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
36 lines
1.1 KiB
C++
36 lines
1.1 KiB
C++
//===----------------------------------------------------------------------===//
|
|
//
|
|
// Part of the LLVM Project, 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
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#ifndef ASAN_TESTING_H
|
|
#define ASAN_TESTING_H
|
|
|
|
#include "test_macros.h"
|
|
|
|
#if _CCCL_HAS_FEATURE(address_sanitizer)
|
|
extern "C" int __sanitizer_verify_contiguous_container(const void* beg, const void* mid, const void* end);
|
|
|
|
template <typename T, typename Alloc>
|
|
bool is_contiguous_container_asan_correct(const std::vector<T, Alloc>& c)
|
|
{
|
|
if (std::is_same<Alloc, std::allocator<T>>::value && c.data() != nullptr)
|
|
{
|
|
return __sanitizer_verify_contiguous_container(c.data(), c.data() + c.size(), c.data() + c.capacity()) != 0;
|
|
}
|
|
return true;
|
|
}
|
|
|
|
#else
|
|
template <typename T, typename Alloc>
|
|
bool is_contiguous_container_asan_correct(const std::vector<T, Alloc>&)
|
|
{
|
|
return true;
|
|
}
|
|
#endif
|
|
|
|
#endif // ASAN_TESTING_H
|