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
32 lines
706 B
Plaintext
32 lines
706 B
Plaintext
#include <thrust/device_free.h>
|
|
#include <thrust/device_malloc.h>
|
|
#include <thrust/device_ptr.h>
|
|
#include <thrust/device_vector.h>
|
|
|
|
#include <cuda.h>
|
|
|
|
int main()
|
|
{
|
|
size_t N = 10;
|
|
|
|
// create a device_ptr
|
|
thrust::device_ptr<int> dev_ptr = thrust::device_malloc<int>(N);
|
|
|
|
// extract raw pointer from device_ptr
|
|
int* raw_ptr = thrust::raw_pointer_cast(dev_ptr);
|
|
|
|
// use raw_ptr in CUDA API functions
|
|
cudaMemset(raw_ptr, 0, N * sizeof(int));
|
|
|
|
// free memory
|
|
thrust::device_free(dev_ptr);
|
|
|
|
// we can use the same approach for device_vector
|
|
thrust::device_vector<int> d_vec(N);
|
|
|
|
// note: d_vec.data() returns a device_ptr
|
|
raw_ptr = thrust::raw_pointer_cast(d_vec.data());
|
|
|
|
return 0;
|
|
}
|