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
48 lines
1.0 KiB
C++
48 lines
1.0 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 DEFAULTONLY_H
|
|
#define DEFAULTONLY_H
|
|
|
|
#include <cuda/std/cassert>
|
|
|
|
#include "test_macros.h"
|
|
|
|
class DefaultOnly
|
|
{
|
|
int data_;
|
|
|
|
TEST_FUNC DefaultOnly(const DefaultOnly&);
|
|
TEST_FUNC DefaultOnly& operator=(const DefaultOnly&);
|
|
|
|
public:
|
|
STATIC_MEMBER_VAR(count, int)
|
|
|
|
TEST_FUNC DefaultOnly()
|
|
: data_(-1)
|
|
{
|
|
++count();
|
|
}
|
|
TEST_FUNC ~DefaultOnly()
|
|
{
|
|
data_ = 0;
|
|
--count();
|
|
}
|
|
|
|
TEST_FUNC friend bool operator==(const DefaultOnly& x, const DefaultOnly& y)
|
|
{
|
|
return x.data_ == y.data_;
|
|
}
|
|
TEST_FUNC friend bool operator<(const DefaultOnly& x, const DefaultOnly& y)
|
|
{
|
|
return x.data_ < y.data_;
|
|
}
|
|
};
|
|
|
|
#endif // DEFAULTONLY_H
|