dedf08166a
Added 863 files from NVIDIA/cccl sparse checkout: - c2h/ (27 files): Catch2 test helpers — generators, validators, runner - nvbench_helper/ (10 files): Benchmark harness utilities - cmake/ (29 files): CMake presets and build helpers - cudax/ (794 files): Experimental CUDA extensions - AGENTS.md: NVIDIA's official AI agent instructions for CCCL - CMakePresets.json: Standardized build configurations - cccl-version.json: Version tracking Also added CCCL_ASSET_MAP.md mapping all 4295 CCCL files to competition value and PRD items. cccl_upstream now covers 100% of competition-critical assets: - 27 tuning headers (SM80/90/100 benchmark data) - 32 dispatch headers (algorithm implementations) - 60 Thrust examples (correctness verification) - 217 CUB Catch2 tests (regression matrix) - 153 CUB benchmarks (parameter space search) - 18 CUB examples (API verification) - 27 test helpers + benchmark harness - 794 cudax experimental extensions
104 lines
2.5 KiB
Plaintext
104 lines
2.5 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) 2026 NVIDIA CORPORATION & AFFILIATES.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#ifndef COMMON_GROUP_CUH
|
|
#define COMMON_GROUP_CUH
|
|
|
|
#include <cuda/barrier>
|
|
#include <cuda/std/cstddef>
|
|
#include <cuda/std/type_traits>
|
|
#include <cuda/warp>
|
|
|
|
#include <cuda/experimental/group.cuh>
|
|
|
|
#include "testing.cuh"
|
|
|
|
namespace
|
|
{
|
|
template <class T, cuda::std::size_t Id>
|
|
__device__ T global_barriers_storage;
|
|
|
|
//! @brief Returns reference to an array of N cuda::barrier objects with suitable thread scope for level allocated in
|
|
//! suitable address space (shared or device memory). Id parameter can be used to create unique object.
|
|
template <cuda::std::size_t N, cuda::std::size_t Id = 0, class Level>
|
|
__device__ auto& get_barriers(const Level& level) noexcept
|
|
{
|
|
constexpr auto scope = cudax::__minimum_required_scope_for<Level>();
|
|
|
|
using Barrier = cuda::barrier<scope>;
|
|
using BarriersStorage = cuda::std::aligned_storage_t<N * sizeof(Barrier), alignof(Barrier)>;
|
|
|
|
if constexpr (scope >= cuda::thread_scope_block)
|
|
{
|
|
__shared__ BarriersStorage shared_barriers_storage;
|
|
return reinterpret_cast<Barrier(&)[N]>(shared_barriers_storage);
|
|
}
|
|
else
|
|
{
|
|
return reinterpret_cast<Barrier(&)[N]>(global_barriers_storage<BarriersStorage, Id>);
|
|
}
|
|
}
|
|
|
|
struct ThreadsInWarpMappingResult
|
|
{
|
|
__device__ static constexpr ::cuda::std::size_t static_group_count()
|
|
{
|
|
return 1;
|
|
}
|
|
|
|
__device__ unsigned group_count() const
|
|
{
|
|
return 1;
|
|
}
|
|
|
|
__device__ unsigned group_rank() const
|
|
{
|
|
return 0;
|
|
}
|
|
|
|
__device__ static constexpr ::cuda::std::size_t static_unit_count()
|
|
{
|
|
return 32;
|
|
}
|
|
|
|
__device__ unsigned unit_count() const
|
|
{
|
|
return 32;
|
|
}
|
|
|
|
__device__ unsigned unit_rank() const
|
|
{
|
|
return cuda::gpu_thread.rank_as<unsigned>(cuda::warp);
|
|
}
|
|
|
|
__device__ cuda::device::lane_mask lane_mask() const noexcept
|
|
{
|
|
return cuda::device::lane_mask::all();
|
|
}
|
|
|
|
__device__ bool is_valid() const
|
|
{
|
|
return true;
|
|
}
|
|
|
|
__device__ static constexpr bool is_always_exhaustive() noexcept
|
|
{
|
|
return true;
|
|
}
|
|
|
|
__device__ static constexpr bool is_always_contiguous() noexcept
|
|
{
|
|
return true;
|
|
}
|
|
};
|
|
} // namespace
|
|
|
|
#endif // COMMON_GROUP_CUH
|