[flang] Added fir.is_contiguous_box and fir.box_total_elements ops.

flang/include/flang/Optimizer/Builder/Runtime/Inquiry.h

@@ -50,9 +50,15 @@ mlir::Value genSize(fir::FirOpBuilder &builder, mlir::Location loc,
 mlir::Value genSizeDim(fir::FirOpBuilder &builder, mlir::Location loc,
                        mlir::Value array, mlir::Value dim);
 
-/// Generate call to `Is_contiguous` runtime routine.
+/// Generate call to `IsContiguous` runtime routine.
 mlir::Value genIsContiguous(fir::FirOpBuilder &builder, mlir::Location loc,
                             mlir::Value array);
 
+/// Generate call to `IsContiguousUpTo` runtime routine.
+/// \p dim specifies the dimension up to which contiguity
+/// needs to be checked (not exceeding the actual rank of the array).
+mlir::Value genIsContiguousUpTo(fir::FirOpBuilder &builder, mlir::Location loc,
+                                mlir::Value array, mlir::Value dim);
+
 } // namespace fir::runtime
 #endif // FORTRAN_OPTIMIZER_BUILDER_RUNTIME_INQUIRY_H

flang/include/flang/Optimizer/Dialect/FIROps.td

@@ -3416,4 +3416,28 @@ def fir_UnpackArrayOp
   let hasVerifier = 1;
 }
 
+def fir_IsContiguousBoxOp : fir_Op<"is_contiguous_box", [NoMemoryEffect]> {
+  let summary = "Returns true if the boxed entity is contiguous";
+  let description = [{
+    Returns true iff the boxed entity is contiguous:
+      * in the leading dimension (if `innermost` attribute is set),
+      * in all dimensions (if `innermost` attribute is not set).
+  }];
+  let arguments = (ins AnyBoxLike:$box, UnitAttr:$innermost);
+  let results = (outs I1);
+
+  let assemblyFormat = [{
+    $box (`innermost` $innermost^):(`whole`)? attr-dict `:` functional-type(operands, results)
+  }];
+  let hasCanonicalizer = 1;
+}
+
+def fir_BoxTotalElementsOp
+    : fir_SimpleOneResultOp<"box_total_elements", [NoMemoryEffect]> {
+  let summary = "Returns the boxed entity's total size in elements";
+  let arguments = (ins AnyBoxLike:$box);
+  let results = (outs AnyIntegerLike);
+  let hasCanonicalizer = 1;
+}
+
 #endif

flang/include/flang/Optimizer/Transforms/Passes.h

@@ -62,6 +62,7 @@ namespace fir {
 #define GEN_PASS_DECL_COMPILERGENERATEDNAMESCONVERSION
 #define GEN_PASS_DECL_SETRUNTIMECALLATTRIBUTES
 #define GEN_PASS_DECL_GENRUNTIMECALLSFORTEST
+#define GEN_PASS_DECL_SIMPLIFYFIROPERATIONS
 
 #include "flang/Optimizer/Transforms/Passes.h.inc"
 
@@ -86,6 +87,9 @@ void populateCfgConversionRewrites(mlir::RewritePatternSet &patterns,
                                    bool forceLoopToExecuteOnce = false,
                                    bool setNSW = true);
 
+void populateSimplifyFIROperationsPatterns(mlir::RewritePatternSet &patterns,
+                                           bool preferInlineImplementation);
+
 // declarative passes
 #define GEN_PASS_REGISTRATION
 #include "flang/Optimizer/Transforms/Passes.h.inc"

flang/include/flang/Optimizer/Transforms/Passes.td

@@ -486,4 +486,18 @@ def GenRuntimeCallsForTest
   let dependentDialects = ["fir::FIROpsDialect", "mlir::func::FuncDialect"];
 }
 
+def SimplifyFIROperations : Pass<"simplify-fir-operations", "mlir::ModuleOp"> {
+  let summary = "Simplifies complex FIR operations";
+  let description = [{
+    Expands complex FIR operations into their equivalent using
+    FIR, SCF and other usual dialects. It may also generate calls
+    to Fortran runtime.
+  }];
+
+  let options = [Option<
+      "preferInlineImplementation", "prefer-inline-implementation", "bool",
+      /*default=*/"false",
+      "Prefer expanding without using Fortran runtime calls.">];
+}
+
 #endif // FLANG_OPTIMIZER_TRANSFORMS_PASSES

flang/include/flang/Runtime/support.h

@@ -34,6 +34,10 @@ extern "C" {
 // Predicate: is the storage described by a Descriptor contiguous in memory?
 bool RTDECL(IsContiguous)(const Descriptor &);
 
+// Predicate: is the storage described by a Descriptor contiguous in memory
+// up to the given dimension?
+bool RTDECL(IsContiguousUpTo)(const Descriptor &, char);
+
 // Predicate: is this descriptor describing an assumed-size array?
 bool RTDECL(IsAssumedSize)(const Descriptor &);
 

flang/lib/Optimizer/Builder/Runtime/Inquiry.cpp

@@ -91,7 +91,7 @@ mlir::Value fir::runtime::genSize(fir::FirOpBuilder &builder,
   return builder.create<fir::CallOp>(loc, sizeFunc, args).getResult(0);
 }
 
-/// Generate call to `Is_contiguous` runtime routine.
+/// Generate call to `IsContiguous` runtime routine.
 mlir::Value fir::runtime::genIsContiguous(fir::FirOpBuilder &builder,
                                           mlir::Location loc,
                                           mlir::Value array) {
@@ -102,6 +102,18 @@ mlir::Value fir::runtime::genIsContiguous(fir::FirOpBuilder &builder,
   return builder.create<fir::CallOp>(loc, isContiguousFunc, args).getResult(0);
 }
 
+/// Generate call to `IsContiguousUpTo` runtime routine.
+mlir::Value fir::runtime::genIsContiguousUpTo(fir::FirOpBuilder &builder,
+                                              mlir::Location loc,
+                                              mlir::Value array,
+                                              mlir::Value dim) {
+  mlir::func::FuncOp isContiguousFunc =
+      fir::runtime::getRuntimeFunc<mkRTKey(IsContiguousUpTo)>(loc, builder);
+  auto fTy = isContiguousFunc.getFunctionType();
+  auto args = fir::runtime::createArguments(builder, loc, fTy, array, dim);
+  return builder.create<fir::CallOp>(loc, isContiguousFunc, args).getResult(0);
+}
+
 void fir::runtime::genShape(fir::FirOpBuilder &builder, mlir::Location loc,
                             mlir::Value resultAddr, mlir::Value array,
                             mlir::Value kind) {

flang/lib/Optimizer/Dialect/FIROps.cpp

@@ -4671,6 +4671,79 @@ void fir::UnpackArrayOp::getEffects(
                          mlir::SideEffects::DefaultResource::get());
 }
 
+//===----------------------------------------------------------------------===//
+// IsContiguousBoxOp
+//===----------------------------------------------------------------------===//
+
+namespace {
+struct SimplifyIsContiguousBoxOp
+    : public mlir::OpRewritePattern<fir::IsContiguousBoxOp> {
+  using mlir::OpRewritePattern<fir::IsContiguousBoxOp>::OpRewritePattern;
+  mlir::LogicalResult
+  matchAndRewrite(fir::IsContiguousBoxOp op,
+                  mlir::PatternRewriter &rewriter) const override;
+};
+} // namespace
+
+mlir::LogicalResult SimplifyIsContiguousBoxOp::matchAndRewrite(
+    fir::IsContiguousBoxOp op, mlir::PatternRewriter &rewriter) const {
+  auto boxType = mlir::cast<fir::BaseBoxType>(op.getBox().getType());
+  // Nothing to do for assumed-rank arrays and !fir.box<none>.
+  if (boxType.isAssumedRank() || fir::isBoxNone(boxType))
+    return mlir::failure();
+
+  if (fir::getBoxRank(boxType) == 0) {
+    // Scalars are always contiguous.
+    mlir::Type i1Type = rewriter.getI1Type();
+    rewriter.replaceOpWithNewOp<mlir::arith::ConstantOp>(
+        op, i1Type, rewriter.getIntegerAttr(i1Type, 1));
+    return mlir::success();
+  }
+
+  return mlir::failure();
+}
+
+void fir::IsContiguousBoxOp::getCanonicalizationPatterns(
+    mlir::RewritePatternSet &patterns, mlir::MLIRContext *context) {
+  patterns.add<SimplifyIsContiguousBoxOp>(context);
+}
+
+//===----------------------------------------------------------------------===//
+// BoxTotalElementsOp
+//===----------------------------------------------------------------------===//
+
+namespace {
+struct SimplifyBoxTotalElementsOp
+    : public mlir::OpRewritePattern<fir::BoxTotalElementsOp> {
+  using mlir::OpRewritePattern<fir::BoxTotalElementsOp>::OpRewritePattern;
+  mlir::LogicalResult
+  matchAndRewrite(fir::BoxTotalElementsOp op,
+                  mlir::PatternRewriter &rewriter) const override;
+};
+} // namespace
+
+mlir::LogicalResult SimplifyBoxTotalElementsOp::matchAndRewrite(
+    fir::BoxTotalElementsOp op, mlir::PatternRewriter &rewriter) const {
+  auto boxType = mlir::cast<fir::BaseBoxType>(op.getBox().getType());
+  // Nothing to do for assumed-rank arrays and !fir.box<none>.
+  if (boxType.isAssumedRank() || fir::isBoxNone(boxType))
+    return mlir::failure();
+
+  if (fir::getBoxRank(boxType) == 0) {
+    // Scalar: 1 element.
+    rewriter.replaceOpWithNewOp<mlir::arith::ConstantOp>(
+        op, op.getType(), rewriter.getIntegerAttr(op.getType(), 1));
+    return mlir::success();
+  }
+
+  return mlir::failure();
+}
+
+void fir::BoxTotalElementsOp::getCanonicalizationPatterns(
+    mlir::RewritePatternSet &patterns, mlir::MLIRContext *context) {
+  patterns.add<SimplifyBoxTotalElementsOp>(context);
+}
+
 //===----------------------------------------------------------------------===//
 // FIROpsDialect
 //===----------------------------------------------------------------------===//

flang/lib/Optimizer/Passes/Pipelines.cpp

@@ -198,6 +198,11 @@ void createDefaultFIROptimizerPassPipeline(mlir::PassManager &pm,
   pm.addPass(fir::createPolymorphicOpConversion());
   pm.addPass(fir::createAssumedRankOpConversion());
 
+  // Expand FIR operations that may use SCF dialect for their
+  // implementation. This is a mandatory pass.
+  pm.addPass(fir::createSimplifyFIROperations(
+      {/*preferInlineImplementation=*/pc.OptLevel.isOptimizingForSpeed()}));
+
   if (pc.AliasAnalysis && !disableFirAliasTags && !useOldAliasTags)
     pm.addPass(fir::createAddAliasTags());
 

flang/lib/Optimizer/Transforms/CMakeLists.txt

@@ -31,6 +31,7 @@ add_flang_library(FIRTransforms
   DebugTypeGenerator.cpp
   SetRuntimeCallAttributes.cpp
   GenRuntimeCallsForTest.cpp
+  SimplifyFIROperations.cpp
 
   DEPENDS
   CUFAttrs

flang/lib/Optimizer/Transforms/SimplifyFIROperations.cpp

@@ -0,0 +1,157 @@
+//===- SimplifyFIROperations.cpp -- simplify complex FIR operations  ------===//
+//
+// 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
+//
+//===----------------------------------------------------------------------===//
+
+//===----------------------------------------------------------------------===//
+/// \file
+/// This pass transforms some FIR operations into their equivalent
+/// implementations using other FIR operations. The transformation
+/// can legally use SCF dialect and generate Fortran runtime calls.
+//===----------------------------------------------------------------------===//
+
+#include "flang/Optimizer/Builder/BoxValue.h"
+#include "flang/Optimizer/Builder/CUFCommon.h"
+#include "flang/Optimizer/Builder/FIRBuilder.h"
+#include "flang/Optimizer/Builder/LowLevelIntrinsics.h"
+#include "flang/Optimizer/Builder/Todo.h"
+#include "flang/Optimizer/Dialect/FIROps.h"
+#include "flang/Optimizer/Dialect/FIRType.h"
+#include "flang/Optimizer/Dialect/Support/FIRContext.h"
+#include "flang/Optimizer/HLFIR/HLFIRDialect.h"
+#include "flang/Optimizer/Transforms/Passes.h"
+#include "flang/Optimizer/Transforms/Utils.h"
+#include "flang/Runtime/entry-names.h"
+#include "flang/Support/Fortran.h"
+#include "mlir/IR/Matchers.h"
+#include "mlir/IR/Operation.h"
+#include "mlir/Pass/Pass.h"
+#include "mlir/Transforms/DialectConversion.h"
+
+#include "flang/Optimizer/Builder/Runtime/Inquiry.h"
+
+namespace fir {
+#define GEN_PASS_DEF_SIMPLIFYFIROPERATIONS
+#include "flang/Optimizer/Transforms/Passes.h.inc"
+} // namespace fir
+
+#define DEBUG_TYPE "flang-simplify-fir-operations"
+
+namespace {
+/// Pass runner.
+class SimplifyFIROperationsPass
+    : public fir::impl::SimplifyFIROperationsBase<SimplifyFIROperationsPass> {
+public:
+  using fir::impl::SimplifyFIROperationsBase<
+      SimplifyFIROperationsPass>::SimplifyFIROperationsBase;
+
+  void runOnOperation() override final;
+};
+
+/// Base class for all conversions holding the pass options.
+template <typename Op>
+class ConversionBase : public mlir::OpRewritePattern<Op> {
+public:
+  using mlir::OpRewritePattern<Op>::OpRewritePattern;
+
+  template <typename... Args>
+  ConversionBase(mlir::MLIRContext *context, Args &&...args)
+      : mlir::OpRewritePattern<Op>(context),
+        options{std::forward<Args>(args)...} {}
+
+  mlir::LogicalResult matchAndRewrite(Op,
+                                      mlir::PatternRewriter &) const override;
+
+protected:
+  fir::SimplifyFIROperationsOptions options;
+};
+
+/// fir::IsContiguousBoxOp converter.
+using IsContiguousBoxCoversion = ConversionBase<fir::IsContiguousBoxOp>;
+
+/// fir::BoxTotalElementsOp converter.
+using BoxTotalElementsConversion = ConversionBase<fir::BoxTotalElementsOp>;
+} // namespace
+
+/// Generate a call to IsContiguous/IsContiguousUpTo function or an inline
+/// sequence reading extents/strides from the box and checking them.
+/// This conversion may produce fir.box_elesize and a loop (for assumed
+/// rank).
+template <>
+mlir::LogicalResult IsContiguousBoxCoversion::matchAndRewrite(
+    fir::IsContiguousBoxOp op, mlir::PatternRewriter &rewriter) const {
+  mlir::Location loc = op.getLoc();
+  fir::FirOpBuilder builder(rewriter, op.getOperation());
+  // TODO: support preferInlineImplementation.
+  bool doInline = options.preferInlineImplementation && false;
+  if (!doInline) {
+    // Generate Fortran runtime call.
+    mlir::Value result;
+    if (op.getInnermost()) {
+      mlir::Value one =
+          builder.createIntegerConstant(loc, builder.getI8Type(), 1);
+      result =
+          fir::runtime::genIsContiguousUpTo(builder, loc, op.getBox(), one);
+    } else {
+      result = fir::runtime::genIsContiguous(builder, loc, op.getBox());
+    }
+    result = builder.createConvert(loc, op.getType(), result);
+    rewriter.replaceOp(op, result);
+    return mlir::success();
+  }
+
+  // Generate inline implementation.
+  TODO(loc, "inline IsContiguousBoxOp");
+  return mlir::success();
+}
+
+/// Generate a call to Size runtime function or an inline
+/// sequence reading extents from the box an multiplying them.
+/// This conversion may produce a loop (for assumed rank).
+template <>
+mlir::LogicalResult BoxTotalElementsConversion::matchAndRewrite(
+    fir::BoxTotalElementsOp op, mlir::PatternRewriter &rewriter) const {
+  mlir::Location loc = op.getLoc();
+  fir::FirOpBuilder builder(rewriter, op.getOperation());
+  // TODO: support preferInlineImplementation.
+  // Reading the extent from the box for 1D arrays probably
+  // results in less code than the call, so we can always
+  // inline it.
+  bool doInline = options.preferInlineImplementation && false;
+  if (!doInline) {
+    // Generate Fortran runtime call.
+    mlir::Value result = fir::runtime::genSize(builder, loc, op.getBox());
+    result = builder.createConvert(loc, op.getType(), result);
+    rewriter.replaceOp(op, result);
+    return mlir::success();
+  }
+
+  // Generate inline implementation.
+  TODO(loc, "inline BoxTotalElementsOp");
+  return mlir::success();
+}
+
+void SimplifyFIROperationsPass::runOnOperation() {
+  mlir::ModuleOp module = getOperation();
+  mlir::MLIRContext &context = getContext();
+  mlir::ConversionTarget target(context);
+  target.addIllegalOp<fir::IsContiguousBoxOp>();
+  target.addIllegalOp<fir::BoxTotalElementsOp>();
+  mlir::RewritePatternSet patterns(&context);
+  fir::populateSimplifyFIROperationsPatterns(patterns,
+                                             preferInlineImplementation);
+  if (mlir::failed(
+          mlir::applyPartialConversion(module, target, std::move(patterns)))) {
+    mlir::emitError(module.getLoc(), DEBUG_TYPE " pass failed");
+    signalPassFailure();
+  }
+}
+
+void fir::populateSimplifyFIROperationsPatterns(
+    mlir::RewritePatternSet &patterns, bool preferInlineImplementation) {
+  patterns.insert<IsContiguousBoxCoversion, BoxTotalElementsConversion>(
+      patterns.getContext(), preferInlineImplementation);
+}

flang/test/Driver/bbc-mlir-pass-pipeline.f90

@@ -47,6 +47,7 @@
 
 ! CHECK-NEXT: PolymorphicOpConversion
 ! CHECK-NEXT: AssumedRankOpConversion
+! CHECK-NEXT: SimplifyFIROperations
 
 ! CHECK-NEXT: Pipeline Collection : ['fir.global', 'func.func', 'omp.declare_reduction', 'omp.private']
 ! CHECK-NEXT: 'fir.global' Pipeline

flang/test/Driver/mlir-debug-pass-pipeline.f90

@@ -77,6 +77,7 @@
 
 ! ALL-NEXT: PolymorphicOpConversion
 ! ALL-NEXT: AssumedRankOpConversion
+! ALL-NEXT: SimplifyFIROperations
 
 ! ALL-NEXT: Pipeline Collection : ['fir.global', 'func.func', 'omp.declare_reduction', 'omp.private']
 ! ALL-NEXT:   'fir.global' Pipeline