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
62 lines
1.8 KiB
Plaintext
62 lines
1.8 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 NVIDIA CORPORATION & AFFILIATES.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#ifndef _CUDA_STD_CLIMITS
|
|
#define _CUDA_STD_CLIMITS
|
|
|
|
#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
|
|
|
|
#if _CCCL_HOSTED()
|
|
# include <climits>
|
|
#else // ^^^ _CCCL_HOSTED() ^^^ / vvv _CCCL_FREESTANDING() vvv
|
|
# define _CCCL_CHAR_IS_UNSIGNED() ('\xff' > 0) // CURSED
|
|
|
|
# define CHAR_BIT 8
|
|
|
|
# define SCHAR_MIN (-128)
|
|
# define SCHAR_MAX 127
|
|
# define UCHAR_MAX 255
|
|
|
|
# if _CCCL_CHAR_IS_UNSIGNED()
|
|
# define CHAR_MIN 0
|
|
# define CHAR_MAX UCHAR_MAX
|
|
# else
|
|
# define CHAR_MIN SCHAR_MIN
|
|
# define CHAR_MAX SCHAR_MAX
|
|
# endif
|
|
# define SHRT_MIN (-SHRT_MAX - 1)
|
|
# define SHRT_MAX 0x7fff
|
|
# define USHRT_MAX 0xffff
|
|
# define INT_MIN (-INT_MAX - 1)
|
|
# define INT_MAX 0x7fffffff
|
|
# define UINT_MAX 0xffffffff
|
|
# define LONG_MIN (-LONG_MAX - 1)
|
|
# ifdef __LP64__
|
|
# define LONG_MAX LLONG_MAX
|
|
# define ULONG_MAX ULLONG_MAX
|
|
# else
|
|
# define LONG_MAX INT_MAX
|
|
# define ULONG_MAX UINT_MAX
|
|
# endif
|
|
# define LLONG_MIN (-LLONG_MAX - 1)
|
|
# define LLONG_MAX 0x7fffffffffffffffLL
|
|
# define ULLONG_MAX 0xffffffffffffffffUL
|
|
#endif // _CCCL_FREESTANDING()
|
|
|
|
#endif // _CUDA_STD_CLIMITS
|