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
35 lines
1.2 KiB
Plaintext
35 lines
1.2 KiB
Plaintext
//===----------------------------------------------------------------------===//
|
|
//
|
|
// Part of CUDA Experimental 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) 2024 NVIDIA CORPORATION & AFFILIATES.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include <cuda/std/execution>
|
|
#include <cuda/std/type_traits>
|
|
|
|
#include <cuda/experimental/execution.cuh>
|
|
|
|
#include <testing.cuh>
|
|
|
|
namespace cudax = cuda::experimental;
|
|
|
|
template <class T, class U>
|
|
using is_same = cuda::std::is_same<cuda::std::remove_cvref_t<T>, U>;
|
|
|
|
C2H_TEST("Execution policies", "[execution][policies]")
|
|
{
|
|
namespace execution = cuda::std::execution;
|
|
SECTION("Individual options")
|
|
{
|
|
cudax::execution::any_execution_policy pol = execution::seq;
|
|
pol = execution::par;
|
|
pol = execution::par_unseq;
|
|
pol = execution::unseq;
|
|
CHECK(pol == execution::unseq);
|
|
}
|
|
}
|