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
36 lines
1.6 KiB
Plaintext
36 lines
1.6 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) 2022-2026 NVIDIA CORPORATION & AFFILIATES.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
/** @file
|
|
*
|
|
* @brief Main include file for the standalone CUDA places library.
|
|
*
|
|
* Provides data_place, exec_place, stream_pool, green context support,
|
|
* place partitioning utilities, and partition strategies (`cyclic_shape`,
|
|
* `cyclic_partition`, `blocked_partition`, `tiled_partition`) without pulling
|
|
* in the full CUDASTF task-graph framework.
|
|
*/
|
|
|
|
#pragma once
|
|
|
|
#include <cuda/experimental/__places/cute_partition.cuh>
|
|
#include <cuda/experimental/__places/exec/cuda_context.cuh>
|
|
#include <cuda/experimental/__places/exec/cuda_stream.cuh>
|
|
#include <cuda/experimental/__places/exec/green_context.cuh>
|
|
#include <cuda/experimental/__places/exec/green_ctx_view.cuh>
|
|
#include <cuda/experimental/__places/localized_array.cuh>
|
|
#include <cuda/experimental/__places/machine.cuh>
|
|
#include <cuda/experimental/__places/partitions/blocked_partition.cuh>
|
|
#include <cuda/experimental/__places/partitions/cyclic_shape.cuh>
|
|
#include <cuda/experimental/__places/partitions/tiled_partition.cuh>
|
|
#include <cuda/experimental/__places/place_partition.cuh>
|
|
#include <cuda/experimental/__places/places.cuh>
|
|
#include <cuda/experimental/__places/stream_pool.cuh>
|