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
60 lines
2.1 KiB
Plaintext
60 lines
2.1 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) 2024 NVIDIA CORPORATION & AFFILIATES.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#ifndef _CUDA_STD_CFLOAT
|
|
#define _CUDA_STD_CFLOAT
|
|
|
|
#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 <cfloat>
|
|
#else // ^^^ _CCCL_HOSTED() ^^^ / vvv _CCCL_FREESTANDING() vvv
|
|
# define FLT_RADIX 2
|
|
# define DECIMAL_DIG DBL_DECIMAL_DIG
|
|
# define FLT_ROUNDS 1
|
|
# define FLT_EVAL_METHOD 0
|
|
|
|
# define FLT_DECIMAL_DIG 9
|
|
# define FLT_MIN 1.17549435082228750796873653722224568e-38f
|
|
# define FLT_TRUE_MIN 1.40129846432481707092372958328991613e-45f
|
|
# define FLT_MAX 3.40282346638528859811704183484516925e+38f
|
|
# define FLT_EPSILON 1.19209289550781250000000000000000000e-7f
|
|
# define FLT_DIG 6
|
|
# define FLT_MANT_DIG 24
|
|
# define FLT_MIN_EXP (-125)
|
|
# define FLT_MIN_10_EXP (-37)
|
|
# define FLT_MAX_EXP 128
|
|
# define FLT_MAX_10_EXP 38
|
|
# define FLT_HAS_SUBNORM 1
|
|
|
|
# define DBL_DECIMAL_DIG 17
|
|
# define DBL_MIN 2.22507385850720138309023271733240406e-308
|
|
# define DBL_TRUE_MIN 4.94065645841246544176568792868221372e-324
|
|
# define DBL_MAX 1.79769313486231570814527423731704357e+308
|
|
# define DBL_EPSILON 2.22044604925031308084726333618164062e-16
|
|
# define DBL_DIG 15
|
|
# define DBL_MANT_DIG 53
|
|
# define DBL_MIN_EXP (-1021)
|
|
# define DBL_MIN_10_EXP (-307)
|
|
# define DBL_MAX_EXP 1024
|
|
# define DBL_MAX_10_EXP 308
|
|
# define DBL_HAS_SUBNORM 1
|
|
#endif // ^^^ _CCCL_FREESTANDING() ^^^
|
|
|
|
#endif // _CUDA_STD_CFLOAT
|