struct ForcedMaxvalInteger16 {
+  static constexpr const char *name =
+      ExpandAndQuoteKey(RTNAME(MaxvalInteger16));
+  static constexpr fir::runtime::FuncTypeBuilderFunc getTypeModel() {
+    return [](mlir::MLIRContext *ctx) {
+      auto ty = mlir::IntegerType::get(ctx, 128);
+      auto boxTy =
+          fir::runtime::getModel<const Fortran::runtime::Descriptor &>()(ctx);
+      auto strTy = fir::ReferenceType::get(mlir::IntegerType::get(ctx, 8));
+      auto intTy = mlir::IntegerType::get(ctx, 8 * sizeof(int));
+      return mlir::FunctionType::get(ctx, {boxTy, strTy, intTy, intTy, boxTy},
+                                     {ty});
+    };
+  }
+};
+
+/// Placeholder for real*10 version of Minval Intrinsic
+struct ForcedMinvalReal10 {
+  static constexpr const char *name = ExpandAndQuoteKey(RTNAME(MinvalReal10));
+  static constexpr fir::runtime::FuncTypeBuilderFunc getTypeModel() {
+    return [](mlir::MLIRContext *ctx) {
+      auto ty = mlir::FloatType::getF80(ctx);
+      auto boxTy =
+          fir::runtime::getModel<const Fortran::runtime::Descriptor &>()(ctx);
+      auto strTy = fir::ReferenceType::get(mlir::IntegerType::get(ctx, 8));
+      auto intTy = mlir::IntegerType::get(ctx, 8 * sizeof(int));
+      return mlir::FunctionType::get(ctx, {boxTy, strTy, intTy, intTy, boxTy},
+                                     {ty});
+    };
+  }
+};
+
+/// Placeholder for real*16 version of Minval Intrinsic
+struct ForcedMinvalReal16 {
+  static constexpr const char *name = ExpandAndQuoteKey(RTNAME(MinvalReal16));
+  static constexpr fir::runtime::FuncTypeBuilderFunc getTypeModel() {
+    return [](mlir::MLIRContext *ctx) {
+      auto ty = mlir::FloatType::getF128(ctx);
+      auto boxTy =
+          fir::runtime::getModel<const Fortran::runtime::Descriptor &>()(ctx);
+      auto strTy = fir::ReferenceType::get(mlir::IntegerType::get(ctx, 8));
+      auto intTy = mlir::IntegerType::get(ctx, 8 * sizeof(int));
+      return mlir::FunctionType::get(ctx, {boxTy, strTy, intTy, intTy, boxTy},
+                                     {ty});
+    };
+  }
+};
+
+/// Placeholder for integer*16 version of Minval Intrinsic
+struct ForcedMinvalInteger16 {
+  static constexpr const char *name =
+      ExpandAndQuoteKey(RTNAME(MinvalInteger16));
+  static constexpr fir::runtime::FuncTypeBuilderFunc getTypeModel() {
+    return [](mlir::MLIRContext *ctx) {
+      auto ty = mlir::IntegerType::get(ctx, 128);
+      auto boxTy =
+          fir::runtime::getModel<const Fortran::runtime::Descriptor &>()(ctx);
+      auto strTy = fir::ReferenceType::get(mlir::IntegerType::get(ctx, 8));
+      auto intTy = mlir::IntegerType::get(ctx, 8 * sizeof(int));
+      return mlir::FunctionType::get(ctx, {boxTy, strTy, intTy, intTy, boxTy},
+                                     {ty});
+    };
+  }
+};
+
+/// Placeholder for real*10 version of Product Intrinsic
+struct ForcedProductReal10 {
+  static constexpr const char *name = ExpandAndQuoteKey(RTNAME(ProductReal10));
+  static constexpr fir::runtime::FuncTypeBuilderFunc getTypeModel() {
+    return [](mlir::MLIRContext *ctx) {
+      auto ty = mlir::FloatType::getF80(ctx);
+      auto boxTy =
+          fir::runtime::getModel<const Fortran::runtime::Descriptor &>()(ctx);
+      auto strTy = fir::ReferenceType::get(mlir::IntegerType::get(ctx, 8));
+      auto intTy = mlir::IntegerType::get(ctx, 8 * sizeof(int));
+      return mlir::FunctionType::get(ctx, {boxTy, strTy, intTy, intTy, boxTy},
+                                     {ty});
+    };
+  }
+};
+
+/// Placeholder for real*16 version of Product Intrinsic
+struct ForcedProductReal16 {
+  static constexpr const char *name = ExpandAndQuoteKey(RTNAME(ProductReal16));
+  static constexpr fir::runtime::FuncTypeBuilderFunc getTypeModel() {
+    return [](mlir::MLIRContext *ctx) {
+      auto ty = mlir::FloatType::getF128(ctx);
+      auto boxTy =
+          fir::runtime::getModel<const Fortran::runtime::Descriptor &>()(ctx);
+      auto strTy = fir::ReferenceType::get(mlir::IntegerType::get(ctx, 8));
+      auto intTy = mlir::IntegerType::get(ctx, 8 * sizeof(int));
+      return mlir::FunctionType::get(ctx, {boxTy, strTy, intTy, intTy, boxTy},
+                                     {ty});
+    };
+  }
+};
+
+/// Placeholder for integer*16 version of Product Intrinsic
+struct ForcedProductInteger16 {
+  static constexpr const char *name =
+      ExpandAndQuoteKey(RTNAME(ProductInteger16));
+  static constexpr fir::runtime::FuncTypeBuilderFunc getTypeModel() {
+    return [](mlir::MLIRContext *ctx) {
+      auto ty = mlir::IntegerType::get(ctx, 128);
+      auto boxTy =
+          fir::runtime::getModel<const Fortran::runtime::Descriptor &>()(ctx);
+      auto strTy = fir::ReferenceType::get(mlir::IntegerType::get(ctx, 8));
+      auto intTy = mlir::IntegerType::get(ctx, 8 * sizeof(int));
+      return mlir::FunctionType::get(ctx, {boxTy, strTy, intTy, intTy, boxTy},
+                                     {ty});
+    };
+  }
+};
+
+/// Placeholder for complex(10) version of Product Intrinsic
+struct ForcedProductComplex10 {
+  static constexpr const char *name =
+      ExpandAndQuoteKey(RTNAME(CppProductComplex10));
+  static constexpr fir::runtime::FuncTypeBuilderFunc getTypeModel() {
+    return [](mlir::MLIRContext *ctx) {
+      auto ty = mlir::ComplexType::get(mlir::FloatType::getF80(ctx));
+      auto boxTy =
+          fir::runtime::getModel<const Fortran::runtime::Descriptor &>()(ctx);
+      auto strTy = fir::ReferenceType::get(mlir::IntegerType::get(ctx, 8));
+      auto intTy = mlir::IntegerType::get(ctx, 8 * sizeof(int));
+      auto resTy = fir::ReferenceType::get(ty);
+      return mlir::FunctionType::get(
+          ctx, {resTy, boxTy, strTy, intTy, intTy, boxTy}, {});
+    };
+  }
+};
+
+/// Placeholder for complex(16) version of Product Intrinsic
+struct ForcedProductComplex16 {
+  static constexpr const char *name =
+      ExpandAndQuoteKey(RTNAME(CppProductComplex16));
+  static constexpr fir::runtime::FuncTypeBuilderFunc getTypeModel() {
+    return [](mlir::MLIRContext *ctx) {
+      auto ty = mlir::ComplexType::get(mlir::FloatType::getF128(ctx));
+      auto boxTy =
+          fir::runtime::getModel<const Fortran::runtime::Descriptor &>()(ctx);
+      auto strTy = fir::ReferenceType::get(mlir::IntegerType::get(ctx, 8));
+      auto intTy = mlir::IntegerType::get(ctx, 8 * sizeof(int));
+      auto resTy = fir::ReferenceType::get(ty);
+      return mlir::FunctionType::get(
+          ctx, {resTy, boxTy, strTy, intTy, intTy, boxTy}, {});
+    };
+  }
+};
+
+/// Placeholder for real*10 version of DotProduct Intrinsic
+struct ForcedDotProductReal10 {
+  static constexpr const char *name =
+      ExpandAndQuoteKey(RTNAME(DotProductReal10));
+  static constexpr fir::runtime::FuncTypeBuilderFunc getTypeModel() {
+    return [](mlir::MLIRContext *ctx) {
+      auto ty = mlir::FloatType::getF80(ctx);
+      auto boxTy =
+          fir::runtime::getModel<const Fortran::runtime::Descriptor &>()(ctx);
+      auto strTy = fir::ReferenceType::get(mlir::IntegerType::get(ctx, 8));
+      auto intTy = mlir::IntegerType::get(ctx, 8 * sizeof(int));
+      return mlir::FunctionType::get(ctx, {boxTy, boxTy, strTy, intTy}, {ty});
+    };
+  }
+};
+
+/// Placeholder for real*16 version of DotProduct Intrinsic
+struct ForcedDotProductReal16 {
+  static constexpr const char *name =
+      ExpandAndQuoteKey(RTNAME(DotProductReal16));
+  static constexpr fir::runtime::FuncTypeBuilderFunc getTypeModel() {
+    return [](mlir::MLIRContext *ctx) {
+      auto ty = mlir::FloatType::getF128(ctx);
+      auto boxTy =
+          fir::runtime::getModel<const Fortran::runtime::Descriptor &>()(ctx);
+      auto strTy = fir::ReferenceType::get(mlir::IntegerType::get(ctx, 8));
+      auto intTy = mlir::IntegerType::get(ctx, 8 * sizeof(int));
+      return mlir::FunctionType::get(ctx, {boxTy, boxTy, strTy, intTy}, {ty});
+    };
+  }
+};
+
+/// Placeholder for complex(10) version of DotProduct Intrinsic
+struct ForcedDotProductComplex10 {
+  static constexpr const char *name =
+      ExpandAndQuoteKey(RTNAME(CppDotProductComplex10));
+  static constexpr fir::runtime::FuncTypeBuilderFunc getTypeModel() {
+    return [](mlir::MLIRContext *ctx) {
+      auto ty = mlir::ComplexType::get(mlir::FloatType::getF80(ctx));
+      auto boxTy =
+          fir::runtime::getModel<const Fortran::runtime::Descriptor &>()(ctx);
+      auto strTy = fir::ReferenceType::get(mlir::IntegerType::get(ctx, 8));
+      auto intTy = mlir::IntegerType::get(ctx, 8 * sizeof(int));
+      auto resTy = fir::ReferenceType::get(ty);
+      return mlir::FunctionType::get(ctx, {resTy, boxTy, boxTy, strTy, intTy},
+                                     {});
+    };
+  }
+};
+
+/// Placeholder for complex(16) version of DotProduct Intrinsic
+struct ForcedDotProductComplex16 {
+  static constexpr const char *name =
+      ExpandAndQuoteKey(RTNAME(CppDotProductComplex16));
+  static constexpr fir::runtime::FuncTypeBuilderFunc getTypeModel() {
+    return [](mlir::MLIRContext *ctx) {
+      auto ty = mlir::ComplexType::get(mlir::FloatType::getF128(ctx));
+      auto boxTy =
+          fir::runtime::getModel<const Fortran::runtime::Descriptor &>()(ctx);
+      auto strTy = fir::ReferenceType::get(mlir::IntegerType::get(ctx, 8));
+      auto intTy = mlir::IntegerType::get(ctx, 8 * sizeof(int));
+      auto resTy = fir::ReferenceType::get(ty);
+      return mlir::FunctionType::get(ctx, {resTy, boxTy, boxTy, strTy, intTy},
+                                     {});
+    };
+  }
+};
+
+/// Placeholder for integer*16 version of DotProduct Intrinsic
+struct ForcedDotProductInteger16 {
+  static constexpr const char *name =
+      ExpandAndQuoteKey(RTNAME(DotProductInteger16));
+  static constexpr fir::runtime::FuncTypeBuilderFunc getTypeModel() {
+    return [](mlir::MLIRContext *ctx) {
+      auto ty = mlir::IntegerType::get(ctx, 128);
+      auto boxTy =
+          fir::runtime::getModel<const Fortran::runtime::Descriptor &>()(ctx);
+      auto strTy = fir::ReferenceType::get(mlir::IntegerType::get(ctx, 8));
+      auto intTy = mlir::IntegerType::get(ctx, 8 * sizeof(int));
+      return mlir::FunctionType::get(ctx, {boxTy, boxTy, strTy, intTy}, {ty});
+    };
+  }
+};
+
+/// Placeholder for real*10 version of Sum Intrinsic
+struct ForcedSumReal10 {
+  static constexpr const char *name = ExpandAndQuoteKey(RTNAME(SumReal10));
+  static constexpr fir::runtime::FuncTypeBuilderFunc getTypeModel() {
+    return [](mlir::MLIRContext *ctx) {
+      auto ty = mlir::FloatType::getF80(ctx);
+      auto boxTy =
+          fir::runtime::getModel<const Fortran::runtime::Descriptor &>()(ctx);
+      auto strTy = fir::ReferenceType::get(mlir::IntegerType::get(ctx, 8));
+      auto intTy = mlir::IntegerType::get(ctx, 8 * sizeof(int));
+      return mlir::FunctionType::get(ctx, {boxTy, strTy, intTy, intTy, boxTy},
+                                     {ty});
+    };
+  }
+};
+
+/// Placeholder for real*16 version of Sum Intrinsic
+struct ForcedSumReal16 {
+  static constexpr const char *name = ExpandAndQuoteKey(RTNAME(SumReal16));
+  static constexpr fir::runtime::FuncTypeBuilderFunc getTypeModel() {
+    return [](mlir::MLIRContext *ctx) {
+      auto ty = mlir::FloatType::getF128(ctx);
+      auto boxTy =
+          fir::runtime::getModel<const Fortran::runtime::Descriptor &>()(ctx);
+      auto strTy = fir::ReferenceType::get(mlir::IntegerType::get(ctx, 8));
+      auto intTy = mlir::IntegerType::get(ctx, 8 * sizeof(int));
+      return mlir::FunctionType::get(ctx, {boxTy, strTy, intTy, intTy, boxTy},
+                                     {ty});
+    };
+  }
+};
+
+/// Placeholder for integer*16 version of Sum Intrinsic
+struct ForcedSumInteger16 {
+  static constexpr const char *name = ExpandAndQuoteKey(RTNAME(SumInteger16));
+  static constexpr fir::runtime::FuncTypeBuilderFunc getTypeModel() {
+    return [](mlir::MLIRContext *ctx) {
+      auto ty = mlir::IntegerType::get(ctx, 128);
+      auto boxTy =
+          fir::runtime::getModel<const Fortran::runtime::Descriptor &>()(ctx);
+      auto strTy = fir::ReferenceType::get(mlir::IntegerType::get(ctx, 8));
+      auto intTy = mlir::IntegerType::get(ctx, 8 * sizeof(int));
+      return mlir::FunctionType::get(ctx, {boxTy, strTy, intTy, intTy, boxTy},
+                                     {ty});
+    };
+  }
+};
+
+/// Placeholder for complex(10) version of Sum Intrinsic
+struct ForcedSumComplex10 {
+  static constexpr const char *name =
+      ExpandAndQuoteKey(RTNAME(CppSumComplex10));
+  static constexpr fir::runtime::FuncTypeBuilderFunc getTypeModel() {
+    return [](mlir::MLIRContext *ctx) {
+      auto ty = mlir::ComplexType::get(mlir::FloatType::getF80(ctx));
+      auto boxTy =
+          fir::runtime::getModel<const Fortran::runtime::Descriptor &>()(ctx);
+      auto strTy = fir::ReferenceType::get(mlir::IntegerType::get(ctx, 8));
+      auto intTy = mlir::IntegerType::get(ctx, 8 * sizeof(int));
+      auto resTy = fir::ReferenceType::get(ty);
+      return mlir::FunctionType::get(
+          ctx, {resTy, boxTy, strTy, intTy, intTy, boxTy}, {});
+    };
+  }
+};
+
+/// Placeholder for complex(16) version of Sum Intrinsic
+struct ForcedSumComplex16 {
+  static constexpr const char *name =
+      ExpandAndQuoteKey(RTNAME(CppSumComplex16));
+  static constexpr fir::runtime::FuncTypeBuilderFunc getTypeModel() {
+    return [](mlir::MLIRContext *ctx) {
+      auto ty = mlir::ComplexType::get(mlir::FloatType::getF128(ctx));
+      auto boxTy =
+          fir::runtime::getModel<const Fortran::runtime::Descriptor &>()(ctx);
+      auto strTy = fir::ReferenceType::get(mlir::IntegerType::get(ctx, 8));
+      auto intTy = mlir::IntegerType::get(ctx, 8 * sizeof(int));
+      auto resTy = fir::ReferenceType::get(ty);
+      return mlir::FunctionType::get(
+          ctx, {resTy, boxTy, strTy, intTy, intTy, boxTy}, {});
+    };
+  }
+};
+
+/// Generate call to specialized runtime function that takes a mask and
+/// dim argument. The All, Any, and Count intrinsics use this pattern.
+template <typename FN>
+mlir::Value genSpecial2Args(FN func, fir::FirOpBuilder &builder,
+                            mlir::Location loc, mlir::Value maskBox,
+                            mlir::Value dim) {
+  auto fTy = func.getType();
+  auto sourceFile = fir::factory::locationToFilename(builder, loc);
+  auto sourceLine =
+      fir::factory::locationToLineNo(builder, loc, fTy.getInput(2));
+  auto args = fir::runtime::createArguments(builder, loc, fTy, maskBox,
+                                            sourceFile, sourceLine, dim);
+  return builder.create<fir::CallOp>(loc, func, args).getResult(0);
+}
+
+/// Generate calls to reduction intrinsics such as All and Any.
+/// These are the descriptor based implementations that take two
+/// arguments (mask, dim).
+template <typename FN>
+static void genReduction2Args(FN func, fir::FirOpBuilder &builder,
+                              mlir::Location loc, mlir::Value resultBox,
+                              mlir::Value maskBox, mlir::Value dim) {
+  auto fTy = func.getType();
+  auto sourceFile = fir::factory::locationToFilename(builder, loc);
+  auto sourceLine =
+      fir::factory::locationToLineNo(builder, loc, fTy.getInput(4));
+  auto args = fir::runtime::createArguments(
+      builder, loc, fTy, resultBox, maskBox, dim, sourceFile, sourceLine);
+  builder.create<fir::CallOp>(loc, func, args);
+}
+
+/// Generate calls to reduction intrinsics such as Maxval and Minval.
+/// These take arguments such as (array, dim, mask).
+template <typename FN>
+static void genReduction3Args(FN func, fir::FirOpBuilder &builder,
+                              mlir::Location loc, mlir::Value resultBox,
+                              mlir::Value arrayBox, mlir::Value dim,
+                              mlir::Value maskBox) {
+
+  auto fTy = func.getType();
+  auto sourceFile = fir::factory::locationToFilename(builder, loc);
+  auto sourceLine =
+      fir::factory::locationToLineNo(builder, loc, fTy.getInput(4));
+  auto args =
+      fir::runtime::createArguments(builder, loc, fTy, resultBox, arrayBox, dim,
+                                    sourceFile, sourceLine, maskBox);
+  builder.create<fir::CallOp>(loc, func, args);
+}
+
+/// Generate calls to reduction intrinsics such as Maxloc and Minloc.
+/// These take arguments such as (array, mask, kind, back).
+template <typename FN>
+static void genReduction4Args(FN func, fir::FirOpBuilder &builder,
+                              mlir::Location loc, mlir::Value resultBox,
+                              mlir::Value arrayBox, mlir::Value maskBox,
+                              mlir::Value kind, mlir::Value back) {
+  auto fTy = func.getType();
+  auto sourceFile = fir::factory::locationToFilename(builder, loc);
+  auto sourceLine =
+      fir::factory::locationToLineNo(builder, loc, fTy.getInput(4));
+  auto args = fir::runtime::createArguments(builder, loc, fTy, resultBox,
+                                            arrayBox, kind, sourceFile,
+                                            sourceLine, maskBox, back);
+  builder.create<fir::CallOp>(loc, func, args);
+}
+
+/// Generate calls to reduction intrinsics such as Maxloc and Minloc.
+/// These take arguments such as (array, dim, mask, kind, back).
+template <typename FN>
+static void
+genReduction5Args(FN func, fir::FirOpBuilder &builder, mlir::Location loc,
+                  mlir::Value resultBox, mlir::Value arrayBox, mlir::Value dim,
+                  mlir::Value maskBox, mlir::Value kind, mlir::Value back) {
+  auto fTy = func.getType();
+  auto sourceFile = fir::factory::locationToFilename(builder, loc);
+  auto sourceLine =
+      fir::factory::locationToLineNo(builder, loc, fTy.getInput(5));
+  auto args = fir::runtime::createArguments(builder, loc, fTy, resultBox,
+                                            arrayBox, kind, dim, sourceFile,
+                                            sourceLine, maskBox, back);
+  builder.create<fir::CallOp>(loc, func, args);
+}
+
+/// Generate call to `all` runtime routine.
+/// This calls the descriptor based runtime call implementation of the `all`
+/// intrinsic.
+void fir::runtime::genAllDescriptor(fir::FirOpBuilder &builder,
+                                    mlir::Location loc, mlir::Value resultBox,
+                                    mlir::Value maskBox, mlir::Value dim) {
+  auto allFunc = fir::runtime::getRuntimeFunc<mkRTKey(AllDim)>(loc, builder);
+  genReduction2Args(allFunc, builder, loc, resultBox, maskBox, dim);
+}
+
+/// Generate call to `any` runtime routine.
+/// This calls the descriptor based runtime call implementation of the `any`
+/// intrinsic.
+void fir::runtime::genAnyDescriptor(fir::FirOpBuilder &builder,
+                                    mlir::Location loc, mlir::Value resultBox,
+                                    mlir::Value maskBox, mlir::Value dim) {
+  auto anyFunc = fir::runtime::getRuntimeFunc<mkRTKey(AnyDim)>(loc, builder);
+  genReduction2Args(anyFunc, builder, loc, resultBox, maskBox, dim);
+}
+
+/// Generate call to `all` intrinsic runtime routine. This routine is
+/// specialized for mask arguments with rank == 1.
+mlir::Value fir::runtime::genAll(fir::FirOpBuilder &builder, mlir::Location loc,
+                                 mlir::Value maskBox, mlir::Value dim) {
+  auto allFunc = fir::runtime::getRuntimeFunc<mkRTKey(All)>(loc, builder);
+  return genSpecial2Args(allFunc, builder, loc, maskBox, dim);
+}
+
+/// Generate call to `any` intrinsic runtime routine. This routine is
+/// specialized for mask arguments with rank == 1.
+mlir::Value fir::runtime::genAny(fir::FirOpBuilder &builder, mlir::Location loc,
+                                 mlir::Value maskBox, mlir::Value dim) {
+  auto anyFunc = fir::runtime::getRuntimeFunc<mkRTKey(Any)>(loc, builder);
+  return genSpecial2Args(anyFunc, builder, loc, maskBox, dim);
+}
+
+/// Generate call to `count` runtime routine. This routine is a specialized
+/// version when mask is a rank one array or the dim argument is not
+/// specified by the user.
+mlir::Value fir::runtime::genCount(fir::FirOpBuilder &builder,
+                                   mlir::Location loc, mlir::Value maskBox,
+                                   mlir::Value dim) {
+  auto countFunc = fir::runtime::getRuntimeFunc<mkRTKey(Count)>(loc, builder);
+  return genSpecial2Args(countFunc, builder, loc, maskBox, dim);
+}
+
+/// Generate call to general CountDim runtime routine. This routine has a
+/// descriptor result.
+void fir::runtime::genCountDim(fir::FirOpBuilder &builder, mlir::Location loc,
+                               mlir::Value resultBox, mlir::Value maskBox,
+                               mlir::Value dim, mlir::Value kind) {
+  auto func = fir::runtime::getRuntimeFunc<mkRTKey(CountDim)>(loc, builder);
+  auto fTy = func.getType();
+  auto sourceFile = fir::factory::locationToFilename(builder, loc);
+  auto sourceLine =
+      fir::factory::locationToLineNo(builder, loc, fTy.getInput(5));
+  auto args = fir::runtime::createArguments(
+      builder, loc, fTy, resultBox, maskBox, dim, kind, sourceFile, sourceLine);
+  builder.create<fir::CallOp>(loc, func, args);
+}
+
+/// Generate call to `maxloc` intrinsic runtime routine. This is the version
+/// that does not take a dim argument.
+void fir::runtime::genMaxloc(fir::FirOpBuilder &builder, mlir::Location loc,
+                             mlir::Value resultBox, mlir::Value arrayBox,
+                             mlir::Value maskBox, mlir::Value kind,
+                             mlir::Value back) {
+  auto func = fir::runtime::getRuntimeFunc<mkRTKey(Maxloc)>(loc, builder);
+  genReduction4Args(func, builder, loc, resultBox, arrayBox, maskBox, kind,
+                    back);
+}
+
+/// Generate call to `maxloc` intrinsic runtime routine. This is the version
+/// that takes a dim argument.
+void fir::runtime::genMaxlocDim(fir::FirOpBuilder &builder, mlir::Location loc,
+                                mlir::Value resultBox, mlir::Value arrayBox,
+                                mlir::Value dim, mlir::Value maskBox,
+                                mlir::Value kind, mlir::Value back) {
+  auto func = fir::runtime::getRuntimeFunc<mkRTKey(MaxlocDim)>(loc, builder);
+  genReduction5Args(func, builder, loc, resultBox, arrayBox, dim, maskBox, kind,
+                    back);
+}
+
+/// Generate call to `maxval` intrinsic runtime routine. This is the version
+/// that does not take a dim argument.
+mlir::Value fir::runtime::genMaxval(fir::FirOpBuilder &builder,
+                                    mlir::Location loc, mlir::Value arrayBox,
+                                    mlir::Value maskBox) {
+  mlir::FuncOp func;
+  auto ty = arrayBox.getType();
+  auto arrTy = fir::dyn_cast_ptrOrBoxEleTy(ty);
+  auto eleTy = arrTy.cast<fir::SequenceType>().getEleTy();
+  auto dim = builder.createIntegerConstant(loc, builder.getIndexType(), 0);
+
+  if (eleTy.isF32())
+    func = fir::runtime::getRuntimeFunc<mkRTKey(MaxvalReal4)>(loc, builder);
+  else if (eleTy.isF64())
+    func = fir::runtime::getRuntimeFunc<mkRTKey(MaxvalReal8)>(loc, builder);
+  else if (eleTy.isF80())
+    func = fir::runtime::getRuntimeFunc<ForcedMaxvalReal10>(loc, builder);
+  else if (eleTy.isF128())
+    func = fir::runtime::getRuntimeFunc<ForcedMaxvalReal16>(loc, builder);
+  else if (eleTy ==
+           builder.getIntegerType(builder.getKindMap().getIntegerBitsize(1)))
+    func = fir::runtime::getRuntimeFunc<mkRTKey(MaxvalInteger1)>(loc, builder);
+  else if (eleTy ==
+           builder.getIntegerType(builder.getKindMap().getIntegerBitsize(2)))
+    func = fir::runtime::getRuntimeFunc<mkRTKey(MaxvalInteger2)>(loc, builder);
+  else if (eleTy ==
+           builder.getIntegerType(builder.getKindMap().getIntegerBitsize(4)))
+    func = fir::runtime::getRuntimeFunc<mkRTKey(MaxvalInteger4)>(loc, builder);
+  else if (eleTy ==
+           builder.getIntegerType(builder.getKindMap().getIntegerBitsize(8)))
+    func = fir::runtime::getRuntimeFunc<mkRTKey(MaxvalInteger8)>(loc, builder);
+  else if (eleTy ==
+           builder.getIntegerType(builder.getKindMap().getIntegerBitsize(16)))
+    func = fir::runtime::getRuntimeFunc<ForcedMaxvalInteger16>(loc, builder);
+  else
+    fir::emitFatalError(loc, "invalid type in Maxval lowering");
+
+  auto fTy = func.getType();
+  auto sourceFile = fir::factory::locationToFilename(builder, loc);
+  auto sourceLine =
+      fir::factory::locationToLineNo(builder, loc, fTy.getInput(2));
+  auto args = fir::runtime::createArguments(
+      builder, loc, fTy, arrayBox, sourceFile, sourceLine, dim, maskBox);
+
+  return builder.create<fir::CallOp>(loc, func, args).getResult(0);
+}
+
+/// Generate call to `maxval` intrinsic runtime routine. This is the version
+/// that handles any rank array with the dim argument specified.
+void fir::runtime::genMaxvalDim(fir::FirOpBuilder &builder, mlir::Location loc,
+                                mlir::Value resultBox, mlir::Value arrayBox,
+                                mlir::Value dim, mlir::Value maskBox) {
+  auto func = fir::runtime::getRuntimeFunc<mkRTKey(MaxvalDim)>(loc, builder);
+  genReduction3Args(func, builder, loc, resultBox, arrayBox, dim, maskBox);
+}
+
+/// Generate call to `maxval` intrinsic runtime routine. This is the version
+/// that handles character arrays of rank 1 and without a DIM argument.
+void fir::runtime::genMaxvalChar(fir::FirOpBuilder &builder, mlir::Location loc,
+                                 mlir::Value resultBox, mlir::Value arrayBox,
+                                 mlir::Value maskBox) {
+  auto func =
+      fir::runtime::getRuntimeFunc<mkRTKey(MaxvalCharacter)>(loc, builder);
+  auto fTy = func.getType();
+  auto sourceFile = fir::factory::locationToFilename(builder, loc);
+  auto sourceLine =
+      fir::factory::locationToLineNo(builder, loc, fTy.getInput(3));
+  auto args = fir::runtime::createArguments(
+      builder, loc, fTy, resultBox, arrayBox, sourceFile, sourceLine, maskBox);
+  builder.create<fir::CallOp>(loc, func, args);
+}
+
+/// Generate call to `minloc` intrinsic runtime routine. This is the version
+/// that does not take a dim argument.
+void fir::runtime::genMinloc(fir::FirOpBuilder &builder, mlir::Location loc,
+                             mlir::Value resultBox, mlir::Value arrayBox,
+                             mlir::Value maskBox, mlir::Value kind,
+                             mlir::Value back) {
+  auto func = fir::runtime::getRuntimeFunc<mkRTKey(Minloc)>(loc, builder);
+  genReduction4Args(func, builder, loc, resultBox, arrayBox, maskBox, kind,
+                    back);
+}
+
+/// Generate call to `minloc` intrinsic runtime routine. This is the version
+/// that takes a dim argument.
+void fir::runtime::genMinlocDim(fir::FirOpBuilder &builder, mlir::Location loc,
+                                mlir::Value resultBox, mlir::Value arrayBox,
+                                mlir::Value dim, mlir::Value maskBox,
+                                mlir::Value kind, mlir::Value back) {
+  auto func = fir::runtime::getRuntimeFunc<mkRTKey(MinlocDim)>(loc, builder);
+  genReduction5Args(func, builder, loc, resultBox, arrayBox, dim, maskBox, kind,
+                    back);
+}
+
+/// Generate call to `minval` intrinsic runtime routine. This is the version
+/// that handles any rank array with the dim argument specified.
+void fir::runtime::genMinvalDim(fir::FirOpBuilder &builder, mlir::Location loc,
+                                mlir::Value resultBox, mlir::Value arrayBox,
+                                mlir::Value dim, mlir::Value maskBox) {
+  auto func = fir::runtime::getRuntimeFunc<mkRTKey(MinvalDim)>(loc, builder);
+  genReduction3Args(func, builder, loc, resultBox, arrayBox, dim, maskBox);
+}
+
+/// Generate call to `minval` intrinsic runtime routine. This is the version
+/// that handles character arrays of rank 1 and without a DIM argument.
+void fir::runtime::genMinvalChar(fir::FirOpBuilder &builder, mlir::Location loc,
+                                 mlir::Value resultBox, mlir::Value arrayBox,
+                                 mlir::Value maskBox) {
+  auto func =
+      fir::runtime::getRuntimeFunc<mkRTKey(MinvalCharacter)>(loc, builder);
+  auto fTy = func.getType();
+  auto sourceFile = fir::factory::locationToFilename(builder, loc);
+  auto sourceLine =
+      fir::factory::locationToLineNo(builder, loc, fTy.getInput(3));
+  auto args = fir::runtime::createArguments(
+      builder, loc, fTy, resultBox, arrayBox, sourceFile, sourceLine, maskBox);
+  builder.create<fir::CallOp>(loc, func, args);
+}
+
+/// Generate call to `minval` intrinsic runtime routine. This is the version
+/// that does not take a dim argument.
+mlir::Value fir::runtime::genMinval(fir::FirOpBuilder &builder,
+                                    mlir::Location loc, mlir::Value arrayBox,
+                                    mlir::Value maskBox) {
+  mlir::FuncOp func;
+  auto ty = arrayBox.getType();
+  auto arrTy = fir::dyn_cast_ptrOrBoxEleTy(ty);
+  auto eleTy = arrTy.cast<fir::SequenceType>().getEleTy();
+  auto dim = builder.createIntegerConstant(loc, builder.getIndexType(), 0);
+
+  if (eleTy.isF32())
+    func = fir::runtime::getRuntimeFunc<mkRTKey(MinvalReal4)>(loc, builder);
+  else if (eleTy.isF64())
+    func = fir::runtime::getRuntimeFunc<mkRTKey(MinvalReal8)>(loc, builder);
+  else if (eleTy.isF80())
+    func = fir::runtime::getRuntimeFunc<ForcedMinvalReal10>(loc, builder);
+  else if (eleTy.isF128())
+    func = fir::runtime::getRuntimeFunc<ForcedMinvalReal16>(loc, builder);
+  else if (eleTy ==
+           builder.getIntegerType(builder.getKindMap().getIntegerBitsize(1)))
+    func = fir::runtime::getRuntimeFunc<mkRTKey(MinvalInteger1)>(loc, builder);
+  else if (eleTy ==
+           builder.getIntegerType(builder.getKindMap().getIntegerBitsize(2)))
+    func = fir::runtime::getRuntimeFunc<mkRTKey(MinvalInteger2)>(loc, builder);
+  else if (eleTy ==
+           builder.getIntegerType(builder.getKindMap().getIntegerBitsize(4)))
+    func = fir::runtime::getRuntimeFunc<mkRTKey(MinvalInteger4)>(loc, builder);
+  else if (eleTy ==
+           builder.getIntegerType(builder.getKindMap().getIntegerBitsize(8)))
+    func = fir::runtime::getRuntimeFunc<mkRTKey(MinvalInteger8)>(loc, builder);
+  else if (eleTy ==
+           builder.getIntegerType(builder.getKindMap().getIntegerBitsize(16)))
+    func = fir::runtime::getRuntimeFunc<ForcedMinvalInteger16>(loc, builder);
+  else
+    fir::emitFatalError(loc, "invalid type in Minval lowering");
+
+  auto fTy = func.getType();
+  auto sourceFile = fir::factory::locationToFilename(builder, loc);
+  auto sourceLine =
+      fir::factory::locationToLineNo(builder, loc, fTy.getInput(2));
+  auto args = fir::runtime::createArguments(
+      builder, loc, fTy, arrayBox, sourceFile, sourceLine, dim, maskBox);
+
+  return builder.create<fir::CallOp>(loc, func, args).getResult(0);
+}
+
+/// Generate call to `product` intrinsic runtime routine. This is the version
+/// that handles any rank array with the dim argument specified.
+void fir::runtime::genProductDim(fir::FirOpBuilder &builder, mlir::Location loc,
+                                 mlir::Value resultBox, mlir::Value arrayBox,
+                                 mlir::Value dim, mlir::Value maskBox) {
+  auto func = fir::runtime::getRuntimeFunc<mkRTKey(ProductDim)>(loc, builder);
+  genReduction3Args(func, builder, loc, resultBox, arrayBox, dim, maskBox);
+}
+
+/// Generate call to `product` intrinsic runtime routine. This is the version
+/// that does not take a dim argument.
+mlir::Value fir::runtime::genProduct(fir::FirOpBuilder &builder,
+                                     mlir::Location loc, mlir::Value arrayBox,
+                                     mlir::Value maskBox,
+                                     mlir::Value resultBox) {
+  mlir::FuncOp func;
+  auto ty = arrayBox.getType();
+  auto arrTy = fir::dyn_cast_ptrOrBoxEleTy(ty);
+  auto eleTy = arrTy.cast<fir::SequenceType>().getEleTy();
+  // Dim is set to 0 for the version that does not have it as argument.
+  auto dim = builder.createIntegerConstant(loc, builder.getIndexType(), 0);
+
+  if (eleTy.isF32())
+    func = fir::runtime::getRuntimeFunc<mkRTKey(ProductReal4)>(loc, builder);
+  else if (eleTy.isF64())
+    func = fir::runtime::getRuntimeFunc<mkRTKey(ProductReal8)>(loc, builder);
+  else if (eleTy.isF80())
+    func = fir::runtime::getRuntimeFunc<ForcedProductReal10>(loc, builder);
+  else if (eleTy.isF128())
+    func = fir::runtime::getRuntimeFunc<ForcedProductReal16>(loc, builder);
+  else if (eleTy ==
+           builder.getIntegerType(builder.getKindMap().getIntegerBitsize(1)))
+    func = fir::runtime::getRuntimeFunc<mkRTKey(ProductInteger1)>(loc, builder);
+  else if (eleTy ==
+           builder.getIntegerType(builder.getKindMap().getIntegerBitsize(2)))
+    func = fir::runtime::getRuntimeFunc<mkRTKey(ProductInteger2)>(loc, builder);
+  else if (eleTy ==
+           builder.getIntegerType(builder.getKindMap().getIntegerBitsize(4)))
+    func = fir::runtime::getRuntimeFunc<mkRTKey(ProductInteger4)>(loc, builder);
+  else if (eleTy ==
+           builder.getIntegerType(builder.getKindMap().getIntegerBitsize(8)))
+    func = fir::runtime::getRuntimeFunc<mkRTKey(ProductInteger8)>(loc, builder);
+  else if (eleTy ==
+           builder.getIntegerType(builder.getKindMap().getIntegerBitsize(16)))
+    func = fir::runtime::getRuntimeFunc<ForcedProductInteger16>(loc, builder);
+  else if (eleTy == fir::ComplexType::get(builder.getContext(), 4))
+    func =
+        fir::runtime::getRuntimeFunc<mkRTKey(CppProductComplex4)>(loc, builder);
+  else if (eleTy == fir::ComplexType::get(builder.getContext(), 8))
+    func =
+        fir::runtime::getRuntimeFunc<mkRTKey(CppProductComplex8)>(loc, builder);
+  else if (eleTy == fir::ComplexType::get(builder.getContext(), 10))
+    func = fir::runtime::getRuntimeFunc<ForcedProductComplex10>(loc, builder);
+  else if (eleTy == fir::ComplexType::get(builder.getContext(), 16))
+    func = fir::runtime::getRuntimeFunc<ForcedProductComplex16>(loc, builder);
+  else
+    fir::emitFatalError(loc, "invalid type in Product lowering");
+
+  auto fTy = func.getType();
+  auto sourceFile = fir::factory::locationToFilename(builder, loc);
+  if (fir::isa_complex(eleTy)) {
+    auto sourceLine =
+        fir::factory::locationToLineNo(builder, loc, fTy.getInput(3));
+    auto args =
+        fir::runtime::createArguments(builder, loc, fTy, resultBox, arrayBox,
+                                      sourceFile, sourceLine, dim, maskBox);
+    builder.create<fir::CallOp>(loc, func, args);
+    return resultBox;
+  }
+
+  auto sourceLine =
+      fir::factory::locationToLineNo(builder, loc, fTy.getInput(2));
+  auto args = fir::runtime::createArguments(
+      builder, loc, fTy, arrayBox, sourceFile, sourceLine, dim, maskBox);
+
+  return builder.create<fir::CallOp>(loc, func, args).getResult(0);
+}
+
+/// Generate call to `dot_product` intrinsic runtime routine.
+mlir::Value fir::runtime::genDotProduct(fir::FirOpBuilder &builder,
+                                        mlir::Location loc,
+                                        mlir::Value vectorABox,
+                                        mlir::Value vectorBBox,
+                                        mlir::Value resultBox) {
+  mlir::FuncOp func;
+  auto ty = vectorABox.getType();
+  auto arrTy = fir::dyn_cast_ptrOrBoxEleTy(ty);
+  auto eleTy = arrTy.cast<fir::SequenceType>().getEleTy();
+
+  if (eleTy.isF32())
+    func = fir::runtime::getRuntimeFunc<mkRTKey(DotProductReal4)>(loc, builder);
+  else if (eleTy.isF64())
+    func = fir::runtime::getRuntimeFunc<mkRTKey(DotProductReal8)>(loc, builder);
+  else if (eleTy.isF80())
+    func = fir::runtime::getRuntimeFunc<ForcedDotProductReal10>(loc, builder);
+  else if (eleTy.isF128())
+    func = fir::runtime::getRuntimeFunc<ForcedDotProductReal16>(loc, builder);
+  else if (eleTy == fir::ComplexType::get(builder.getContext(), 4))
+    func = fir::runtime::getRuntimeFunc<mkRTKey(CppDotProductComplex4)>(
+        loc, builder);
+  else if (eleTy == fir::ComplexType::get(builder.getContext(), 8))
+    func = fir::runtime::getRuntimeFunc<mkRTKey(CppDotProductComplex8)>(
+        loc, builder);
+  else if (eleTy == fir::ComplexType::get(builder.getContext(), 10))
+    func =
+        fir::runtime::getRuntimeFunc<ForcedDotProductComplex10>(loc, builder);
+  else if (eleTy == fir::ComplexType::get(builder.getContext(), 16))
+    func =
+        fir::runtime::getRuntimeFunc<ForcedDotProductComplex16>(loc, builder);
+  else if (eleTy ==
+           builder.getIntegerType(builder.getKindMap().getIntegerBitsize(1)))
+    func =
+        fir::runtime::getRuntimeFunc<mkRTKey(DotProductInteger1)>(loc, builder);
+  else if (eleTy ==
+           builder.getIntegerType(builder.getKindMap().getIntegerBitsize(2)))
+    func =
+        fir::runtime::getRuntimeFunc<mkRTKey(DotProductInteger2)>(loc, builder);
+  else if (eleTy ==
+           builder.getIntegerType(builder.getKindMap().getIntegerBitsize(4)))
+    func =
+        fir::runtime::getRuntimeFunc<mkRTKey(DotProductInteger4)>(loc, builder);
+  else if (eleTy ==
+           builder.getIntegerType(builder.getKindMap().getIntegerBitsize(8)))
+    func =
+        fir::runtime::getRuntimeFunc<mkRTKey(DotProductInteger8)>(loc, builder);
+  else if (eleTy ==
+           builder.getIntegerType(builder.getKindMap().getIntegerBitsize(16)))
+    func =
+        fir::runtime::getRuntimeFunc<ForcedDotProductInteger16>(loc, builder);
+  else if (eleTy.isa<fir::LogicalType>())
+    func =
+        fir::runtime::getRuntimeFunc<mkRTKey(DotProductLogical)>(loc, builder);
+  else
+    fir::emitFatalError(loc, "invalid type in DotProduct lowering");
+
+  auto fTy = func.getType();
+  auto sourceFile = fir::factory::locationToFilename(builder, loc);
+
+  if (fir::isa_complex(eleTy)) {
+    auto sourceLine =
+        fir::factory::locationToLineNo(builder, loc, fTy.getInput(4));
+    auto args =
+        fir::runtime::createArguments(builder, loc, fTy, resultBox, vectorABox,
+                                      vectorBBox, sourceFile, sourceLine);
+    builder.create<fir::CallOp>(loc, func, args);
+    return resultBox;
+  }
+
+  auto sourceLine =
+      fir::factory::locationToLineNo(builder, loc, fTy.getInput(3));
+  auto args = fir::runtime::createArguments(builder, loc, fTy, vectorABox,
+                                            vectorBBox, sourceFile, sourceLine);
+  return builder.create<fir::CallOp>(loc, func, args).getResult(0);
+}
+/// Generate call to Sum intrinsic runtime routine. This is the version
+/// that handles any rank array with the dim argument specified.
+void fir::runtime::genSumDim(fir::FirOpBuilder &builder, mlir::Location loc,
+                             mlir::Value resultBox, mlir::Value arrayBox,
+                             mlir::Value dim, mlir::Value maskBox) {
+  auto func = fir::runtime::getRuntimeFunc<mkRTKey(SumDim)>(loc, builder);
+  genReduction3Args(func, builder, loc, resultBox, arrayBox, dim, maskBox);
+}
+
+/// Generate call to `sum` intrinsic runtime routine. This is the version
+/// that does not take a dim argument.
+mlir::Value fir::runtime::genSum(fir::FirOpBuilder &builder, mlir::Location loc,
+                                 mlir::Value arrayBox, mlir::Value maskBox,
+                                 mlir::Value resultBox) {
+  mlir::FuncOp func;
+  auto arrTy = fir::dyn_cast_ptrOrBoxEleTy(arrayBox.getType());
+  auto eleTy = arrTy.cast<fir::SequenceType>().getEleTy();
+  auto dim = builder.createIntegerConstant(loc, builder.getIndexType(), 0);
+
+  if (eleTy.isF32())
+    func = fir::runtime::getRuntimeFunc<mkRTKey(SumReal4)>(loc, builder);
+  else if (eleTy.isF64())
+    func = fir::runtime::getRuntimeFunc<mkRTKey(SumReal8)>(loc, builder);
+  else if (eleTy.isF80())
+    func = fir::runtime::getRuntimeFunc<ForcedSumReal10>(loc, builder);
+  else if (eleTy.isF128())
+    func = fir::runtime::getRuntimeFunc<ForcedSumReal16>(loc, builder);
+  else if (eleTy ==
+           builder.getIntegerType(builder.getKindMap().getIntegerBitsize(1)))
+    func = fir::runtime::getRuntimeFunc<mkRTKey(SumInteger1)>(loc, builder);
+  else if (eleTy ==
+           builder.getIntegerType(builder.getKindMap().getIntegerBitsize(2)))
+    func = fir::runtime::getRuntimeFunc<mkRTKey(SumInteger2)>(loc, builder);
+  else if (eleTy ==
+           builder.getIntegerType(builder.getKindMap().getIntegerBitsize(4)))
+    func = fir::runtime::getRuntimeFunc<mkRTKey(SumInteger4)>(loc, builder);
+  else if (eleTy ==
+           builder.getIntegerType(builder.getKindMap().getIntegerBitsize(8)))
+    func = fir::runtime::getRuntimeFunc<mkRTKey(SumInteger8)>(loc, builder);
+  else if (eleTy ==
+           builder.getIntegerType(builder.getKindMap().getIntegerBitsize(16)))
+    func = fir::runtime::getRuntimeFunc<ForcedSumInteger16>(loc, builder);
+  else if (eleTy == fir::ComplexType::get(builder.getContext(), 4))
+    func = fir::runtime::getRuntimeFunc<mkRTKey(CppSumComplex4)>(loc, builder);
+  else if (eleTy == fir::ComplexType::get(builder.getContext(), 8))
+    func = fir::runtime::getRuntimeFunc<mkRTKey(CppSumComplex8)>(loc, builder);
+  else if (eleTy == fir::ComplexType::get(builder.getContext(), 10))
+    func = fir::runtime::getRuntimeFunc<ForcedSumComplex10>(loc, builder);
+  else if (eleTy == fir::ComplexType::get(builder.getContext(), 16))
+    func = fir::runtime::getRuntimeFunc<ForcedSumComplex16>(loc, builder);
+  else
+    fir::emitFatalError(loc, "invalid type in Sum lowering");
+
+  auto fTy = func.getType();
+  auto sourceFile = fir::factory::locationToFilename(builder, loc);
+  if (fir::isa_complex(eleTy)) {
+    auto sourceLine =
+        fir::factory::locationToLineNo(builder, loc, fTy.getInput(3));
+    auto args =
+        fir::runtime::createArguments(builder, loc, fTy, resultBox, arrayBox,
+                                      sourceFile, sourceLine, dim, maskBox);
+    builder.create<fir::CallOp>(loc, func, args);
+    return resultBox;
+  }
+
+  auto sourceLine =
+      fir::factory::locationToLineNo(builder, loc, fTy.getInput(2));
+  auto args = fir::runtime::createArguments(
+      builder, loc, fTy, arrayBox, sourceFile, sourceLine, dim, maskBox);
+
+  return builder.create<fir::CallOp>(loc, func, args).getResult(0);
+}
diff --git a/flang/unittests/Optimizer/Builder/Runtime/ReductionTest.cpp b/flang/unittests/Optimizer/Builder/Runtime/ReductionTest.cpp
new file mode 100644
index 0000000..b3be60d
--- /dev/null
+++ b/flang/unittests/Optimizer/Builder/Runtime/ReductionTest.cpp
@@ -0,0 +1,327 @@
+//===- ReductionTest.cpp -- Reduction runtime builder unit tests ----------===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+
+#include "flang/Optimizer/Builder/Runtime/Reduction.h"
+#include "RuntimeCallTestBase.h"
+#include "gtest/gtest.h"
+
+TEST_F(RuntimeCallTest, genAllTest) {
+  mlir::Location loc = firBuilder->getUnknownLoc();
+  mlir::Value undef = firBuilder->create<fir::UndefOp>(loc, seqTy10);
+  mlir::Value dim = firBuilder->createIntegerConstant(loc, i32Ty, 1);
+  mlir::Value all = fir::runtime::genAll(*firBuilder, loc, undef, dim);
+  checkCallOp(all.getDefiningOp(), "_FortranAAll", 2);
+}
+
+TEST_F(RuntimeCallTest, genAllDescriptorTest) {
+  mlir::Location loc = firBuilder->getUnknownLoc();
+  mlir::Value result = firBuilder->create<fir::UndefOp>(loc, seqTy10);
+  mlir::Value mask = firBuilder->create<fir::UndefOp>(loc, seqTy10);
+  mlir::Value dim = firBuilder->createIntegerConstant(loc, i32Ty, 1);
+  fir::runtime::genAllDescriptor(*firBuilder, loc, result, mask, dim);
+  checkCallOpFromResultBox(result, "_FortranAAllDim", 3);
+}
+
+TEST_F(RuntimeCallTest, genAnyTest) {
+  mlir::Location loc = firBuilder->getUnknownLoc();
+  mlir::Value undef = firBuilder->create<fir::UndefOp>(loc, seqTy10);
+  mlir::Value dim = firBuilder->createIntegerConstant(loc, i32Ty, 1);
+  mlir::Value any = fir::runtime::genAny(*firBuilder, loc, undef, dim);
+  checkCallOp(any.getDefiningOp(), "_FortranAAny", 2);
+}
+
+TEST_F(RuntimeCallTest, genAnyDescriptorTest) {
+  mlir::Location loc = firBuilder->getUnknownLoc();
+  mlir::Value result = firBuilder->create<fir::UndefOp>(loc, seqTy10);
+  mlir::Value mask = firBuilder->create<fir::UndefOp>(loc, seqTy10);
+  mlir::Value dim = firBuilder->createIntegerConstant(loc, i32Ty, 1);
+  fir::runtime::genAnyDescriptor(*firBuilder, loc, result, mask, dim);
+  checkCallOpFromResultBox(result, "_FortranAAnyDim", 3);
+}
+
+TEST_F(RuntimeCallTest, genCountTest) {
+  mlir::Location loc = firBuilder->getUnknownLoc();
+  mlir::Value undef = firBuilder->create<fir::UndefOp>(loc, seqTy10);
+  mlir::Value dim = firBuilder->createIntegerConstant(loc, i32Ty, 1);
+  mlir::Value count = fir::runtime::genCount(*firBuilder, loc, undef, dim);
+  checkCallOp(count.getDefiningOp(), "_FortranACount", 2);
+}
+
+TEST_F(RuntimeCallTest, genCountDimTest) {
+  mlir::Location loc = firBuilder->getUnknownLoc();
+  mlir::Value result = firBuilder->create<fir::UndefOp>(loc, seqTy10);
+  mlir::Value mask = firBuilder->create<fir::UndefOp>(loc, seqTy10);
+  mlir::Value dim = firBuilder->createIntegerConstant(loc, i32Ty, 1);
+  mlir::Value kind = firBuilder->createIntegerConstant(loc, i32Ty, 1);
+  fir::runtime::genCountDim(*firBuilder, loc, result, mask, dim, kind);
+  checkCallOpFromResultBox(result, "_FortranACountDim", 4);
+}
+
+void testGenMaxVal(
+    fir::FirOpBuilder &builder, mlir::Type eleTy, llvm::StringRef fctName) {
+  mlir::Location loc = builder.getUnknownLoc();
+  mlir::Type seqTy =
+      fir::SequenceType::get(fir::SequenceType::Shape(1, 10), eleTy);
+  mlir::Type refSeqTy = fir::ReferenceType::get(seqTy);
+  mlir::Value undef = builder.create<fir::UndefOp>(loc, refSeqTy);
+  mlir::Value mask = builder.create<fir::UndefOp>(loc, seqTy);
+  mlir::Value max = fir::runtime::genMaxval(builder, loc, undef, mask);
+  checkCallOp(max.getDefiningOp(), fctName, 3);
+}
+
+TEST_F(RuntimeCallTest, genMaxValTest) {
+  testGenMaxVal(*firBuilder, f32Ty, "_FortranAMaxvalReal4");
+  testGenMaxVal(*firBuilder, f64Ty, "_FortranAMaxvalReal8");
+  testGenMaxVal(*firBuilder, f80Ty, "_FortranAMaxvalReal10");
+  testGenMaxVal(*firBuilder, f128Ty, "_FortranAMaxvalReal16");
+
+  testGenMaxVal(*firBuilder, i8Ty, "_FortranAMaxvalInteger1");
+  testGenMaxVal(*firBuilder, i16Ty, "_FortranAMaxvalInteger2");
+  testGenMaxVal(*firBuilder, i32Ty, "_FortranAMaxvalInteger4");
+  testGenMaxVal(*firBuilder, i64Ty, "_FortranAMaxvalInteger8");
+  testGenMaxVal(*firBuilder, i128Ty, "_FortranAMaxvalInteger16");
+}
+
+void testGenMinVal(
+    fir::FirOpBuilder &builder, mlir::Type eleTy, llvm::StringRef fctName) {
+  mlir::Location loc = builder.getUnknownLoc();
+  mlir::Type seqTy =
+      fir::SequenceType::get(fir::SequenceType::Shape(1, 10), eleTy);
+  mlir::Type refSeqTy = fir::ReferenceType::get(seqTy);
+  mlir::Value undef = builder.create<fir::UndefOp>(loc, refSeqTy);
+  mlir::Value mask = builder.create<fir::UndefOp>(loc, seqTy);
+  mlir::Value min = fir::runtime::genMinval(builder, loc, undef, mask);
+  checkCallOp(min.getDefiningOp(), fctName, 3);
+}
+
+TEST_F(RuntimeCallTest, genMinValTest) {
+  testGenMinVal(*firBuilder, f32Ty, "_FortranAMinvalReal4");
+  testGenMinVal(*firBuilder, f64Ty, "_FortranAMinvalReal8");
+  testGenMinVal(*firBuilder, f80Ty, "_FortranAMinvalReal10");
+  testGenMinVal(*firBuilder, f128Ty, "_FortranAMinvalReal16");
+
+  testGenMinVal(*firBuilder, i8Ty, "_FortranAMinvalInteger1");
+  testGenMinVal(*firBuilder, i16Ty, "_FortranAMinvalInteger2");
+  testGenMinVal(*firBuilder, i32Ty, "_FortranAMinvalInteger4");
+  testGenMinVal(*firBuilder, i64Ty, "_FortranAMinvalInteger8");
+  testGenMinVal(*firBuilder, i128Ty, "_FortranAMinvalInteger16");
+}
+
+void testGenSum(
+    fir::FirOpBuilder &builder, mlir::Type eleTy, llvm::StringRef fctName) {
+  mlir::Location loc = builder.getUnknownLoc();
+  mlir::Type seqTy =
+      fir::SequenceType::get(fir::SequenceType::Shape(1, 10), eleTy);
+  mlir::Type refSeqTy = fir::ReferenceType::get(seqTy);
+  mlir::Value undef = builder.create<fir::UndefOp>(loc, refSeqTy);
+  mlir::Value mask = builder.create<fir::UndefOp>(loc, seqTy);
+  mlir::Value result = builder.create<fir::UndefOp>(loc, seqTy);
+  mlir::Value sum = fir::runtime::genSum(builder, loc, undef, mask, result);
+  if (fir::isa_complex(eleTy))
+    checkCallOpFromResultBox(result, fctName, 4);
+  else
+    checkCallOp(sum.getDefiningOp(), fctName, 3);
+}
+
+TEST_F(RuntimeCallTest, genSumTest) {
+  testGenSum(*firBuilder, f32Ty, "_FortranASumReal4");
+  testGenSum(*firBuilder, f64Ty, "_FortranASumReal8");
+  testGenSum(*firBuilder, f80Ty, "_FortranASumReal10");
+  testGenSum(*firBuilder, f128Ty, "_FortranASumReal16");
+  testGenSum(*firBuilder, i8Ty, "_FortranASumInteger1");
+  testGenSum(*firBuilder, i16Ty, "_FortranASumInteger2");
+  testGenSum(*firBuilder, i32Ty, "_FortranASumInteger4");
+  testGenSum(*firBuilder, i64Ty, "_FortranASumInteger8");
+  testGenSum(*firBuilder, i128Ty, "_FortranASumInteger16");
+  testGenSum(*firBuilder, c4Ty, "_FortranACppSumComplex4");
+  testGenSum(*firBuilder, c8Ty, "_FortranACppSumComplex8");
+  testGenSum(*firBuilder, c10Ty, "_FortranACppSumComplex10");
+  testGenSum(*firBuilder, c16Ty, "_FortranACppSumComplex16");
+}
+
+void testGenProduct(
+    fir::FirOpBuilder &builder, mlir::Type eleTy, llvm::StringRef fctName) {
+  mlir::Location loc = builder.getUnknownLoc();
+  mlir::Type seqTy =
+      fir::SequenceType::get(fir::SequenceType::Shape(1, 10), eleTy);
+  mlir::Type refSeqTy = fir::ReferenceType::get(seqTy);
+  mlir::Value undef = builder.create<fir::UndefOp>(loc, refSeqTy);
+  mlir::Value mask = builder.create<fir::UndefOp>(loc, seqTy);
+  mlir::Value result = builder.create<fir::UndefOp>(loc, seqTy);
+  mlir::Value prod =
+      fir::runtime::genProduct(builder, loc, undef, mask, result);
+  if (fir::isa_complex(eleTy))
+    checkCallOpFromResultBox(result, fctName, 4);
+  else
+    checkCallOp(prod.getDefiningOp(), fctName, 3);
+}
+
+TEST_F(RuntimeCallTest, genProduct) {
+  testGenProduct(*firBuilder, f32Ty, "_FortranAProductReal4");
+  testGenProduct(*firBuilder, f64Ty, "_FortranAProductReal8");
+  testGenProduct(*firBuilder, f80Ty, "_FortranAProductReal10");
+  testGenProduct(*firBuilder, f128Ty, "_FortranAProductReal16");
+  testGenProduct(*firBuilder, i8Ty, "_FortranAProductInteger1");
+  testGenProduct(*firBuilder, i16Ty, "_FortranAProductInteger2");
+  testGenProduct(*firBuilder, i32Ty, "_FortranAProductInteger4");
+  testGenProduct(*firBuilder, i64Ty, "_FortranAProductInteger8");
+  testGenProduct(*firBuilder, i128Ty, "_FortranAProductInteger16");
+  testGenProduct(*firBuilder, c4Ty, "_FortranACppProductComplex4");
+  testGenProduct(*firBuilder, c8Ty, "_FortranACppProductComplex8");
+  testGenProduct(*firBuilder, c10Ty, "_FortranACppProductComplex10");
+  testGenProduct(*firBuilder, c16Ty, "_FortranACppProductComplex16");
+}
+
+void testGenDotProduct(
+    fir::FirOpBuilder &builder, mlir::Type eleTy, llvm::StringRef fctName) {
+  mlir::Location loc = builder.getUnknownLoc();
+  mlir::Type seqTy =
+      fir::SequenceType::get(fir::SequenceType::Shape(1, 10), eleTy);
+  mlir::Type refSeqTy = fir::ReferenceType::get(seqTy);
+  mlir::Value a = builder.create<fir::UndefOp>(loc, refSeqTy);
+  mlir::Value b = builder.create<fir::UndefOp>(loc, refSeqTy);
+  mlir::Value result = builder.create<fir::UndefOp>(loc, seqTy);
+  mlir::Value prod = fir::runtime::genDotProduct(builder, loc, a, b, result);
+  if (fir::isa_complex(eleTy))
+    checkCallOpFromResultBox(result, fctName, 3);
+  else
+    checkCallOp(prod.getDefiningOp(), fctName, 2);
+}
+
+TEST_F(RuntimeCallTest, genDotProduct) {
+  testGenDotProduct(*firBuilder, f32Ty, "_FortranADotProductReal4");
+  testGenDotProduct(*firBuilder, f64Ty, "_FortranADotProductReal8");
+  testGenDotProduct(*firBuilder, f80Ty, "_FortranADotProductReal10");
+  testGenDotProduct(*firBuilder, f128Ty, "_FortranADotProductReal16");
+  testGenDotProduct(*firBuilder, i8Ty, "_FortranADotProductInteger1");
+  testGenDotProduct(*firBuilder, i16Ty, "_FortranADotProductInteger2");
+  testGenDotProduct(*firBuilder, i32Ty, "_FortranADotProductInteger4");
+  testGenDotProduct(*firBuilder, i64Ty, "_FortranADotProductInteger8");
+  testGenDotProduct(*firBuilder, i128Ty, "_FortranADotProductInteger16");
+  testGenDotProduct(*firBuilder, c4Ty, "_FortranACppDotProductComplex4");
+  testGenDotProduct(*firBuilder, c8Ty, "_FortranACppDotProductComplex8");
+  testGenDotProduct(*firBuilder, c10Ty, "_FortranACppDotProductComplex10");
+  testGenDotProduct(*firBuilder, c16Ty, "_FortranACppDotProductComplex16");
+}
+
+void checkGenMxxloc(fir::FirOpBuilder &builder,
+    void (*genFct)(fir::FirOpBuilder &, Location, mlir::Value, mlir::Value,
+        mlir::Value, mlir::Value, mlir::Value),
+    llvm::StringRef fctName, unsigned nbArgs) {
+  mlir::Location loc = builder.getUnknownLoc();
+  mlir::Type i32Ty = builder.getI32Type();
+  mlir::Type seqTy =
+      fir::SequenceType::get(fir::SequenceType::Shape(1, 10), i32Ty);
+  mlir::Type refSeqTy = fir::ReferenceType::get(seqTy);
+  mlir::Value a = builder.create<fir::UndefOp>(loc, refSeqTy);
+  mlir::Value result = builder.create<fir::UndefOp>(loc, seqTy);
+  mlir::Value mask = builder.create<fir::UndefOp>(loc, seqTy);
+  mlir::Value kind = builder.createIntegerConstant(loc, i32Ty, 1);
+  mlir::Value back = builder.createIntegerConstant(loc, i32Ty, 1);
+  genFct(builder, loc, result, a, mask, kind, back);
+  checkCallOpFromResultBox(result, fctName, nbArgs);
+}
+
+TEST_F(RuntimeCallTest, genMaxlocTest) {
+  checkGenMxxloc(*firBuilder, fir::runtime::genMaxloc, "_FortranAMaxloc", 5);
+}
+
+TEST_F(RuntimeCallTest, genMinlocTest) {
+  checkGenMxxloc(*firBuilder, fir::runtime::genMinloc, "_FortranAMinloc", 5);
+}
+
+void checkGenMxxlocDim(fir::FirOpBuilder &builder,
+    void (*genFct)(fir::FirOpBuilder &, Location, mlir::Value, mlir::Value,
+        mlir::Value, mlir::Value, mlir::Value, mlir::Value),
+    llvm::StringRef fctName, unsigned nbArgs) {
+  mlir::Location loc = builder.getUnknownLoc();
+  auto i32Ty = builder.getI32Type();
+  mlir::Type seqTy =
+      fir::SequenceType::get(fir::SequenceType::Shape(1, 10), i32Ty);
+  mlir::Type refSeqTy = fir::ReferenceType::get(seqTy);
+  mlir::Value a = builder.create<fir::UndefOp>(loc, refSeqTy);
+  mlir::Value result = builder.create<fir::UndefOp>(loc, seqTy);
+  mlir::Value mask = builder.create<fir::UndefOp>(loc, seqTy);
+  mlir::Value kind = builder.createIntegerConstant(loc, i32Ty, 1);
+  mlir::Value dim = builder.createIntegerConstant(loc, i32Ty, 1);
+  mlir::Value back = builder.createIntegerConstant(loc, i32Ty, 1);
+  genFct(builder, loc, result, a, dim, mask, kind, back);
+  checkCallOpFromResultBox(result, fctName, nbArgs);
+}
+
+TEST_F(RuntimeCallTest, genMaxlocDimTest) {
+  checkGenMxxlocDim(
+      *firBuilder, fir::runtime::genMaxlocDim, "_FortranAMaxlocDim", 6);
+}
+
+TEST_F(RuntimeCallTest, genMinlocDimTest) {
+  checkGenMxxlocDim(
+      *firBuilder, fir::runtime::genMinlocDim, "_FortranAMinlocDim", 6);
+}
+
+void checkGenMxxvalChar(fir::FirOpBuilder &builder,
+    void (*genFct)(
+        fir::FirOpBuilder &, Location, mlir::Value, mlir::Value, mlir::Value),
+    llvm::StringRef fctName, unsigned nbArgs) {
+  mlir::Location loc = builder.getUnknownLoc();
+  auto i32Ty = builder.getI32Type();
+  mlir::Type seqTy =
+      fir::SequenceType::get(fir::SequenceType::Shape(1, 10), i32Ty);
+  mlir::Type refSeqTy = fir::ReferenceType::get(seqTy);
+  mlir::Value a = builder.create<fir::UndefOp>(loc, refSeqTy);
+  mlir::Value result = builder.create<fir::UndefOp>(loc, seqTy);
+  mlir::Value mask = builder.create<fir::UndefOp>(loc, seqTy);
+  genFct(builder, loc, result, a, mask);
+  checkCallOpFromResultBox(result, fctName, nbArgs);
+}
+
+TEST_F(RuntimeCallTest, genMaxvalCharTest) {
+  checkGenMxxvalChar(
+      *firBuilder, fir::runtime::genMaxvalChar, "_FortranAMaxvalCharacter", 3);
+}
+
+TEST_F(RuntimeCallTest, genMinvalCharTest) {
+  checkGenMxxvalChar(
+      *firBuilder, fir::runtime::genMinvalChar, "_FortranAMinvalCharacter", 3);
+}
+
+void checkGen4argsDim(fir::FirOpBuilder &builder,
+    void (*genFct)(fir::FirOpBuilder &, Location, mlir::Value, mlir::Value,
+        mlir::Value, mlir::Value),
+    llvm::StringRef fctName, unsigned nbArgs) {
+  mlir::Location loc = builder.getUnknownLoc();
+  auto i32Ty = builder.getI32Type();
+  mlir::Type seqTy =
+      fir::SequenceType::get(fir::SequenceType::Shape(1, 10), i32Ty);
+  mlir::Type refSeqTy = fir::ReferenceType::get(seqTy);
+  mlir::Value a = builder.create<fir::UndefOp>(loc, refSeqTy);
+  mlir::Value result = builder.create<fir::UndefOp>(loc, seqTy);
+  mlir::Value mask = builder.create<fir::UndefOp>(loc, seqTy);
+  mlir::Value dim = builder.createIntegerConstant(loc, i32Ty, 1);
+  genFct(builder, loc, result, a, dim, mask);
+  checkCallOpFromResultBox(result, fctName, nbArgs);
+}
+
+TEST_F(RuntimeCallTest, genMaxvalDimTest) {
+  checkGen4argsDim(
+      *firBuilder, fir::runtime::genMaxvalDim, "_FortranAMaxvalDim", 4);
+}
+
+TEST_F(RuntimeCallTest, genMinvalDimTest) {
+  checkGen4argsDim(
+      *firBuilder, fir::runtime::genMinvalDim, "_FortranAMinvalDim", 4);
+}
+
+TEST_F(RuntimeCallTest, genProductDimTest) {
+  checkGen4argsDim(
+      *firBuilder, fir::runtime::genProductDim, "_FortranAProductDim", 4);
+}
+
+TEST_F(RuntimeCallTest, genSumDimTest) {
+  checkGen4argsDim(*firBuilder, fir::runtime::genSumDim, "_FortranASumDim", 4);
+}
diff --git a/flang/unittests/Optimizer/Builder/Runtime/RuntimeCallTestBase.h b/flang/unittests/Optimizer/Builder/Runtime/RuntimeCallTestBase.h
index 0605fd1..728313d 100644
--- a/flang/unittests/Optimizer/Builder/Runtime/RuntimeCallTestBase.h
+++ b/flang/unittests/Optimizer/Builder/Runtime/RuntimeCallTestBase.h
@@ -48,6 +48,8 @@
     c8Ty = fir::ComplexType::get(firBuilder->getContext(), 8);
     c10Ty = fir::ComplexType::get(firBuilder->getContext(), 10);
     c16Ty = fir::ComplexType::get(firBuilder->getContext(), 16);
+
+    seqTy10 = fir::SequenceType::get(fir::SequenceType::Shape(1, 10), i32Ty);
   }
 
   mlir::MLIRContext context;
@@ -68,6 +70,7 @@
   mlir::Type c8Ty;
   mlir::Type c10Ty;
   mlir::Type c16Ty;
+  mlir::Type seqTy10;
 };
 
 /// Check that the \p op is a `fir::CallOp` operation and its name matches
diff --git a/flang/unittests/Optimizer/CMakeLists.txt b/flang/unittests/Optimizer/CMakeLists.txt
index 81983c2..1ade44c 100644
--- a/flang/unittests/Optimizer/CMakeLists.txt
+++ b/flang/unittests/Optimizer/CMakeLists.txt
@@ -14,6 +14,7 @@
   Builder/DoLoopHelperTest.cpp
   Builder/FIRBuilderTest.cpp
   Builder/Runtime/AssignTest.cpp
+  Builder/Runtime/ReductionTest.cpp
   Builder/Runtime/TransformationalTest.cpp
   FIRContextTest.cpp
   InternalNamesTest.cpp