56fd68e7dd
CCCL (CUDA C++ Core Libraries) provides: - CUB: device/block/warp-level GPU primitives (reduce, scan, sort, topk) - Thrust: high-level parallel algorithms (transform_reduce, sort, scan) - libcudacxx: CUDA C++ standard library (atomics, barriers, memory) - cudax: experimental features (memory resources, allocators) - Tuning policies: per-SM hardware-specific algorithm parameters Competition optimization vectors mapped to CCCL: - Output TPS (83% weight): warp_reduce, block_reduce, device_topk - Input TPS (14% weight): device_scan, block_load, prefetch - Cache TPS (3% weight): prefix caching strategy patterns - Memory (0.9 util): pooled/cached/buddy allocators Source: https://github.com/NVIDIA/cccl (shallow clone, HEAD only) License: Apache-2.0
51 lines
1.5 KiB
C++
51 lines
1.5 KiB
C++
/*
|
|
* SPDX-FileCopyrightText: Copyright (c) 2023-2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
|
|
* SPDX-License-Identifier: Apache-2.0
|
|
*
|
|
* Licensed under the Apache License, Version 2.0 (the "License");
|
|
* you may not use this file except in compliance with the License.
|
|
* You may obtain a copy of the License at
|
|
*
|
|
* http://www.apache.org/licenses/LICENSE-2.0
|
|
*
|
|
* Unless required by applicable law or agreed to in writing, software
|
|
* distributed under the License is distributed on an "AS IS" BASIS,
|
|
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
* See the License for the specific language governing permissions and
|
|
* limitations under the License.
|
|
*/
|
|
|
|
#include <thrust/device_vector.h>
|
|
#include <thrust/reduce.h>
|
|
|
|
#include <iostream>
|
|
|
|
int main()
|
|
{
|
|
constexpr std::size_t N = 1000;
|
|
thrust::device_vector<int> data(N, 1);
|
|
|
|
const auto result = thrust::reduce(data.cbegin(), data.cend());
|
|
|
|
std::cout << "Sum: " << result << '\n';
|
|
|
|
if (result != N)
|
|
{
|
|
std::cerr << "Error: Expected sum of " << N << ", but got " << result << '\n';
|
|
return 1;
|
|
}
|
|
|
|
std::cout << "Detected device system: ";
|
|
#if THRUST_DEVICE_SYSTEM == THRUST_DEVICE_SYSTEM_CUDA
|
|
std::cout << "CUDA" << '\n';
|
|
#elif THRUST_DEVICE_SYSTEM == THRUST_DEVICE_SYSTEM_TBB
|
|
std::cout << "TBB" << '\n';
|
|
#elif THRUST_DEVICE_SYSTEM == THRUST_DEVICE_SYSTEM_OMP
|
|
std::cout << "OMP" << '\n';
|
|
#elif THRUST_DEVICE_SYSTEM == THRUST_DEVICE_SYSTEM_CPP
|
|
std::cout << "CPP" << '\n';
|
|
#endif
|
|
|
|
return 0;
|
|
}
|