image_framework_ymj/include/open3d/ml/contrib/cuda_utils.h
2024-12-06 16:25:16 +08:00

63 lines
2.5 KiB
C++
Executable File

// ----------------------------------------------------------------------------
// - Open3D: www.open3d.org -
// ----------------------------------------------------------------------------
// Copyright (c) 2018-2023 www.open3d.org
// SPDX-License-Identifier: MIT
// ----------------------------------------------------------------------------
//***************************************************************************************/
//
// Based on Pointnet2 Library (MIT License):
// https://github.com/sshaoshuai/Pointnet2.PyTorch
//
// Copyright (c) 2019 Shaoshuai Shi
//
// Permission is hereby granted, free of charge, to any person obtaining a
// copy of this software and associated documentation files (the "Software"),
// to deal in the Software without restriction, including without limitation
// the rights to use, copy, modify, merge, publish, distribute, sublicense,
// and/or sell copies of the Software, and to permit persons to whom the
// Software is furnished to do so, subject to the following conditions:
//
// The above copyright notice and this permission notice shall be included in
// all copies or substantial portions of the Software.
//
// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
// IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
// FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
// THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
// LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
// FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER
// DEALINGS IN THE SOFTWARE.
//
//***************************************************************************************/
#pragma once
#include <cmath>
namespace open3d {
namespace ml {
namespace contrib {
#define TOTAL_THREADS 1024
#define THREADS_PER_BLOCK 256
#define DIVUP(m, n) ((m) / (n) + ((m) % (n) > 0))
inline int OptNumThreads(int work_size) {
const int pow_2 = std::log(static_cast<double>(work_size)) / std::log(2.0);
return max(min(1 << pow_2, TOTAL_THREADS), 1);
}
inline dim3 OptBlockConfig(int x, int y) {
const int x_threads = OptNumThreads(x);
const int y_threads =
max(min(OptNumThreads(y), TOTAL_THREADS / x_threads), 1);
dim3 block_config(x_threads, y_threads, 1);
return block_config;
}
} // namespace contrib
} // namespace ml
} // namespace open3d