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
57 lines
1.5 KiB
C++
57 lines
1.5 KiB
C++
// -*- C++ -*-
|
|
//===----------------------------------------------------------------------===//
|
|
//
|
|
// Part of the LLVM Project, 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) 2023 NVIDIA CORPORATION & AFFILIATES.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
#ifndef LIBCXX_TEST_SUPPORT_INDIRECTLY_READABLE_H
|
|
#define LIBCXX_TEST_SUPPORT_INDIRECTLY_READABLE_H
|
|
|
|
#include <cuda/std/type_traits>
|
|
|
|
#include "test_macros.h"
|
|
|
|
template <class Token>
|
|
struct Common
|
|
{};
|
|
|
|
template <class Token>
|
|
struct T1 : Common<Token>
|
|
{};
|
|
|
|
template <class Token>
|
|
struct T2 : Common<Token>
|
|
{};
|
|
|
|
namespace cuda::std
|
|
{
|
|
template <template <class> class T1Qual, template <class> class T2Qual, class Token>
|
|
struct basic_common_reference<T1<Token>, T2<Token>, T1Qual, T2Qual>
|
|
{
|
|
using type = Common<Token>;
|
|
};
|
|
template <template <class> class T2Qual, template <class> class T1Qual, class Token>
|
|
struct basic_common_reference<T2<Token>, T1<Token>, T2Qual, T1Qual>
|
|
: basic_common_reference<T1<Token>, T2<Token>, T1Qual, T2Qual>
|
|
{};
|
|
} // namespace cuda::std
|
|
|
|
template <class Token>
|
|
struct IndirectlyReadable
|
|
{
|
|
using value_type = T1<Token>;
|
|
TEST_FUNC T2<Token>& operator*() const;
|
|
};
|
|
|
|
template <class Token>
|
|
struct IndirectlyReadable2
|
|
{
|
|
using value_type = T1<Token>;
|
|
TEST_FUNC T2<Token>& operator*() const;
|
|
};
|
|
|
|
#endif // LIBCXX_TEST_SUPPORT_INDIRECTLY_READABLE_H
|