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
43 lines
1.5 KiB
Plaintext
43 lines
1.5 KiB
Plaintext
//===----------------------------------------------------------------------===//
|
|
//
|
|
// Part of CUDASTF in CUDA C++ Core Libraries,
|
|
// under the Apache License v2.0 with LLVM Exceptions.
|
|
// See https://llvm.org/LICENSE.txt for license information.
|
|
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
|
// SPDX-FileCopyrightText: Copyright (c) 2022-2024 NVIDIA CORPORATION & AFFILIATES.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include <cuda/experimental/__places/place_partition.cuh>
|
|
#include <cuda/experimental/__stf/internal/stf_places_partition_into_stf.cuh>
|
|
#include <cuda/experimental/stf.cuh>
|
|
|
|
using namespace cuda::experimental::stf;
|
|
|
|
#if _CCCL_CTK_AT_LEAST(12, 4)
|
|
/**
|
|
* @brief Test green context partition and affinity: partition by green_context, push/pop affinity per subplace.
|
|
*/
|
|
void test_green_ctx_affinity()
|
|
{
|
|
async_resources_handle handle;
|
|
for (auto p : place_partition(exec_place::current_device(), handle, place_partition_scope::green_context))
|
|
{
|
|
handle.push_affinity(::std::make_shared<exec_place>(p));
|
|
_CCCL_ASSERT(handle.current_affinity().size() == 1, "invalid value");
|
|
handle.pop_affinity();
|
|
}
|
|
}
|
|
#endif // _CCCL_CTK_AT_LEAST(12, 4)
|
|
|
|
int main()
|
|
{
|
|
#if _CCCL_CTK_BELOW(12, 4)
|
|
fprintf(stderr, "Green contexts are not supported by this version of CUDA: skipping test.\n");
|
|
return 0;
|
|
#else // ^^^ _CCCL_CTK_BELOW(12, 4) ^^^ / vvv _CCCL_CTK_AT_LEAST(12, 4) vvv
|
|
test_green_ctx_affinity();
|
|
return 0;
|
|
#endif // ^^^ _CCCL_CTK_AT_LEAST(12, 4) ^^^
|
|
}
|