//===- StandardToLLVM.cpp - Standard to LLVM dialect conversion -----------===//
//
// 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
//
//===----------------------------------------------------------------------===//
//
// This file implements a pass to convert MLIR standard and builtin dialects
// into the LLVM IR dialect.
//
//===----------------------------------------------------------------------===//

#include "../PassDetail.h"
#include "mlir/Analysis/DataLayoutAnalysis.h"
#include "mlir/Conversion/LLVMCommon/ConversionTarget.h"
#include "mlir/Conversion/LLVMCommon/Pattern.h"
#include "mlir/Conversion/LLVMCommon/VectorPattern.h"
#include "mlir/Conversion/StandardToLLVM/ConvertStandardToLLVM.h"
#include "mlir/Conversion/StandardToLLVM/ConvertStandardToLLVMPass.h"
#include "mlir/Dialect/LLVMIR/FunctionCallUtils.h"
#include "mlir/Dialect/LLVMIR/LLVMDialect.h"
#include "mlir/Dialect/Math/IR/Math.h"
#include "mlir/Dialect/StandardOps/IR/Ops.h"
#include "mlir/Dialect/Utils/StaticValueUtils.h"
#include "mlir/IR/Attributes.h"
#include "mlir/IR/BlockAndValueMapping.h"
#include "mlir/IR/Builders.h"
#include "mlir/IR/BuiltinOps.h"
#include "mlir/IR/MLIRContext.h"
#include "mlir/IR/PatternMatch.h"
#include "mlir/IR/TypeUtilities.h"
#include "mlir/Support/LogicalResult.h"
#include "mlir/Support/MathExtras.h"
#include "mlir/Transforms/DialectConversion.h"
#include "mlir/Transforms/Passes.h"
#include "mlir/Transforms/Utils.h"
#include "llvm/ADT/TypeSwitch.h"
#include "llvm/IR/DerivedTypes.h"
#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/Type.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/FormatVariadic.h"
#include <functional>

using namespace mlir;

#define PASS_NAME "convert-std-to-llvm"

/// Only retain those attributes that are not constructed by
/// `LLVMFuncOp::build`. If `filterArgAttrs` is set, also filter out argument
/// attributes.
static void filterFuncAttributes(ArrayRef<NamedAttribute> attrs,
                                 bool filterArgAttrs,
                                 SmallVectorImpl<NamedAttribute> &result) {
  for (const auto &attr : attrs) {
    if (attr.first == SymbolTable::getSymbolAttrName() ||
        attr.first == function_like_impl::getTypeAttrName() ||
        attr.first == "std.varargs" ||
        (filterArgAttrs &&
         attr.first == function_like_impl::getArgDictAttrName()))
      continue;
    result.push_back(attr);
  }
}

/// Creates an auxiliary function with pointer-to-memref-descriptor-struct
/// arguments instead of unpacked arguments. This function can be called from C
/// by passing a pointer to a C struct corresponding to a memref descriptor.
/// Similarly, returned memrefs are passed via pointers to a C struct that is
/// passed as additional argument.
/// Internally, the auxiliary function unpacks the descriptor into individual
/// components and forwards them to `newFuncOp` and forwards the results to
/// the extra arguments.
static void wrapForExternalCallers(OpBuilder &rewriter, Location loc,
                                   LLVMTypeConverter &typeConverter,
                                   FuncOp funcOp, LLVM::LLVMFuncOp newFuncOp) {
  auto type = funcOp.getType();
  SmallVector<NamedAttribute, 4> attributes;
  filterFuncAttributes(funcOp->getAttrs(), /*filterArgAttrs=*/false,
                       attributes);
  Type wrapperFuncType;
  bool resultIsNowArg;
  std::tie(wrapperFuncType, resultIsNowArg) =
      typeConverter.convertFunctionTypeCWrapper(type);
  auto wrapperFuncOp = rewriter.create<LLVM::LLVMFuncOp>(
      loc, llvm::formatv("_mlir_ciface_{0}", funcOp.getName()).str(),
      wrapperFuncType, LLVM::Linkage::External, /*dsoLocal*/ false, attributes);

  OpBuilder::InsertionGuard guard(rewriter);
  rewriter.setInsertionPointToStart(wrapperFuncOp.addEntryBlock());

  SmallVector<Value, 8> args;
  size_t argOffset = resultIsNowArg ? 1 : 0;
  for (auto &en : llvm::enumerate(type.getInputs())) {
    Value arg = wrapperFuncOp.getArgument(en.index() + argOffset);
    if (auto memrefType = en.value().dyn_cast<MemRefType>()) {
      Value loaded = rewriter.create<LLVM::LoadOp>(loc, arg);
      MemRefDescriptor::unpack(rewriter, loc, loaded, memrefType, args);
      continue;
    }
    if (en.value().isa<UnrankedMemRefType>()) {
      Value loaded = rewriter.create<LLVM::LoadOp>(loc, arg);
      UnrankedMemRefDescriptor::unpack(rewriter, loc, loaded, args);
      continue;
    }

    args.push_back(arg);
  }

  auto call = rewriter.create<LLVM::CallOp>(loc, newFuncOp, args);

  if (resultIsNowArg) {
    rewriter.create<LLVM::StoreOp>(loc, call.getResult(0),
                                   wrapperFuncOp.getArgument(0));
    rewriter.create<LLVM::ReturnOp>(loc, ValueRange{});
  } else {
    rewriter.create<LLVM::ReturnOp>(loc, call.getResults());
  }
}

/// Creates an auxiliary function with pointer-to-memref-descriptor-struct
/// arguments instead of unpacked arguments. Creates a body for the (external)
/// `newFuncOp` that allocates a memref descriptor on stack, packs the
/// individual arguments into this descriptor and passes a pointer to it into
/// the auxiliary function. If the result of the function cannot be directly
/// returned, we write it to a special first argument that provides a pointer
/// to a corresponding struct. This auxiliary external function is now
/// compatible with functions defined in C using pointers to C structs
/// corresponding to a memref descriptor.
static void wrapExternalFunction(OpBuilder &builder, Location loc,
                                 LLVMTypeConverter &typeConverter,
                                 FuncOp funcOp, LLVM::LLVMFuncOp newFuncOp) {
  OpBuilder::InsertionGuard guard(builder);

  Type wrapperType;
  bool resultIsNowArg;
  std::tie(wrapperType, resultIsNowArg) =
      typeConverter.convertFunctionTypeCWrapper(funcOp.getType());
  // This conversion can only fail if it could not convert one of the argument
  // types. But since it has been applied to a non-wrapper function before, it
  // should have failed earlier and not reach this point at all.
  assert(wrapperType && "unexpected type conversion failure");

  SmallVector<NamedAttribute, 4> attributes;
  filterFuncAttributes(funcOp->getAttrs(), /*filterArgAttrs=*/false,
                       attributes);

  // Create the auxiliary function.
  auto wrapperFunc = builder.create<LLVM::LLVMFuncOp>(
      loc, llvm::formatv("_mlir_ciface_{0}", funcOp.getName()).str(),
      wrapperType, LLVM::Linkage::External, /*dsoLocal*/ false, attributes);

  builder.setInsertionPointToStart(newFuncOp.addEntryBlock());

  // Get a ValueRange containing arguments.
  FunctionType type = funcOp.getType();
  SmallVector<Value, 8> args;
  args.reserve(type.getNumInputs());
  ValueRange wrapperArgsRange(newFuncOp.getArguments());

  if (resultIsNowArg) {
    // Allocate the struct on the stack and pass the pointer.
    Type resultType =
        wrapperType.cast<LLVM::LLVMFunctionType>().getParamType(0);
    Value one = builder.create<LLVM::ConstantOp>(
        loc, typeConverter.convertType(builder.getIndexType()),
        builder.getIntegerAttr(builder.getIndexType(), 1));
    Value result = builder.create<LLVM::AllocaOp>(loc, resultType, one);
    args.push_back(result);
  }

  // Iterate over the inputs of the original function and pack values into
  // memref descriptors if the original type is a memref.
  for (auto &en : llvm::enumerate(type.getInputs())) {
    Value arg;
    int numToDrop = 1;
    auto memRefType = en.value().dyn_cast<MemRefType>();
    auto unrankedMemRefType = en.value().dyn_cast<UnrankedMemRefType>();
    if (memRefType || unrankedMemRefType) {
      numToDrop = memRefType
                      ? MemRefDescriptor::getNumUnpackedValues(memRefType)
                      : UnrankedMemRefDescriptor::getNumUnpackedValues();
      Value packed =
          memRefType
              ? MemRefDescriptor::pack(builder, loc, typeConverter, memRefType,
                                       wrapperArgsRange.take_front(numToDrop))
              : UnrankedMemRefDescriptor::pack(
                    builder, loc, typeConverter, unrankedMemRefType,
                    wrapperArgsRange.take_front(numToDrop));

      auto ptrTy = LLVM::LLVMPointerType::get(packed.getType());
      Value one = builder.create<LLVM::ConstantOp>(
          loc, typeConverter.convertType(builder.getIndexType()),
          builder.getIntegerAttr(builder.getIndexType(), 1));
      Value allocated =
          builder.create<LLVM::AllocaOp>(loc, ptrTy, one, /*alignment=*/0);
      builder.create<LLVM::StoreOp>(loc, packed, allocated);
      arg = allocated;
    } else {
      arg = wrapperArgsRange[0];
    }

    args.push_back(arg);
    wrapperArgsRange = wrapperArgsRange.drop_front(numToDrop);
  }
  assert(wrapperArgsRange.empty() && "did not map some of the arguments");

  auto call = builder.create<LLVM::CallOp>(loc, wrapperFunc, args);

  if (resultIsNowArg) {
    Value result = builder.create<LLVM::LoadOp>(loc, args.front());
    builder.create<LLVM::ReturnOp>(loc, ValueRange{result});
  } else {
    builder.create<LLVM::ReturnOp>(loc, call.getResults());
  }
}

namespace {

struct FuncOpConversionBase : public ConvertOpToLLVMPattern<FuncOp> {
protected:
  using ConvertOpToLLVMPattern<FuncOp>::ConvertOpToLLVMPattern;

  // Convert input FuncOp to LLVMFuncOp by using the LLVMTypeConverter provided
  // to this legalization pattern.
  LLVM::LLVMFuncOp
  convertFuncOpToLLVMFuncOp(FuncOp funcOp,
                            ConversionPatternRewriter &rewriter) const {
    // Convert the original function arguments. They are converted using the
    // LLVMTypeConverter provided to this legalization pattern.
    auto varargsAttr = funcOp->getAttrOfType<BoolAttr>("std.varargs");
    TypeConverter::SignatureConversion result(funcOp.getNumArguments());
    auto llvmType = getTypeConverter()->convertFunctionSignature(
        funcOp.getType(), varargsAttr && varargsAttr.getValue(), result);
    if (!llvmType)
      return nullptr;

    // Propagate argument attributes to all converted arguments obtained after
    // converting a given original argument.
    SmallVector<NamedAttribute, 4> attributes;
    filterFuncAttributes(funcOp->getAttrs(), /*filterArgAttrs=*/true,
                         attributes);
    if (ArrayAttr argAttrDicts = funcOp.getAllArgAttrs()) {
      SmallVector<Attribute, 4> newArgAttrs(
          llvmType.cast<LLVM::LLVMFunctionType>().getNumParams());
      for (unsigned i = 0, e = funcOp.getNumArguments(); i < e; ++i) {
        auto mapping = result.getInputMapping(i);
        assert(mapping.hasValue() &&
               "unexpected deletion of function argument");
        for (size_t j = 0; j < mapping->size; ++j)
          newArgAttrs[mapping->inputNo + j] = argAttrDicts[i];
      }
      attributes.push_back(
          rewriter.getNamedAttr(function_like_impl::getArgDictAttrName(),
                                rewriter.getArrayAttr(newArgAttrs)));
    }
    for (auto pair : llvm::enumerate(attributes)) {
      if (pair.value().first == "llvm.linkage") {
        attributes.erase(attributes.begin() + pair.index());
        break;
      }
    }

    // Create an LLVM function, use external linkage by default until MLIR
    // functions have linkage.
    LLVM::Linkage linkage = LLVM::Linkage::External;
    if (funcOp->hasAttr("llvm.linkage")) {
      auto attr =
          funcOp->getAttr("llvm.linkage").dyn_cast<mlir::LLVM::LinkageAttr>();
      if (!attr) {
        funcOp->emitError()
            << "Contains llvm.linkage attribute not of type LLVM::LinkageAttr";
        return nullptr;
      }
      linkage = attr.getLinkage();
    }
    auto newFuncOp = rewriter.create<LLVM::LLVMFuncOp>(
        funcOp.getLoc(), funcOp.getName(), llvmType, linkage,
        /*dsoLocal*/ false, attributes);
    rewriter.inlineRegionBefore(funcOp.getBody(), newFuncOp.getBody(),
                                newFuncOp.end());
    if (failed(rewriter.convertRegionTypes(&newFuncOp.getBody(), *typeConverter,
                                           &result)))
      return nullptr;

    return newFuncOp;
  }
};

/// FuncOp legalization pattern that converts MemRef arguments to pointers to
/// MemRef descriptors (LLVM struct data types) containing all the MemRef type
/// information.
static constexpr StringRef kEmitIfaceAttrName = "llvm.emit_c_interface";
struct FuncOpConversion : public FuncOpConversionBase {
  FuncOpConversion(LLVMTypeConverter &converter)
      : FuncOpConversionBase(converter) {}

  LogicalResult
  matchAndRewrite(FuncOp funcOp, OpAdaptor adaptor,
                  ConversionPatternRewriter &rewriter) const override {
    auto newFuncOp = convertFuncOpToLLVMFuncOp(funcOp, rewriter);
    if (!newFuncOp)
      return failure();

    if (getTypeConverter()->getOptions().emitCWrappers ||
        funcOp->getAttrOfType<UnitAttr>(kEmitIfaceAttrName)) {
      if (newFuncOp.isExternal())
        wrapExternalFunction(rewriter, funcOp.getLoc(), *getTypeConverter(),
                             funcOp, newFuncOp);
      else
        wrapForExternalCallers(rewriter, funcOp.getLoc(), *getTypeConverter(),
                               funcOp, newFuncOp);
    }

    rewriter.eraseOp(funcOp);
    return success();
  }
};

/// FuncOp legalization pattern that converts MemRef arguments to bare pointers
/// to the MemRef element type. This will impact the calling convention and ABI.
struct BarePtrFuncOpConversion : public FuncOpConversionBase {
  using FuncOpConversionBase::FuncOpConversionBase;

  LogicalResult
  matchAndRewrite(FuncOp funcOp, OpAdaptor adaptor,
                  ConversionPatternRewriter &rewriter) const override {

    // TODO: bare ptr conversion could be handled by argument materialization
    // and most of the code below would go away. But to do this, we would need a
    // way to distinguish between FuncOp and other regions in the
    // addArgumentMaterialization hook.

    // Store the type of memref-typed arguments before the conversion so that we
    // can promote them to MemRef descriptor at the beginning of the function.
    SmallVector<Type, 8> oldArgTypes =
        llvm::to_vector<8>(funcOp.getType().getInputs());

    auto newFuncOp = convertFuncOpToLLVMFuncOp(funcOp, rewriter);
    if (!newFuncOp)
      return failure();
    if (newFuncOp.getBody().empty()) {
      rewriter.eraseOp(funcOp);
      return success();
    }

    // Promote bare pointers from memref arguments to memref descriptors at the
    // beginning of the function so that all the memrefs in the function have a
    // uniform representation.
    Block *entryBlock = &newFuncOp.getBody().front();
    auto blockArgs = entryBlock->getArguments();
    assert(blockArgs.size() == oldArgTypes.size() &&
           "The number of arguments and types doesn't match");

    OpBuilder::InsertionGuard guard(rewriter);
    rewriter.setInsertionPointToStart(entryBlock);
    for (auto it : llvm::zip(blockArgs, oldArgTypes)) {
      BlockArgument arg = std::get<0>(it);
      Type argTy = std::get<1>(it);

      // Unranked memrefs are not supported in the bare pointer calling
      // convention. We should have bailed out before in the presence of
      // unranked memrefs.
      assert(!argTy.isa<UnrankedMemRefType>() &&
             "Unranked memref is not supported");
      auto memrefTy = argTy.dyn_cast<MemRefType>();
      if (!memrefTy)
        continue;

      // Replace barePtr with a placeholder (undef), promote barePtr to a ranked
      // or unranked memref descriptor and replace placeholder with the last
      // instruction of the memref descriptor.
      // TODO: The placeholder is needed to avoid replacing barePtr uses in the
      // MemRef descriptor instructions. We may want to have a utility in the
      // rewriter to properly handle this use case.
      Location loc = funcOp.getLoc();
      auto placeholder = rewriter.create<LLVM::UndefOp>(
          loc, getTypeConverter()->convertType(memrefTy));
      rewriter.replaceUsesOfBlockArgument(arg, placeholder);

      Value desc = MemRefDescriptor::fromStaticShape(
          rewriter, loc, *getTypeConverter(), memrefTy, arg);
      rewriter.replaceOp(placeholder, {desc});
    }

    rewriter.eraseOp(funcOp);
    return success();
  }
};

// Straightforward lowerings.
using AbsFOpLowering = VectorConvertToLLVMPattern<AbsFOp, LLVM::FAbsOp>;
using AddFOpLowering = VectorConvertToLLVMPattern<AddFOp, LLVM::FAddOp>;
using AddIOpLowering = VectorConvertToLLVMPattern<AddIOp, LLVM::AddOp>;
using AndOpLowering = VectorConvertToLLVMPattern<AndOp, LLVM::AndOp>;
using BitcastOpLowering =
    VectorConvertToLLVMPattern<BitcastOp, LLVM::BitcastOp>;
using CeilFOpLowering = VectorConvertToLLVMPattern<CeilFOp, LLVM::FCeilOp>;
using CopySignOpLowering =
    VectorConvertToLLVMPattern<CopySignOp, LLVM::CopySignOp>;
using DivFOpLowering = VectorConvertToLLVMPattern<DivFOp, LLVM::FDivOp>;
using FPExtOpLowering = VectorConvertToLLVMPattern<FPExtOp, LLVM::FPExtOp>;
using FPToSIOpLowering = VectorConvertToLLVMPattern<FPToSIOp, LLVM::FPToSIOp>;
using FPToUIOpLowering = VectorConvertToLLVMPattern<FPToUIOp, LLVM::FPToUIOp>;
using FPTruncOpLowering =
    VectorConvertToLLVMPattern<FPTruncOp, LLVM::FPTruncOp>;
using FloorFOpLowering = VectorConvertToLLVMPattern<FloorFOp, LLVM::FFloorOp>;
using FmaFOpLowering = VectorConvertToLLVMPattern<FmaFOp, LLVM::FMAOp>;
using MulFOpLowering = VectorConvertToLLVMPattern<MulFOp, LLVM::FMulOp>;
using MulIOpLowering = VectorConvertToLLVMPattern<MulIOp, LLVM::MulOp>;
using NegFOpLowering = VectorConvertToLLVMPattern<NegFOp, LLVM::FNegOp>;
using OrOpLowering = VectorConvertToLLVMPattern<OrOp, LLVM::OrOp>;
using RemFOpLowering = VectorConvertToLLVMPattern<RemFOp, LLVM::FRemOp>;
using SIToFPOpLowering = VectorConvertToLLVMPattern<SIToFPOp, LLVM::SIToFPOp>;
using SelectOpLowering = VectorConvertToLLVMPattern<SelectOp, LLVM::SelectOp>;
using SignExtendIOpLowering =
    VectorConvertToLLVMPattern<SignExtendIOp, LLVM::SExtOp>;
using ShiftLeftOpLowering =
    VectorConvertToLLVMPattern<ShiftLeftOp, LLVM::ShlOp>;
using SignedDivIOpLowering =
    VectorConvertToLLVMPattern<SignedDivIOp, LLVM::SDivOp>;
using SignedRemIOpLowering =
    VectorConvertToLLVMPattern<SignedRemIOp, LLVM::SRemOp>;
using SignedShiftRightOpLowering =
    VectorConvertToLLVMPattern<SignedShiftRightOp, LLVM::AShrOp>;
using SubFOpLowering = VectorConvertToLLVMPattern<SubFOp, LLVM::FSubOp>;
using SubIOpLowering = VectorConvertToLLVMPattern<SubIOp, LLVM::SubOp>;
using TruncateIOpLowering =
    VectorConvertToLLVMPattern<TruncateIOp, LLVM::TruncOp>;
using UIToFPOpLowering = VectorConvertToLLVMPattern<UIToFPOp, LLVM::UIToFPOp>;
using UnsignedDivIOpLowering =
    VectorConvertToLLVMPattern<UnsignedDivIOp, LLVM::UDivOp>;
using UnsignedRemIOpLowering =
    VectorConvertToLLVMPattern<UnsignedRemIOp, LLVM::URemOp>;
using UnsignedShiftRightOpLowering =
    VectorConvertToLLVMPattern<UnsignedShiftRightOp, LLVM::LShrOp>;
using XOrOpLowering = VectorConvertToLLVMPattern<XOrOp, LLVM::XOrOp>;
using ZeroExtendIOpLowering =
    VectorConvertToLLVMPattern<ZeroExtendIOp, LLVM::ZExtOp>;

/// Lower `std.assert`. The default lowering calls the `abort` function if the
/// assertion is violated and has no effect otherwise. The failure message is
/// ignored by the default lowering but should be propagated by any custom
/// lowering.
struct AssertOpLowering : public ConvertOpToLLVMPattern<AssertOp> {
  using ConvertOpToLLVMPattern<AssertOp>::ConvertOpToLLVMPattern;

  LogicalResult
  matchAndRewrite(AssertOp op, OpAdaptor adaptor,
                  ConversionPatternRewriter &rewriter) const override {
    auto loc = op.getLoc();

    // Insert the `abort` declaration if necessary.
    auto module = op->getParentOfType<ModuleOp>();
    auto abortFunc = module.lookupSymbol<LLVM::LLVMFuncOp>("abort");
    if (!abortFunc) {
      OpBuilder::InsertionGuard guard(rewriter);
      rewriter.setInsertionPointToStart(module.getBody());
      auto abortFuncTy = LLVM::LLVMFunctionType::get(getVoidType(), {});
      abortFunc = rewriter.create<LLVM::LLVMFuncOp>(rewriter.getUnknownLoc(),
                                                    "abort", abortFuncTy);
    }

    // Split block at `assert` operation.
    Block *opBlock = rewriter.getInsertionBlock();
    auto opPosition = rewriter.getInsertionPoint();
    Block *continuationBlock = rewriter.splitBlock(opBlock, opPosition);

    // Generate IR to call `abort`.
    Block *failureBlock = rewriter.createBlock(opBlock->getParent());
    rewriter.create<LLVM::CallOp>(loc, abortFunc, llvm::None);
    rewriter.create<LLVM::UnreachableOp>(loc);

    // Generate assertion test.
    rewriter.setInsertionPointToEnd(opBlock);
    rewriter.replaceOpWithNewOp<LLVM::CondBrOp>(
        op, adaptor.arg(), continuationBlock, failureBlock);

    return success();
  }
};

struct ConstantOpLowering : public ConvertOpToLLVMPattern<ConstantOp> {
  using ConvertOpToLLVMPattern<ConstantOp>::ConvertOpToLLVMPattern;

  LogicalResult
  matchAndRewrite(ConstantOp op, OpAdaptor adaptor,
                  ConversionPatternRewriter &rewriter) const override {
    // If constant refers to a function, convert it to "addressof".
    if (auto symbolRef = op.getValue().dyn_cast<FlatSymbolRefAttr>()) {
      auto type = typeConverter->convertType(op.getResult().getType());
      if (!type || !LLVM::isCompatibleType(type))
        return rewriter.notifyMatchFailure(op, "failed to convert result type");

      auto newOp = rewriter.create<LLVM::AddressOfOp>(op.getLoc(), type,
                                                      symbolRef.getValue());
      for (const NamedAttribute &attr : op->getAttrs()) {
        if (attr.first.strref() == "value")
          continue;
        newOp->setAttr(attr.first, attr.second);
      }
      rewriter.replaceOp(op, newOp->getResults());
      return success();
    }

    // Calling into other scopes (non-flat reference) is not supported in LLVM.
    if (op.getValue().isa<SymbolRefAttr>())
      return rewriter.notifyMatchFailure(
          op, "referring to a symbol outside of the current module");

    return LLVM::detail::oneToOneRewrite(
        op, LLVM::ConstantOp::getOperationName(), adaptor.getOperands(),
        *getTypeConverter(), rewriter);
  }
};

// A CallOp automatically promotes MemRefType to a sequence of alloca/store and
// passes the pointer to the MemRef across function boundaries.
template <typename CallOpType>
struct CallOpInterfaceLowering : public ConvertOpToLLVMPattern<CallOpType> {
  using ConvertOpToLLVMPattern<CallOpType>::ConvertOpToLLVMPattern;
  using Super = CallOpInterfaceLowering<CallOpType>;
  using Base = ConvertOpToLLVMPattern<CallOpType>;

  LogicalResult
  matchAndRewrite(CallOpType callOp, typename CallOpType::Adaptor adaptor,
                  ConversionPatternRewriter &rewriter) const override {
    // Pack the result types into a struct.
    Type packedResult = nullptr;
    unsigned numResults = callOp.getNumResults();
    auto resultTypes = llvm::to_vector<4>(callOp.getResultTypes());

    if (numResults != 0) {
      if (!(packedResult =
                this->getTypeConverter()->packFunctionResults(resultTypes)))
        return failure();
    }

    auto promoted = this->getTypeConverter()->promoteOperands(
        callOp.getLoc(), /*opOperands=*/callOp->getOperands(),
        adaptor.getOperands(), rewriter);
    auto newOp = rewriter.create<LLVM::CallOp>(
        callOp.getLoc(), packedResult ? TypeRange(packedResult) : TypeRange(),
        promoted, callOp->getAttrs());

    SmallVector<Value, 4> results;
    if (numResults < 2) {
      // If < 2 results, packing did not do anything and we can just return.
      results.append(newOp.result_begin(), newOp.result_end());
    } else {
      // Otherwise, it had been converted to an operation producing a structure.
      // Extract individual results from the structure and return them as list.
      results.reserve(numResults);
      for (unsigned i = 0; i < numResults; ++i) {
        auto type =
            this->typeConverter->convertType(callOp.getResult(i).getType());
        results.push_back(rewriter.create<LLVM::ExtractValueOp>(
            callOp.getLoc(), type, newOp->getResult(0),
            rewriter.getI64ArrayAttr(i)));
      }
    }

    if (this->getTypeConverter()->getOptions().useBarePtrCallConv) {
      // For the bare-ptr calling convention, promote memref results to
      // descriptors.
      assert(results.size() == resultTypes.size() &&
             "The number of arguments and types doesn't match");
      this->getTypeConverter()->promoteBarePtrsToDescriptors(
          rewriter, callOp.getLoc(), resultTypes, results);
    } else if (failed(this->copyUnrankedDescriptors(rewriter, callOp.getLoc(),
                                                    resultTypes, results,
                                                    /*toDynamic=*/false))) {
      return failure();
    }

    rewriter.replaceOp(callOp, results);
    return success();
  }
};

struct CallOpLowering : public CallOpInterfaceLowering<CallOp> {
  using Super::Super;
};

struct CallIndirectOpLowering : public CallOpInterfaceLowering<CallIndirectOp> {
  using Super::Super;
};

struct UnrealizedConversionCastOpLowering
    : public ConvertOpToLLVMPattern<UnrealizedConversionCastOp> {
  using ConvertOpToLLVMPattern<
      UnrealizedConversionCastOp>::ConvertOpToLLVMPattern;

  LogicalResult
  matchAndRewrite(UnrealizedConversionCastOp op, OpAdaptor adaptor,
                  ConversionPatternRewriter &rewriter) const override {
    SmallVector<Type> convertedTypes;
    if (succeeded(typeConverter->convertTypes(op.outputs().getTypes(),
                                              convertedTypes)) &&
        convertedTypes == adaptor.inputs().getTypes()) {
      rewriter.replaceOp(op, adaptor.inputs());
      return success();
    }

    convertedTypes.clear();
    if (succeeded(typeConverter->convertTypes(adaptor.inputs().getTypes(),
                                              convertedTypes)) &&
        convertedTypes == op.outputs().getType()) {
      rewriter.replaceOp(op, adaptor.inputs());
      return success();
    }
    return failure();
  }
};

struct RankOpLowering : public ConvertOpToLLVMPattern<RankOp> {
  using ConvertOpToLLVMPattern<RankOp>::ConvertOpToLLVMPattern;

  LogicalResult
  matchAndRewrite(RankOp op, OpAdaptor adaptor,
                  ConversionPatternRewriter &rewriter) const override {
    Location loc = op.getLoc();
    Type operandType = op.memrefOrTensor().getType();
    if (auto unrankedMemRefType = operandType.dyn_cast<UnrankedMemRefType>()) {
      UnrankedMemRefDescriptor desc(adaptor.memrefOrTensor());
      rewriter.replaceOp(op, {desc.rank(rewriter, loc)});
      return success();
    }
    if (auto rankedMemRefType = operandType.dyn_cast<MemRefType>()) {
      rewriter.replaceOp(
          op, {createIndexConstant(rewriter, loc, rankedMemRefType.getRank())});
      return success();
    }
    return failure();
  }
};

// Common base for load and store operations on MemRefs.  Restricts the match
// to supported MemRef types. Provides functionality to emit code accessing a
// specific element of the underlying data buffer.
template <typename Derived>
struct LoadStoreOpLowering : public ConvertOpToLLVMPattern<Derived> {
  using ConvertOpToLLVMPattern<Derived>::ConvertOpToLLVMPattern;
  using ConvertOpToLLVMPattern<Derived>::isConvertibleAndHasIdentityMaps;
  using Base = LoadStoreOpLowering<Derived>;

  LogicalResult match(Derived op) const override {
    MemRefType type = op.getMemRefType();
    return isConvertibleAndHasIdentityMaps(type) ? success() : failure();
  }
};

// The lowering of index_cast becomes an integer conversion since index becomes
// an integer.  If the bit width of the source and target integer types is the
// same, just erase the cast.  If the target type is wider, sign-extend the
// value, otherwise truncate it.
struct IndexCastOpLowering : public ConvertOpToLLVMPattern<IndexCastOp> {
  using ConvertOpToLLVMPattern<IndexCastOp>::ConvertOpToLLVMPattern;

  LogicalResult
  matchAndRewrite(IndexCastOp indexCastOp, OpAdaptor adaptor,
                  ConversionPatternRewriter &rewriter) const override {
    auto targetType =
        typeConverter->convertType(indexCastOp.getResult().getType());
    auto targetElementType =
        typeConverter
            ->convertType(getElementTypeOrSelf(indexCastOp.getResult()))
            .cast<IntegerType>();
    auto sourceElementType =
        getElementTypeOrSelf(adaptor.in()).cast<IntegerType>();
    unsigned targetBits = targetElementType.getWidth();
    unsigned sourceBits = sourceElementType.getWidth();

    if (targetBits == sourceBits)
      rewriter.replaceOp(indexCastOp, adaptor.in());
    else if (targetBits < sourceBits)
      rewriter.replaceOpWithNewOp<LLVM::TruncOp>(indexCastOp, targetType,
                                                 adaptor.in());
    else
      rewriter.replaceOpWithNewOp<LLVM::SExtOp>(indexCastOp, targetType,
                                                adaptor.in());
    return success();
  }
};

// Convert std.cmp predicate into the LLVM dialect CmpPredicate.  The two
// enums share the numerical values so just cast.
template <typename LLVMPredType, typename StdPredType>
static LLVMPredType convertCmpPredicate(StdPredType pred) {
  return static_cast<LLVMPredType>(pred);
}

struct CmpIOpLowering : public ConvertOpToLLVMPattern<CmpIOp> {
  using ConvertOpToLLVMPattern<CmpIOp>::ConvertOpToLLVMPattern;

  LogicalResult
  matchAndRewrite(CmpIOp cmpiOp, OpAdaptor adaptor,
                  ConversionPatternRewriter &rewriter) const override {
    auto operandType = adaptor.lhs().getType();
    auto resultType = cmpiOp.getResult().getType();

    // Handle the scalar and 1D vector cases.
    if (!operandType.isa<LLVM::LLVMArrayType>()) {
      rewriter.replaceOpWithNewOp<LLVM::ICmpOp>(
          cmpiOp, typeConverter->convertType(resultType),
          convertCmpPredicate<LLVM::ICmpPredicate>(cmpiOp.getPredicate()),
          adaptor.lhs(), adaptor.rhs());
      return success();
    }

    auto vectorType = resultType.dyn_cast<VectorType>();
    if (!vectorType)
      return rewriter.notifyMatchFailure(cmpiOp, "expected vector result type");

    return LLVM::detail::handleMultidimensionalVectors(
        cmpiOp.getOperation(), adaptor.getOperands(), *getTypeConverter(),
        [&](Type llvm1DVectorTy, ValueRange operands) {
          CmpIOpAdaptor adaptor(operands);
          return rewriter.create<LLVM::ICmpOp>(
              cmpiOp.getLoc(), llvm1DVectorTy,
              convertCmpPredicate<LLVM::ICmpPredicate>(cmpiOp.getPredicate()),
              adaptor.lhs(), adaptor.rhs());
        },
        rewriter);

    return success();
  }
};

struct CmpFOpLowering : public ConvertOpToLLVMPattern<CmpFOp> {
  using ConvertOpToLLVMPattern<CmpFOp>::ConvertOpToLLVMPattern;

  LogicalResult
  matchAndRewrite(CmpFOp cmpfOp, OpAdaptor adaptor,
                  ConversionPatternRewriter &rewriter) const override {
    auto operandType = adaptor.lhs().getType();
    auto resultType = cmpfOp.getResult().getType();

    // Handle the scalar and 1D vector cases.
    if (!operandType.isa<LLVM::LLVMArrayType>()) {
      rewriter.replaceOpWithNewOp<LLVM::FCmpOp>(
          cmpfOp, typeConverter->convertType(resultType),
          convertCmpPredicate<LLVM::FCmpPredicate>(cmpfOp.getPredicate()),
          adaptor.lhs(), adaptor.rhs());
      return success();
    }

    auto vectorType = resultType.dyn_cast<VectorType>();
    if (!vectorType)
      return rewriter.notifyMatchFailure(cmpfOp, "expected vector result type");

    return LLVM::detail::handleMultidimensionalVectors(
        cmpfOp.getOperation(), adaptor.getOperands(), *getTypeConverter(),
        [&](Type llvm1DVectorTy, ValueRange operands) {
          CmpFOpAdaptor adaptor(operands);
          return rewriter.create<LLVM::FCmpOp>(
              cmpfOp.getLoc(), llvm1DVectorTy,
              convertCmpPredicate<LLVM::FCmpPredicate>(cmpfOp.getPredicate()),
              adaptor.lhs(), adaptor.rhs());
        },
        rewriter);
  }
};

// Base class for LLVM IR lowering terminator operations with successors.
template <typename SourceOp, typename TargetOp>
struct OneToOneLLVMTerminatorLowering
    : public ConvertOpToLLVMPattern<SourceOp> {
  using ConvertOpToLLVMPattern<SourceOp>::ConvertOpToLLVMPattern;
  using Super = OneToOneLLVMTerminatorLowering<SourceOp, TargetOp>;

  LogicalResult
  matchAndRewrite(SourceOp op, typename SourceOp::Adaptor adaptor,
                  ConversionPatternRewriter &rewriter) const override {
    rewriter.replaceOpWithNewOp<TargetOp>(op, adaptor.getOperands(),
                                          op->getSuccessors(), op->getAttrs());
    return success();
  }
};

// Special lowering pattern for `ReturnOps`.  Unlike all other operations,
// `ReturnOp` interacts with the function signature and must have as many
// operands as the function has return values.  Because in LLVM IR, functions
// can only return 0 or 1 value, we pack multiple values into a structure type.
// Emit `UndefOp` followed by `InsertValueOp`s to create such structure if
// necessary before returning it
struct ReturnOpLowering : public ConvertOpToLLVMPattern<ReturnOp> {
  using ConvertOpToLLVMPattern<ReturnOp>::ConvertOpToLLVMPattern;

  LogicalResult
  matchAndRewrite(ReturnOp op, OpAdaptor adaptor,
                  ConversionPatternRewriter &rewriter) const override {
    Location loc = op.getLoc();
    unsigned numArguments = op.getNumOperands();
    SmallVector<Value, 4> updatedOperands;

    if (getTypeConverter()->getOptions().useBarePtrCallConv) {
      // For the bare-ptr calling convention, extract the aligned pointer to
      // be returned from the memref descriptor.
      for (auto it : llvm::zip(op->getOperands(), adaptor.getOperands())) {
        Type oldTy = std::get<0>(it).getType();
        Value newOperand = std::get<1>(it);
        if (oldTy.isa<MemRefType>()) {
          MemRefDescriptor memrefDesc(newOperand);
          newOperand = memrefDesc.alignedPtr(rewriter, loc);
        } else if (oldTy.isa<UnrankedMemRefType>()) {
          // Unranked memref is not supported in the bare pointer calling
          // convention.
          return failure();
        }
        updatedOperands.push_back(newOperand);
      }
    } else {
      updatedOperands = llvm::to_vector<4>(adaptor.getOperands());
      (void)copyUnrankedDescriptors(rewriter, loc, op.getOperands().getTypes(),
                                    updatedOperands,
                                    /*toDynamic=*/true);
    }

    // If ReturnOp has 0 or 1 operand, create it and return immediately.
    if (numArguments == 0) {
      rewriter.replaceOpWithNewOp<LLVM::ReturnOp>(op, TypeRange(), ValueRange(),
                                                  op->getAttrs());
      return success();
    }
    if (numArguments == 1) {
      rewriter.replaceOpWithNewOp<LLVM::ReturnOp>(
          op, TypeRange(), updatedOperands, op->getAttrs());
      return success();
    }

    // Otherwise, we need to pack the arguments into an LLVM struct type before
    // returning.
    auto packedType = getTypeConverter()->packFunctionResults(
        llvm::to_vector<4>(op.getOperandTypes()));

    Value packed = rewriter.create<LLVM::UndefOp>(loc, packedType);
    for (unsigned i = 0; i < numArguments; ++i) {
      packed = rewriter.create<LLVM::InsertValueOp>(
          loc, packedType, packed, updatedOperands[i],
          rewriter.getI64ArrayAttr(i));
    }
    rewriter.replaceOpWithNewOp<LLVM::ReturnOp>(op, TypeRange(), packed,
                                                op->getAttrs());
    return success();
  }
};

// FIXME: this should be tablegen'ed as well.
struct BranchOpLowering
    : public OneToOneLLVMTerminatorLowering<BranchOp, LLVM::BrOp> {
  using Super::Super;
};
struct CondBranchOpLowering
    : public OneToOneLLVMTerminatorLowering<CondBranchOp, LLVM::CondBrOp> {
  using Super::Super;
};
struct SwitchOpLowering
    : public OneToOneLLVMTerminatorLowering<SwitchOp, LLVM::SwitchOp> {
  using Super::Super;
};

// The Splat operation is lowered to an insertelement + a shufflevector
// operation. Splat to only 1-d vector result types are lowered.
struct SplatOpLowering : public ConvertOpToLLVMPattern<SplatOp> {
  using ConvertOpToLLVMPattern<SplatOp>::ConvertOpToLLVMPattern;

  LogicalResult
  matchAndRewrite(SplatOp splatOp, OpAdaptor adaptor,
                  ConversionPatternRewriter &rewriter) const override {
    VectorType resultType = splatOp.getType().dyn_cast<VectorType>();
    if (!resultType || resultType.getRank() != 1)
      return failure();

    // First insert it into an undef vector so we can shuffle it.
    auto vectorType = typeConverter->convertType(splatOp.getType());
    Value undef = rewriter.create<LLVM::UndefOp>(splatOp.getLoc(), vectorType);
    auto zero = rewriter.create<LLVM::ConstantOp>(
        splatOp.getLoc(),
        typeConverter->convertType(rewriter.getIntegerType(32)),
        rewriter.getZeroAttr(rewriter.getIntegerType(32)));

    auto v = rewriter.create<LLVM::InsertElementOp>(
        splatOp.getLoc(), vectorType, undef, adaptor.input(), zero);

    int64_t width = splatOp.getType().cast<VectorType>().getDimSize(0);
    SmallVector<int32_t, 4> zeroValues(width, 0);

    // Shuffle the value across the desired number of elements.
    ArrayAttr zeroAttrs = rewriter.getI32ArrayAttr(zeroValues);
    rewriter.replaceOpWithNewOp<LLVM::ShuffleVectorOp>(splatOp, v, undef,
                                                       zeroAttrs);
    return success();
  }
};

// The Splat operation is lowered to an insertelement + a shufflevector
// operation. Splat to only 2+-d vector result types are lowered by the
// SplatNdOpLowering, the 1-d case is handled by SplatOpLowering.
struct SplatNdOpLowering : public ConvertOpToLLVMPattern<SplatOp> {
  using ConvertOpToLLVMPattern<SplatOp>::ConvertOpToLLVMPattern;

  LogicalResult
  matchAndRewrite(SplatOp splatOp, OpAdaptor adaptor,
                  ConversionPatternRewriter &rewriter) const override {
    VectorType resultType = splatOp.getType().dyn_cast<VectorType>();
    if (!resultType || resultType.getRank() == 1)
      return failure();

    // First insert it into an undef vector so we can shuffle it.
    auto loc = splatOp.getLoc();
    auto vectorTypeInfo =
        LLVM::detail::extractNDVectorTypeInfo(resultType, *getTypeConverter());
    auto llvmNDVectorTy = vectorTypeInfo.llvmNDVectorTy;
    auto llvm1DVectorTy = vectorTypeInfo.llvm1DVectorTy;
    if (!llvmNDVectorTy || !llvm1DVectorTy)
      return failure();

    // Construct returned value.
    Value desc = rewriter.create<LLVM::UndefOp>(loc, llvmNDVectorTy);

    // Construct a 1-D vector with the splatted value that we insert in all the
    // places within the returned descriptor.
    Value vdesc = rewriter.create<LLVM::UndefOp>(loc, llvm1DVectorTy);
    auto zero = rewriter.create<LLVM::ConstantOp>(
        loc, typeConverter->convertType(rewriter.getIntegerType(32)),
        rewriter.getZeroAttr(rewriter.getIntegerType(32)));
    Value v = rewriter.create<LLVM::InsertElementOp>(loc, llvm1DVectorTy, vdesc,
                                                     adaptor.input(), zero);

    // Shuffle the value across the desired number of elements.
    int64_t width = resultType.getDimSize(resultType.getRank() - 1);
    SmallVector<int32_t, 4> zeroValues(width, 0);
    ArrayAttr zeroAttrs = rewriter.getI32ArrayAttr(zeroValues);
    v = rewriter.create<LLVM::ShuffleVectorOp>(loc, v, v, zeroAttrs);

    // Iterate of linear index, convert to coords space and insert splatted 1-D
    // vector in each position.
    nDVectorIterate(vectorTypeInfo, rewriter, [&](ArrayAttr position) {
      desc = rewriter.create<LLVM::InsertValueOp>(loc, llvmNDVectorTy, desc, v,
                                                  position);
    });
    rewriter.replaceOp(splatOp, desc);
    return success();
  }
};

} // namespace

/// Try to match the kind of a std.atomic_rmw to determine whether to use a
/// lowering to llvm.atomicrmw or fallback to llvm.cmpxchg.
static Optional<LLVM::AtomicBinOp> matchSimpleAtomicOp(AtomicRMWOp atomicOp) {
  switch (atomicOp.kind()) {
  case AtomicRMWKind::addf:
    return LLVM::AtomicBinOp::fadd;
  case AtomicRMWKind::addi:
    return LLVM::AtomicBinOp::add;
  case AtomicRMWKind::assign:
    return LLVM::AtomicBinOp::xchg;
  case AtomicRMWKind::maxs:
    return LLVM::AtomicBinOp::max;
  case AtomicRMWKind::maxu:
    return LLVM::AtomicBinOp::umax;
  case AtomicRMWKind::mins:
    return LLVM::AtomicBinOp::min;
  case AtomicRMWKind::minu:
    return LLVM::AtomicBinOp::umin;
  default:
    return llvm::None;
  }
  llvm_unreachable("Invalid AtomicRMWKind");
}

namespace {

struct AtomicRMWOpLowering : public LoadStoreOpLowering<AtomicRMWOp> {
  using Base::Base;

  LogicalResult
  matchAndRewrite(AtomicRMWOp atomicOp, OpAdaptor adaptor,
                  ConversionPatternRewriter &rewriter) const override {
    if (failed(match(atomicOp)))
      return failure();
    auto maybeKind = matchSimpleAtomicOp(atomicOp);
    if (!maybeKind)
      return failure();
    auto resultType = adaptor.value().getType();
    auto memRefType = atomicOp.getMemRefType();
    auto dataPtr =
        getStridedElementPtr(atomicOp.getLoc(), memRefType, adaptor.memref(),
                             adaptor.indices(), rewriter);
    rewriter.replaceOpWithNewOp<LLVM::AtomicRMWOp>(
        atomicOp, resultType, *maybeKind, dataPtr, adaptor.value(),
        LLVM::AtomicOrdering::acq_rel);
    return success();
  }
};

/// Wrap a llvm.cmpxchg operation in a while loop so that the operation can be
/// retried until it succeeds in atomically storing a new value into memory.
///
///      +---------------------------------+
///      |   <code before the AtomicRMWOp> |
///      |   <compute initial %loaded>     |
///      |   br loop(%loaded)              |
///      +---------------------------------+
///             |
///  -------|   |
///  |      v   v
///  |   +--------------------------------+
///  |   | loop(%loaded):                 |
///  |   |   <body contents>              |
///  |   |   %pair = cmpxchg              |
///  |   |   %ok = %pair[0]               |
///  |   |   %new = %pair[1]              |
///  |   |   cond_br %ok, end, loop(%new) |
///  |   +--------------------------------+
///  |          |        |
///  |-----------        |
///                      v
///      +--------------------------------+
///      | end:                           |
///      |   <code after the AtomicRMWOp> |
///      +--------------------------------+
///
struct GenericAtomicRMWOpLowering
    : public LoadStoreOpLowering<GenericAtomicRMWOp> {
  using Base::Base;

  LogicalResult
  matchAndRewrite(GenericAtomicRMWOp atomicOp, OpAdaptor adaptor,
                  ConversionPatternRewriter &rewriter) const override {

    auto loc = atomicOp.getLoc();
    Type valueType = typeConverter->convertType(atomicOp.getResult().getType());

    // Split the block into initial, loop, and ending parts.
    auto *initBlock = rewriter.getInsertionBlock();
    auto *loopBlock =
        rewriter.createBlock(initBlock->getParent(),
                             std::next(Region::iterator(initBlock)), valueType);
    auto *endBlock = rewriter.createBlock(
        loopBlock->getParent(), std::next(Region::iterator(loopBlock)));

    // Operations range to be moved to `endBlock`.
    auto opsToMoveStart = atomicOp->getIterator();
    auto opsToMoveEnd = initBlock->back().getIterator();

    // Compute the loaded value and branch to the loop block.
    rewriter.setInsertionPointToEnd(initBlock);
    auto memRefType = atomicOp.memref().getType().cast<MemRefType>();
    auto dataPtr = getStridedElementPtr(loc, memRefType, adaptor.memref(),
                                        adaptor.indices(), rewriter);
    Value init = rewriter.create<LLVM::LoadOp>(loc, dataPtr);
    rewriter.create<LLVM::BrOp>(loc, init, loopBlock);

    // Prepare the body of the loop block.
    rewriter.setInsertionPointToStart(loopBlock);

    // Clone the GenericAtomicRMWOp region and extract the result.
    auto loopArgument = loopBlock->getArgument(0);
    BlockAndValueMapping mapping;
    mapping.map(atomicOp.getCurrentValue(), loopArgument);
    Block &entryBlock = atomicOp.body().front();
    for (auto &nestedOp : entryBlock.without_terminator()) {
      Operation *clone = rewriter.clone(nestedOp, mapping);
      mapping.map(nestedOp.getResults(), clone->getResults());
    }
    Value result = mapping.lookup(entryBlock.getTerminator()->getOperand(0));

    // Prepare the epilog of the loop block.
    // Append the cmpxchg op to the end of the loop block.
    auto successOrdering = LLVM::AtomicOrdering::acq_rel;
    auto failureOrdering = LLVM::AtomicOrdering::monotonic;
    auto boolType = IntegerType::get(rewriter.getContext(), 1);
    auto pairType = LLVM::LLVMStructType::getLiteral(rewriter.getContext(),
                                                     {valueType, boolType});
    auto cmpxchg = rewriter.create<LLVM::AtomicCmpXchgOp>(
        loc, pairType, dataPtr, loopArgument, result, successOrdering,
        failureOrdering);
    // Extract the %new_loaded and %ok values from the pair.
    Value newLoaded = rewriter.create<LLVM::ExtractValueOp>(
        loc, valueType, cmpxchg, rewriter.getI64ArrayAttr({0}));
    Value ok = rewriter.create<LLVM::ExtractValueOp>(
        loc, boolType, cmpxchg, rewriter.getI64ArrayAttr({1}));

    // Conditionally branch to the end or back to the loop depending on %ok.
    rewriter.create<LLVM::CondBrOp>(loc, ok, endBlock, ArrayRef<Value>(),
                                    loopBlock, newLoaded);

    rewriter.setInsertionPointToEnd(endBlock);
    moveOpsRange(atomicOp.getResult(), newLoaded, std::next(opsToMoveStart),
                 std::next(opsToMoveEnd), rewriter);

    // The 'result' of the atomic_rmw op is the newly loaded value.
    rewriter.replaceOp(atomicOp, {newLoaded});

    return success();
  }

private:
  // Clones a segment of ops [start, end) and erases the original.
  void moveOpsRange(ValueRange oldResult, ValueRange newResult,
                    Block::iterator start, Block::iterator end,
                    ConversionPatternRewriter &rewriter) const {
    BlockAndValueMapping mapping;
    mapping.map(oldResult, newResult);
    SmallVector<Operation *, 2> opsToErase;
    for (auto it = start; it != end; ++it) {
      rewriter.clone(*it, mapping);
      opsToErase.push_back(&*it);
    }
    for (auto *it : opsToErase)
      rewriter.eraseOp(it);
  }
};

} // namespace

void mlir::populateStdToLLVMFuncOpConversionPattern(
    LLVMTypeConverter &converter, RewritePatternSet &patterns) {
  if (converter.getOptions().useBarePtrCallConv)
    patterns.add<BarePtrFuncOpConversion>(converter);
  else
    patterns.add<FuncOpConversion>(converter);
}

void mlir::populateStdToLLVMConversionPatterns(LLVMTypeConverter &converter,
                                               RewritePatternSet &patterns) {
  populateStdToLLVMFuncOpConversionPattern(converter, patterns);
  // clang-format off
  patterns.add<
      AbsFOpLowering,
      AddFOpLowering,
      AddIOpLowering,
      AndOpLowering,
      AssertOpLowering,
      AtomicRMWOpLowering,
      BitcastOpLowering,
      BranchOpLowering,
      CallIndirectOpLowering,
      CallOpLowering,
      CeilFOpLowering,
      CmpFOpLowering,
      CmpIOpLowering,
      CondBranchOpLowering,
      CopySignOpLowering,
      ConstantOpLowering,
      DivFOpLowering,
      FloorFOpLowering,
      FmaFOpLowering,
      GenericAtomicRMWOpLowering,
      FPExtOpLowering,
      FPToSIOpLowering,
      FPToUIOpLowering,
      FPTruncOpLowering,
      IndexCastOpLowering,
      MulFOpLowering,
      MulIOpLowering,
      NegFOpLowering,
      OrOpLowering,
      RemFOpLowering,
      RankOpLowering,
      ReturnOpLowering,
      SIToFPOpLowering,
      SelectOpLowering,
      ShiftLeftOpLowering,
      SignExtendIOpLowering,
      SignedDivIOpLowering,
      SignedRemIOpLowering,
      SignedShiftRightOpLowering,
      SplatOpLowering,
      SplatNdOpLowering,
      SubFOpLowering,
      SubIOpLowering,
      SwitchOpLowering,
      TruncateIOpLowering,
      UIToFPOpLowering,
      UnsignedDivIOpLowering,
      UnsignedRemIOpLowering,
      UnsignedShiftRightOpLowering,
      XOrOpLowering,
      ZeroExtendIOpLowering>(converter);
  // clang-format on
}

namespace {
/// A pass converting MLIR operations into the LLVM IR dialect.
struct LLVMLoweringPass : public ConvertStandardToLLVMBase<LLVMLoweringPass> {
  LLVMLoweringPass() = default;
  LLVMLoweringPass(bool useBarePtrCallConv, bool emitCWrappers,
                   unsigned indexBitwidth, bool useAlignedAlloc,
                   const llvm::DataLayout &dataLayout) {
    this->useBarePtrCallConv = useBarePtrCallConv;
    this->emitCWrappers = emitCWrappers;
    this->indexBitwidth = indexBitwidth;
    this->dataLayout = dataLayout.getStringRepresentation();
  }

  /// Run the dialect converter on the module.
  void runOnOperation() override {
    if (useBarePtrCallConv && emitCWrappers) {
      getOperation().emitError()
          << "incompatible conversion options: bare-pointer calling convention "
             "and C wrapper emission";
      signalPassFailure();
      return;
    }
    if (failed(LLVM::LLVMDialect::verifyDataLayoutString(
            this->dataLayout, [this](const Twine &message) {
              getOperation().emitError() << message.str();
            }))) {
      signalPassFailure();
      return;
    }

    ModuleOp m = getOperation();
    const auto &dataLayoutAnalysis = getAnalysis<DataLayoutAnalysis>();

    LowerToLLVMOptions options(&getContext(),
                               dataLayoutAnalysis.getAtOrAbove(m));
    options.useBarePtrCallConv = useBarePtrCallConv;
    options.emitCWrappers = emitCWrappers;
    if (indexBitwidth != kDeriveIndexBitwidthFromDataLayout)
      options.overrideIndexBitwidth(indexBitwidth);
    options.dataLayout = llvm::DataLayout(this->dataLayout);

    LLVMTypeConverter typeConverter(&getContext(), options,
                                    &dataLayoutAnalysis);

    RewritePatternSet patterns(&getContext());
    populateStdToLLVMConversionPatterns(typeConverter, patterns);

    LLVMConversionTarget target(getContext());
    if (failed(applyPartialConversion(m, target, std::move(patterns))))
      signalPassFailure();

    m->setAttr(LLVM::LLVMDialect::getDataLayoutAttrName(),
               StringAttr::get(m.getContext(), this->dataLayout));
  }
};
} // end namespace

std::unique_ptr<OperationPass<ModuleOp>> mlir::createLowerToLLVMPass() {
  return std::make_unique<LLVMLoweringPass>();
}

std::unique_ptr<OperationPass<ModuleOp>>
mlir::createLowerToLLVMPass(const LowerToLLVMOptions &options) {
  auto allocLowering = options.allocLowering;
  // There is no way to provide additional patterns for pass, so
  // AllocLowering::None will always fail.
  assert(allocLowering != LowerToLLVMOptions::AllocLowering::None &&
         "LLVMLoweringPass doesn't support AllocLowering::None");
  bool useAlignedAlloc =
      (allocLowering == LowerToLLVMOptions::AllocLowering::AlignedAlloc);
  return std::make_unique<LLVMLoweringPass>(
      options.useBarePtrCallConv, options.emitCWrappers,
      options.getIndexBitwidth(), useAlignedAlloc, options.dataLayout);
}