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
43 lines
2.1 KiB
Plaintext
43 lines
2.1 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) 2022-2025 NVIDIA CORPORATION & AFFILIATES.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
/** @file
|
|
*
|
|
* @brief Main include file for the CUDASTF library.
|
|
*
|
|
* STF pulls `cuda::experimental::places` into `cuda::experimental::stf` via
|
|
* `__stf/internal/stf_places_into_stf_core.cuh` (after `places.cuh` in STF-only
|
|
* headers), `stf_places_extended_exports.cuh` (after `stf::hash`; avoids including
|
|
* `place_partition.cuh`), and `stf_places_partition_into_stf.cuh` where partition
|
|
* APIs are needed. Places headers do not include STF for that bridge.
|
|
*/
|
|
|
|
#pragma once
|
|
|
|
#include <cuda/experimental/__stf/allocators/adapters.cuh>
|
|
#include <cuda/experimental/__stf/allocators/buddy_allocator.cuh>
|
|
#include <cuda/experimental/__stf/allocators/cached_allocator.cuh>
|
|
#include <cuda/experimental/__stf/allocators/pooled_allocator.cuh>
|
|
#include <cuda/experimental/__stf/allocators/uncached_allocator.cuh>
|
|
#include <cuda/experimental/__stf/graph/graph_ctx.cuh>
|
|
// #include <cuda/experimental/__stf/internal/algorithm.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/__stf/internal/context.cuh>
|
|
#include <cuda/experimental/__stf/internal/inner_shape.cuh>
|
|
#include <cuda/experimental/__stf/internal/reducer.cuh>
|
|
#include <cuda/experimental/__stf/internal/scalar_interface.cuh>
|
|
#include <cuda/experimental/__stf/internal/task_dep.cuh>
|
|
#include <cuda/experimental/__stf/internal/void_interface.cuh>
|
|
#include <cuda/experimental/__stf/stackable/stackable_ctx.cuh>
|
|
#include <cuda/experimental/__stf/stream/stream_ctx.cuh>
|
|
#include <cuda/experimental/__stf/utility/run_once.cuh>
|