disco_cuda.cuh 2.85 KB
Newer Older
Boris Bonev's avatar
Boris Bonev committed
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
// coding=utf-8
//
// SPDX-FileCopyrightText: Copyright (c) 2024 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 "disco.h"

#include <cuda_runtime.h>
#include <c10/cuda/CUDAStream.h>

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

#define DIV_UP(a,b) (((a)+((b)-1))/(b))

#define MIN_THREADS (64)
#define ELXTH_MAX   (32)

// forward kernel
torch::Tensor disco_cuda_fwd(torch::Tensor inp,
                             torch::Tensor roff_idx,
                             torch::Tensor ker_idx,
                             torch::Tensor row_idx,
                             torch::Tensor col_idx,
                             torch::Tensor val,
                             int64_t K,
                             int64_t Ho,
                             int64_t Wo);

// backward kernel
torch::Tensor disco_cuda_bwd(torch::Tensor inp,
                             torch::Tensor roff_idx,
                             torch::Tensor ker_idx,
                             torch::Tensor row_idx,
                             torch::Tensor col_idx,
                             torch::Tensor val,
                             int64_t K,
                             int64_t Ho,
                             int64_t Wo);