// coding=utf-8
//
// SPDX-FileCopyrightText: Copyright (c) 2025 The torch-harmonics Authors. All rights reserved.
// SPDX-License-Identifier: BSD-3-Clause
//
// Redistribution and use in source and binary forms, with or without
// modification, are permitted provided that the following conditions are met:
//
// 1. Redistributions of source code must retain the above copyright notice, this
// list of conditions and the following disclaimer.
//
// 2. Redistributions in binary form must reproduce the above copyright notice,
// this list of conditions and the following disclaimer in the documentation
// and/or other materials provided with the distribution.
//
// 3. Neither the name of the copyright holder nor the names of its
// contributors may be used to endorse or promote products derived from
// this software without specific prior written permission.
//
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
// AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
// IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
// DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE
// FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
// DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
// SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
// CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
// OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
// OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

#pragma once

#include <cmath>
#include <cstdint>
#include <torch/torch.h>

#define CHECK_CUDA_TENSOR(x) TORCH_CHECK(x.device().is_cuda(), #x " must be a CUDA tensor")

torch::Tensor s2_attention_fwd_cuda(at::Tensor kx, at::Tensor vx,
                                    at::Tensor qy, at::Tensor quad_weights,
                                    at::Tensor psi_col_idx,
                                    at::Tensor psi_row_off,
                                    int nlon_in, int nlat_out, int nlon_out);

std::tuple<at::Tensor,at::Tensor,at::Tensor> s2_attention_bwd_dkvq_cuda(at::Tensor kx, at::Tensor vx,
                                         at::Tensor qy,
                                         at::Tensor dy,
                                         at::Tensor quad_weights,
                                         at::Tensor psi_col_idx,
                                         at::Tensor psi_row_off,
                                         int nlon_in, int nlat_out, int nlon_out);