123456789101112131415161718192021222324252627282930313233343536373839404142434445 |
- //---------------------------------------------------------------------------//
- // Copyright (c) 2013-2014 Kyle Lutz <kyle.r.lutz@gmail.com>
- //
- // Distributed under the Boost Software License, Version 1.0
- // See accompanying file LICENSE_1_0.txt or copy at
- // http://www.boost.org/LICENSE_1_0.txt
- //
- // See http://boostorg.github.com/compute for more information.
- //---------------------------------------------------------------------------//
- #include <algorithm>
- #include <cstdlib>
- #include <iostream>
- #include <thrust/copy.h>
- #include <thrust/device_vector.h>
- #include <thrust/generate.h>
- #include <thrust/host_vector.h>
- #include <thrust/reduce.h>
- #include "perf.hpp"
- int main(int argc, char *argv[])
- {
- perf_parse_args(argc, argv);
- std::cout << "size: " << PERF_N << std::endl;
- thrust::host_vector<int> h_vec = generate_random_vector<int>(PERF_N);
- // transfer data to the device
- thrust::device_vector<int> d_vec = h_vec;
- int sum = 0;
- perf_timer t;
- for(size_t trial = 0; trial < PERF_TRIALS; trial++){
- t.start();
- sum = thrust::reduce(d_vec.begin(), d_vec.end());
- cudaDeviceSynchronize();
- t.stop();
- }
- std::cout << "time: " << t.min_time() / 1e6 << " ms" << std::endl;
- std::cout << "sum: " << sum << std::endl;
- return 0;
- }
|