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
28 lines
1.1 KiB
Plaintext
28 lines
1.1 KiB
Plaintext
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
|
// SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES.
|
|
#pragma once
|
|
|
|
#include <cub/config.cuh>
|
|
|
|
#if defined(_CCCL_IMPLICIT_SYSTEM_HEADER_GCC)
|
|
# pragma GCC system_header
|
|
#elif defined(_CCCL_IMPLICIT_SYSTEM_HEADER_CLANG)
|
|
# pragma clang system_header
|
|
#elif defined(_CCCL_IMPLICIT_SYSTEM_HEADER_MSVC)
|
|
# pragma system_header
|
|
#endif // no system header
|
|
|
|
#include <cub/detail/warpspeed/allocators/smem_allocator.cuh>
|
|
#include <cub/detail/warpspeed/constant_assert.cuh>
|
|
#include <cub/detail/warpspeed/make_warp_uniform.cuh>
|
|
#include <cub/detail/warpspeed/resource/smem_phase.cuh>
|
|
#include <cub/detail/warpspeed/resource/smem_ref.cuh>
|
|
#include <cub/detail/warpspeed/resource/smem_resource.cuh>
|
|
#include <cub/detail/warpspeed/resource/smem_resource_raw.cuh>
|
|
#include <cub/detail/warpspeed/resource/smem_stage.cuh>
|
|
#include <cub/detail/warpspeed/special_registers.cuh>
|
|
#include <cub/detail/warpspeed/squad/squad.cuh>
|
|
#include <cub/detail/warpspeed/squad/squad_desc.cuh>
|
|
#include <cub/detail/warpspeed/sync_handler.cuh>
|
|
#include <cub/detail/warpspeed/values.cuh>
|