#pragma once

// clang-format will break include orders
// clang-format off
#include <torch/all.h>

#include <ATen/cuda/CUDAContext.h>

#include "cutlass/cutlass.h"

#include "cute/tensor.hpp"
#include "cute/atom/mma_atom.hpp"
#include "cutlass/numeric_types.h"

#include "cutlass/gemm/device/gemm_universal_adapter.h"
#include "cutlass/gemm/kernel/gemm_universal.hpp"
#include "cutlass/epilogue/collective/collective_builder.hpp"
#include "cutlass/gemm/collective/collective_builder.hpp"

#include "core/math.hpp"
#include "cutlass_extensions/common.hpp"
// clang-format on

/*
  Epilogues defined in,
  csrc/cutlass_extensions/epilogue/scaled_mm_epilogues_c3x.hpp,
  must contain a public type named EVTCompute of type Sm90EVT, as well as a
  static prepare_args function that constructs an EVTCompute::Arguments struct.
*/

using namespace cute;

namespace vllm {

// A wrapper for the GEMM kernel that is used to guard against compilation on
// architectures that will never use the kernel. The purpose of this is to
// reduce the size of the compiled binary.
// __CUDA_ARCH__ is not defined in host code, so this lets us smuggle the ifdef
// into code that will be executed on the device where it is defined.
template <typename Kernel>
struct enable_sm90_or_later : Kernel {
  template <typename... Args>
  CUTLASS_DEVICE void operator()(Args&&... args) {
#if defined __CUDA_ARCH__ && __CUDA_ARCH__ >= 900
    Kernel::operator()(std::forward<Args>(args)...);
#endif
  }
};

template <typename ElementAB_, typename ElementD_,
          template <typename, typename, typename> typename Epilogue_,
          typename TileShape, typename ClusterShape, typename KernelSchedule,
          typename EpilogueSchedule>
struct cutlass_3x_gemm {
  using ElementAB = ElementAB_;
  using ElementD = ElementD_;
  using ElementAcc =
      typename std::conditional<std::is_same_v<ElementAB, int8_t>, int32_t,
                                float>::type;

  using EpilogueDescriptor =
      cutlass::epilogue::collective::detail::EpilogueDescriptor<
          TileShape, cutlass::epilogue::collective::EpilogueTileAuto, ElementD,
          ElementD, EpilogueSchedule>;

  using Epilogue = Epilogue_<ElementAcc, ElementD, EpilogueDescriptor>;

  using StrideD = Stride<int64_t, Int<1>, Int<0>>;
  using ElementC = void;
  using StrideC = StrideD;

  using EVTCompute = typename Epilogue::EVTCompute;

  using CollectiveEpilogue =
      typename cutlass::epilogue::collective::CollectiveBuilder<
          cutlass::arch::Sm90, cutlass::arch::OpClassTensorOp, TileShape,
          ClusterShape, cutlass::epilogue::collective::EpilogueTileAuto,
          ElementAcc, float, ElementC, StrideC, 4, ElementD, StrideD, 4,
          EpilogueSchedule, EVTCompute>::CollectiveOp;

  static constexpr size_t CEStorageSize =
      sizeof(typename CollectiveEpilogue::SharedStorage);
  using Stages = typename cutlass::gemm::collective::StageCountAutoCarveout<
      static_cast<int>(CEStorageSize)>;

  // clang-format off
  using CollectiveMainloop =
      typename cutlass::gemm::collective::CollectiveBuilder<
          cutlass::arch::Sm90, cutlass::arch::OpClassTensorOp, 
          ElementAB, cutlass::layout::RowMajor, 16, 
          ElementAB, cutlass::layout::ColumnMajor, 16, 
          ElementAcc, TileShape, ClusterShape,
          Stages,
          KernelSchedule>::CollectiveOp;
  // clang-format on

  using KernelType = enable_sm90_or_later<cutlass::gemm::kernel::GemmUniversal<
      cute::Shape<int, int, int, int>, CollectiveMainloop, CollectiveEpilogue,
      cutlass::gemm::PersistentScheduler>>;

  struct GemmKernel : public KernelType {};
};

template <typename Gemm, typename... EpilogueArgs>
void cutlass_gemm_caller(torch::Tensor& out, torch::Tensor const& a,
                         torch::Tensor const& b,
                         EpilogueArgs&&... epilogue_params) {
  using ElementAB = typename Gemm::ElementAB;
  using ElementD = typename Gemm::ElementD;

  int32_t m = a.size(0);
  int32_t n = b.size(1);
  int32_t k = a.size(1);

  int64_t lda = a.stride(0);
  int64_t ldb = b.stride(1);
  int64_t ldc = out.stride(0);

  using StrideA = Stride<int64_t, Int<1>, int64_t>;
  using StrideB = Stride<int64_t, Int<1>, int64_t>;
  using StrideC = typename Gemm::StrideC;

  StrideA a_stride{lda, Int<1>{}, 0};
  StrideB b_stride{ldb, Int<1>{}, 0};
  StrideC c_stride{ldc, Int<1>{}, Int<0>{}};

  using GemmKernel = typename Gemm::GemmKernel;
  typename GemmKernel::ProblemShape prob_shape{m, n, k, 1};

  auto a_ptr = static_cast<ElementAB*>(a.data_ptr());
  auto b_ptr = static_cast<ElementAB*>(b.data_ptr());
  typename GemmKernel::MainloopArguments mainloop_args{a_ptr, a_stride, b_ptr,
                                                       b_stride};

  auto c_ptr = static_cast<ElementD*>(out.data_ptr());
  typename GemmKernel::EpilogueArguments epilogue_args{
      Gemm::Epilogue::prepare_args(
          std::forward<EpilogueArgs>(epilogue_params)...),
      c_ptr, c_stride, c_ptr, c_stride};

  typename GemmKernel::Arguments args{cutlass::gemm::GemmUniversalMode::kGemm,
                                      prob_shape, mainloop_args, epilogue_args};

  // Launch the CUTLASS GEMM kernel.
  using GemmOp = cutlass::gemm::device::GemmUniversalAdapter<GemmKernel>;
  GemmOp gemm_op;
  CUTLASS_CHECK(gemm_op.can_implement(args));

  size_t workspace_size = gemm_op.get_workspace_size(args);
  auto const workspace_options =
      torch::TensorOptions().dtype(torch::kUInt8).device(a.device());
  auto workspace = torch::empty(workspace_size, workspace_options);

  auto stream = at::cuda::getCurrentCUDAStream(a.get_device());

  cutlass::Status status = gemm_op.run(args, workspace.data_ptr(), stream);
  CUTLASS_CHECK(status);
}

}  // namespace vllm