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
55 lines
1.4 KiB
Plaintext
55 lines
1.4 KiB
Plaintext
#include <thrust/copy.h>
|
|
#include <thrust/device_vector.h>
|
|
#include <thrust/reduce.h>
|
|
|
|
#include <cuda/iterator>
|
|
|
|
#include <iostream>
|
|
#include <iterator>
|
|
|
|
// This example computes a run-length code [1] for an array of characters.
|
|
//
|
|
// [1] http://en.wikipedia.org/wiki/Run-length_encoding
|
|
|
|
int main()
|
|
{
|
|
// input data on the host
|
|
const char data[] = "aaabbbbbcddeeeeeeeeeff";
|
|
|
|
const size_t N = (sizeof(data) / sizeof(char)) - 1;
|
|
|
|
// copy input data to the device
|
|
thrust::device_vector<char> input(data, data + N);
|
|
|
|
// allocate storage for output data and run lengths
|
|
thrust::device_vector<char> output(N);
|
|
thrust::device_vector<int> lengths(N);
|
|
|
|
// print the initial data
|
|
std::cout << "input data:" << '\n';
|
|
thrust::copy(input.begin(), input.end(), std::ostream_iterator<char>(std::cout, ""));
|
|
std::cout << '\n' << '\n';
|
|
|
|
// compute run lengths
|
|
size_t num_runs =
|
|
thrust::reduce_by_key(
|
|
input.begin(),
|
|
input.end(), // input key sequence
|
|
cuda::constant_iterator<int>(1), // input value sequence
|
|
output.begin(), // output key sequence
|
|
lengths.begin() // output value sequence
|
|
)
|
|
.first
|
|
- output.begin(); // compute the output size
|
|
|
|
// print the output
|
|
std::cout << "run-length encoded output:" << '\n';
|
|
for (size_t i = 0; i < num_runs; i++)
|
|
{
|
|
std::cout << "(" << output[i] << "," << lengths[i] << ")";
|
|
}
|
|
std::cout << '\n';
|
|
|
|
return 0;
|
|
}
|