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
965 B
Plaintext
32 lines
965 B
Plaintext
// SPDX-FileCopyrightText: Copyright (c) 2011, Duane Merrill. All rights reserved.
|
|
// SPDX-FileCopyrightText: Copyright (c) 2011-2020, NVIDIA CORPORATION. All rights reserved.
|
|
// SPDX-License-Identifier: BSD-3
|
|
|
|
#pragma once
|
|
|
|
#include <cub/config.cuh>
|
|
|
|
CUB_NAMESPACE_BEGIN
|
|
|
|
#ifndef _CCCL_DOXYGEN_INVOKED // Do not document
|
|
|
|
namespace detail
|
|
{
|
|
/**
|
|
* @brief Helper class template that allows overwriting the `BLOCK_THREAD` and `ITEMS_PER_THREAD`
|
|
* configurations of a given policy.
|
|
*/
|
|
// TODO(bgruber): this should be called something like "override_policy"
|
|
template <typename PolicyT, int BLOCK_THREADS_, int ITEMS_PER_THREAD_ = PolicyT::ITEMS_PER_THREAD>
|
|
struct policy_wrapper_t : PolicyT
|
|
{
|
|
static constexpr int ITEMS_PER_THREAD = ITEMS_PER_THREAD_;
|
|
static constexpr int BLOCK_THREADS = BLOCK_THREADS_;
|
|
static constexpr int ITEMS_PER_TILE = BLOCK_THREADS * ITEMS_PER_THREAD;
|
|
};
|
|
} // namespace detail
|
|
|
|
#endif // _CCCL_DOXYGEN_INVOKED
|
|
|
|
CUB_NAMESPACE_END
|