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
25 lines
860 B
Plaintext
25 lines
860 B
Plaintext
#include <thrust/binary_search.h>
|
|
#include <thrust/device_vector.h>
|
|
#include <thrust/distance.h>
|
|
#include <thrust/sequence.h>
|
|
|
|
#include <cuda/std/utility>
|
|
|
|
#include <unittest/unittest.h>
|
|
|
|
void TestEqualRangeOnStream()
|
|
{ // Regression test for GH issue #921 (nvbug 2173437)
|
|
using vector_t = typename thrust::device_vector<int>;
|
|
using iterator_t = typename vector_t::iterator;
|
|
using result_t = cuda::std::pair<iterator_t, iterator_t>;
|
|
|
|
vector_t input(10);
|
|
thrust::sequence(thrust::device, input.begin(), input.end(), 0);
|
|
cudaStream_t stream = nullptr;
|
|
result_t result = thrust::equal_range(thrust::cuda::par.on(stream), input.begin(), input.end(), 5);
|
|
|
|
ASSERT_EQUAL(5, ::cuda::std::distance(input.begin(), result.first));
|
|
ASSERT_EQUAL(6, ::cuda::std::distance(input.begin(), result.second));
|
|
}
|
|
DECLARE_UNITTEST(TestEqualRangeOnStream);
|