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
41 lines
828 B
Plaintext
41 lines
828 B
Plaintext
#include <thrust/device_vector.h>
|
|
#include <thrust/host_vector.h>
|
|
|
|
#include <iostream>
|
|
|
|
int main()
|
|
{
|
|
// H holds 4 integers
|
|
thrust::host_vector<int> H{14, 20, 38, 46};
|
|
|
|
// H.size() returns the size of vector H
|
|
std::cout << "H has size " << H.size() << '\n';
|
|
|
|
// print contents of H
|
|
for (size_t i = 0; i < H.size(); i++)
|
|
{
|
|
std::cout << "H[" << i << "] = " << H[i] << '\n';
|
|
}
|
|
|
|
// resize H
|
|
H.resize(2);
|
|
|
|
std::cout << "H now has size " << H.size() << '\n';
|
|
|
|
// Copy host_vector H to device_vector D
|
|
thrust::device_vector<int> D = H;
|
|
|
|
// elements of D can be modified
|
|
D[0] = 99;
|
|
D[1] = 88;
|
|
|
|
// print contents of D
|
|
for (size_t i = 0; i < D.size(); i++)
|
|
{
|
|
std::cout << "D[" << i << "] = " << D[i] << '\n';
|
|
}
|
|
|
|
// H and D are automatically deleted when the function returns
|
|
return 0;
|
|
}
|