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
1.0 KiB
Plaintext
32 lines
1.0 KiB
Plaintext
#include <thrust/iterator/detail/minimum_system.h>
|
|
|
|
#include <cuda/std/type_traits>
|
|
|
|
#include "catch2_test_helper.h"
|
|
|
|
template <typename System, typename SeqSystem>
|
|
void check()
|
|
{
|
|
STATIC_REQUIRE(cuda::std::is_convertible_v<System, SeqSystem>);
|
|
STATIC_REQUIRE(!cuda::std::is_convertible_v<SeqSystem, System>);
|
|
STATIC_REQUIRE(cuda::std::is_same_v<thrust::detail::minimum_system_t<SeqSystem, System>, SeqSystem>);
|
|
STATIC_REQUIRE(cuda::std::is_same_v<thrust::detail::minimum_system_t<System, SeqSystem>, SeqSystem>);
|
|
}
|
|
|
|
TEST_CASE("host and device systems convert to sequential", "[minimum_system]")
|
|
{
|
|
using seq = decltype(thrust::seq);
|
|
using seq_tag = decltype(thrust::seq)::tag_type;
|
|
using dev = decltype(thrust::device);
|
|
using dev_tag = thrust::device_system_tag;
|
|
using host = decltype(thrust::host);
|
|
using host_tag = thrust::host_system_tag;
|
|
|
|
check<dev, seq>();
|
|
check<dev_tag, seq>();
|
|
check<dev, seq_tag>();
|
|
check<dev_tag, seq_tag>();
|
|
check<host, seq_tag>();
|
|
check<host_tag, seq_tag>();
|
|
}
|