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
31 lines
1007 B
Plaintext
31 lines
1007 B
Plaintext
// SPDX-FileCopyrightText: Copyright (c) 2011-2023, NVIDIA CORPORATION. All rights reserved.
|
|
// SPDX-License-Identifier: BSD-3
|
|
|
|
#include <thrust/device_vector.h>
|
|
#include <thrust/execution_policy.h>
|
|
#include <thrust/reduce.h>
|
|
|
|
#include "nvbench_helper.cuh"
|
|
|
|
template <typename T>
|
|
static void basic(nvbench::state& state, nvbench::type_list<T>)
|
|
{
|
|
const auto elements = static_cast<std::size_t>(state.get_int64("Elements"));
|
|
|
|
thrust::device_vector<T> in = generate(elements);
|
|
|
|
state.add_element_count(elements);
|
|
state.add_global_memory_reads<T>(elements);
|
|
state.add_global_memory_writes<T>(1);
|
|
|
|
caching_allocator_t alloc;
|
|
state.exec(nvbench::exec_tag::gpu | nvbench::exec_tag::sync, [&](nvbench::launch& launch) {
|
|
do_not_optimize(thrust::reduce(policy(alloc, launch), in.begin(), in.end()));
|
|
});
|
|
}
|
|
|
|
NVBENCH_BENCH_TYPES(basic, NVBENCH_TYPE_AXES(fundamental_types))
|
|
.set_name("base")
|
|
.set_type_axes_names({"T{ct}"})
|
|
.add_int64_power_of_two_axis("Elements", nvbench::range(16, 28, 4));
|