#pragma once

#include "mlir/Dialect/Tensor/IR/Tensor.h"
#include "mlir/IR/BuiltinTypes.h"
#include "mlir/IR/Value.h"
#include "mlir/IR/ValueRange.h"
#include "mlir/Transforms/DialectConversion.h"

#include "llvm/ADT/ArrayRef.h"
#include "llvm/ADT/DenseMap.h"
#include "llvm/ADT/SmallVector.h"

#include <cassert>
#include <cstddef>
#include <optional>
#include <type_traits>
#include <utility>

namespace onnx_mlir {

using HSliceId = size_t;
using CoreId = size_t;

template <class A, class B, class C = std::common_type_t<A, B>>
constexpr C ceilIntegerDivide(A a, B b) {
  static_assert(std::is_integral_v<A>, "A must be an integer type");
  static_assert(std::is_integral_v<B>, "B must be an integer type");
  C ac = static_cast<C>(a);
  C bc = static_cast<C>(b);
  return 1 + (ac - 1) / bc;
}

template <class A, class B, class C = std::common_type_t<A, B>>
constexpr std::pair<C, C> ceilIntegerDivideWithRemainder(A a, B b) {
  static_assert(std::is_integral_v<A>, "A must be an integer type");
  static_assert(std::is_integral_v<B>, "B must be an integer type");
  C ac = static_cast<C>(a);
  C bc = static_cast<C>(b);
  return {ceilIntegerDivide(ac, bc), ac % bc};
}

template <class T>
bool isVectorShape(mlir::ArrayRef<T> shape) {
  return shape.size() == 2 && (shape[0] == 1 || shape[1] == 1);
}

template <class T>
bool isMatrixShape(mlir::ArrayRef<T> shape) {
  return shape.size() == 2;
}

template <class T>
bool isHVectorShape(mlir::ArrayRef<T> shape) {
  return shape.size() == 2 && shape[0] == 1;
}

inline auto getTensorShape(mlir::Value tensor) {
  return mlir::cast<mlir::RankedTensorType>(tensor.getType()).getShape();
}

inline bool haveSameStaticShape(mlir::Value lhs, mlir::Value rhs) {
  auto lhsType = mlir::dyn_cast<mlir::RankedTensorType>(lhs.getType());
  auto rhsType = mlir::dyn_cast<mlir::RankedTensorType>(rhs.getType());
  return lhsType && rhsType && lhsType.hasStaticShape() && rhsType.hasStaticShape()
      && lhsType.getShape() == rhsType.getShape();
}

bool hasStaticPositiveShape(mlir::ArrayRef<int64_t> shape);

bool hasStaticPositiveShape(mlir::RankedTensorType type);

int64_t getStaticShapeElementCount(mlir::ArrayRef<int64_t> shape);

llvm::SmallVector<int64_t> permuteShape(mlir::ArrayRef<int64_t> shape, mlir::ArrayRef<int64_t> permutation);

llvm::SmallVector<int64_t> invertPermutation(mlir::ArrayRef<int64_t> permutation);

mlir::FailureOr<llvm::SmallVector<int64_t>> getTransposePermutationChecked(std::optional<mlir::ArrayAttr> permAttr,
                                                                           int64_t rank);

mlir::Value transposeMaybeInCompute(mlir::Value value,
                                    mlir::RankedTensorType resultType,
                                    mlir::ArrayRef<int64_t> permutation,
                                    mlir::PatternRewriter& rewriter,
                                    mlir::Location loc);

llvm::SmallVector<mlir::OpFoldResult> getUnitStrides(mlir::PatternRewriter& rewriter, int64_t rank);

llvm::SmallVector<mlir::OpFoldResult> getZeroOffsets(mlir::PatternRewriter& rewriter, int64_t rank);

llvm::SmallVector<mlir::OpFoldResult> getStaticSizes(mlir::PatternRewriter& rewriter, mlir::ArrayRef<int64_t> shape);

/// Slices a statically shaped tensor along one axis into contiguous pieces of
/// at most `sliceSize` elements.
llvm::SmallVector<mlir::Value> sliceTensor(const mlir::Value& tensorToSlice,
                                           size_t axis,
                                           int64_t sliceSize,
                                           mlir::ConversionPatternRewriter& rewriter,
                                           mlir::Location loc);

llvm::SmallVector<mlir::Value> sliceVector(const mlir::Value& vectorToSlice,
                                           int64_t sliceSize,
                                           mlir::ConversionPatternRewriter& rewriter,
                                           mlir::Location loc);

/// Partitions one logical vector into per-core crossbar-sized slices using the
/// current PIM target geometry.
llvm::DenseMap<CoreId, llvm::SmallVector<mlir::Value>> sliceVectorPerCrossbarPerCore(
  const mlir::Value& vectorToSlice, mlir::ConversionPatternRewriter& rewriter, mlir::Location loc);

mlir::Value extractAxisSlice(
  mlir::PatternRewriter& rewriter, mlir::Location loc, mlir::Value source, int64_t axis, int64_t offset, int64_t size);

mlir::Value insertStaticSlice(mlir::PatternRewriter& rewriter,
                              mlir::Location loc,
                              mlir::Value source,
                              mlir::Value dest,
                              llvm::ArrayRef<mlir::OpFoldResult> offsets);

} // namespace onnx_mlir