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
47 lines
1.4 KiB
Plaintext
47 lines
1.4 KiB
Plaintext
#include <thrust/functional.h>
|
|
#include <thrust/set_operations.h>
|
|
#include <thrust/sort.h>
|
|
|
|
#include <unittest/unittest.h>
|
|
|
|
template <typename U>
|
|
void TestSetIntersectionKeyValue(size_t n)
|
|
{
|
|
using T = key_value<U, U>;
|
|
|
|
thrust::host_vector<U> h_keys_a = unittest::random_integers<U>(n);
|
|
thrust::host_vector<U> h_values_a = unittest::random_integers<U>(n);
|
|
|
|
thrust::host_vector<U> h_keys_b = unittest::random_integers<U>(n);
|
|
thrust::host_vector<U> h_values_b = unittest::random_integers<U>(n);
|
|
|
|
thrust::host_vector<T> h_a(n), h_b(n);
|
|
for (size_t i = 0; i < n; ++i)
|
|
{
|
|
h_a[i] = T(h_keys_a[i], h_values_a[i]);
|
|
h_b[i] = T(h_keys_b[i], h_values_b[i]);
|
|
}
|
|
|
|
thrust::stable_sort(h_a.begin(), h_a.end());
|
|
thrust::stable_sort(h_b.begin(), h_b.end());
|
|
|
|
thrust::device_vector<T> d_a = h_a;
|
|
thrust::device_vector<T> d_b = h_b;
|
|
|
|
thrust::host_vector<T> h_result(n);
|
|
thrust::device_vector<T> d_result(n);
|
|
|
|
typename thrust::host_vector<T>::iterator h_end;
|
|
typename thrust::device_vector<T>::iterator d_end;
|
|
|
|
h_end = thrust::set_intersection(h_a.begin(), h_a.end(), h_b.begin(), h_b.end(), h_result.begin());
|
|
h_result.resize(h_end - h_result.begin());
|
|
|
|
d_end = thrust::set_intersection(d_a.begin(), d_a.end(), d_b.begin(), d_b.end(), d_result.begin());
|
|
|
|
d_result.resize(d_end - d_result.begin());
|
|
|
|
ASSERT_EQUAL_QUIET(h_result, d_result);
|
|
}
|
|
DECLARE_VARIABLE_UNITTEST(TestSetIntersectionKeyValue);
|