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
47 lines
1.7 KiB
Plaintext
47 lines
1.7 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) 2026 NVIDIA CORPORATION & AFFILIATES.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#ifndef _CUDA_STD_NUMERIC
|
|
#define _CUDA_STD_NUMERIC
|
|
|
|
#include <cuda/std/detail/__config>
|
|
|
|
#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 <cuda/std/__numeric/accumulate.h>
|
|
#include <cuda/std/__numeric/adjacent_difference.h>
|
|
#include <cuda/std/__numeric/exclusive_scan.h>
|
|
#include <cuda/std/__numeric/gcd_lcm.h>
|
|
#include <cuda/std/__numeric/inclusive_scan.h>
|
|
#include <cuda/std/__numeric/inner_product.h>
|
|
#include <cuda/std/__numeric/iota.h>
|
|
#include <cuda/std/__numeric/midpoint.h>
|
|
#include <cuda/std/__numeric/partial_sum.h>
|
|
#include <cuda/std/__numeric/reduce.h>
|
|
#include <cuda/std/__numeric/saturating_add.h>
|
|
#include <cuda/std/__numeric/saturating_cast.h>
|
|
#include <cuda/std/__numeric/saturating_div.h>
|
|
#include <cuda/std/__numeric/saturating_mul.h>
|
|
#include <cuda/std/__numeric/saturating_sub.h>
|
|
#include <cuda/std/__numeric/transform_exclusive_scan.h>
|
|
#include <cuda/std/__numeric/transform_inclusive_scan.h>
|
|
#include <cuda/std/__numeric/transform_reduce.h>
|
|
|
|
// standard mandated include
|
|
#include <cuda/std/version>
|
|
|
|
#endif // _CUDA_STD_NUMERIC
|