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
39 lines
2.0 KiB
Plaintext
39 lines
2.0 KiB
Plaintext
//===----------------------------------------------------------------------===//
|
|
//
|
|
// Part of libcu++, the C++ Standard Library for your entire system,
|
|
// 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) 2023-24 NVIDIA CORPORATION & AFFILIATES.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#ifndef _CUDA__CCCL_CONFIG
|
|
#define _CUDA__CCCL_CONFIG
|
|
|
|
#include <cuda/std/__cccl/architecture.h> // IWYU pragma: export
|
|
#include <cuda/std/__cccl/assert.h> // IWYU pragma: export
|
|
#include <cuda/std/__cccl/attributes.h> // IWYU pragma: export
|
|
#include <cuda/std/__cccl/builtin.h> // IWYU pragma: export
|
|
#include <cuda/std/__cccl/compiler.h> // IWYU pragma: export
|
|
#include <cuda/std/__cccl/cuda_capabilities.h> // IWYU pragma: export
|
|
#include <cuda/std/__cccl/cuda_toolkit.h> // IWYU pragma: export
|
|
#include <cuda/std/__cccl/deprecated.h> // IWYU pragma: export
|
|
#include <cuda/std/__cccl/diagnostic.h> // IWYU pragma: export
|
|
#include <cuda/std/__cccl/dialect.h> // IWYU pragma: export
|
|
#include <cuda/std/__cccl/exceptions.h> // IWYU pragma: export
|
|
#include <cuda/std/__cccl/execution_space.h> // IWYU pragma: export
|
|
#include <cuda/std/__cccl/extended_data_types.h> // IWYU pragma: export
|
|
#include <cuda/std/__cccl/host_std_lib.h> // IWYU pragma: export
|
|
#include <cuda/std/__cccl/os.h> // IWYU pragma: export
|
|
#include <cuda/std/__cccl/preprocessor.h> // IWYU pragma: export
|
|
#include <cuda/std/__cccl/ptx_isa.h> // IWYU pragma: export
|
|
#include <cuda/std/__cccl/rtti.h> // IWYU pragma: export
|
|
#include <cuda/std/__cccl/sequence_access.h> // IWYU pragma: export
|
|
#include <cuda/std/__cccl/system_header.h> // IWYU pragma: export
|
|
#include <cuda/std/__cccl/unreachable.h> // IWYU pragma: export
|
|
#include <cuda/std/__cccl/version.h> // IWYU pragma: export
|
|
#include <cuda/std/__cccl/visibility.h> // IWYU pragma: export
|
|
|
|
#endif // _CUDA__CCCL_CONFIG
|