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
40 lines
892 B
Plaintext
40 lines
892 B
Plaintext
#include <thrust/device_vector.h>
|
|
#include <thrust/functional.h>
|
|
#include <thrust/generate.h>
|
|
#include <thrust/host_vector.h>
|
|
#include <thrust/random.h>
|
|
#include <thrust/reduce.h>
|
|
|
|
#include <iostream>
|
|
|
|
int my_rand()
|
|
{
|
|
static thrust::default_random_engine rng;
|
|
static thrust::uniform_int_distribution<int> dist(0, 9999);
|
|
return dist(rng);
|
|
}
|
|
|
|
int main()
|
|
{
|
|
// generate random data on the host
|
|
thrust::host_vector<int> h_vec(100);
|
|
thrust::generate(h_vec.begin(), h_vec.end(), my_rand);
|
|
|
|
// transfer to device and compute sum
|
|
thrust::device_vector<int> d_vec = h_vec;
|
|
|
|
// initial value of the reduction
|
|
int init = 0;
|
|
|
|
// binary operation used to reduce values
|
|
cuda::std::plus<int> binary_op;
|
|
|
|
// compute sum on the device
|
|
int sum = thrust::reduce(d_vec.begin(), d_vec.end(), init, binary_op);
|
|
|
|
// print the sum
|
|
std::cout << "sum is " << sum << '\n';
|
|
|
|
return 0;
|
|
}
|