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
94 lines
3.4 KiB
Plaintext
94 lines
3.4 KiB
Plaintext
//===----------------------------------------------------------------------===//
|
|
//
|
|
// Part of CUDA Experimental in CUDA C++ Core Libraries,
|
|
// 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.
|
|
//
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
#include "common.cuh"
|
|
|
|
C2H_TEST("Fill", "[data_manipulation]")
|
|
{
|
|
cuda::stream _stream{cuda::device_ref{0}};
|
|
SECTION("Host resource")
|
|
{
|
|
cuda::mr::legacy_pinned_memory_resource host_resource;
|
|
cudax::uninitialized_buffer<int, cuda::mr::device_accessible> buffer(host_resource, buffer_size);
|
|
|
|
cuda::fill_bytes(_stream, buffer, fill_byte);
|
|
|
|
check_result_and_erase(_stream, cuda::std::span(buffer));
|
|
}
|
|
|
|
SECTION("Device resource")
|
|
{
|
|
cuda::device_memory_pool_ref device_resource = cuda::device_default_memory_pool(cuda::device_ref{0});
|
|
cudax::uninitialized_buffer<int, cuda::mr::device_accessible> buffer(device_resource, buffer_size);
|
|
cuda::fill_bytes(_stream, buffer, fill_byte);
|
|
|
|
std::vector<int> host_vector(42);
|
|
REQUIRE_CUDART(cudaMemcpyAsync(
|
|
host_vector.data(), buffer.data(), buffer.size() * sizeof(int), cudaMemcpyDefault, _stream.get()));
|
|
|
|
check_result_and_erase(_stream, host_vector);
|
|
}
|
|
SECTION("Launch transform")
|
|
{
|
|
cuda::mr::legacy_pinned_memory_resource host_resource;
|
|
cudax::weird_buffer buffer(host_resource, buffer_size);
|
|
|
|
cuda::fill_bytes(_stream, buffer, fill_byte);
|
|
check_result_and_erase(_stream, cuda::std::span(buffer.data, buffer.size));
|
|
}
|
|
}
|
|
|
|
C2H_TEST("Mdspan Fill", "[data_manipulation]")
|
|
{
|
|
cuda::stream stream{cuda::device_ref{0}};
|
|
{
|
|
cuda::std::dextents<size_t, 3> dynamic_extents{1, 2, 3};
|
|
auto buffer = make_buffer_for_mdspan(dynamic_extents, 0);
|
|
cuda::std::mdspan<int, decltype(dynamic_extents)> dynamic_mdspan(buffer.data(), dynamic_extents);
|
|
|
|
cuda::fill_bytes(stream, dynamic_mdspan, fill_byte);
|
|
check_result_and_erase(stream, cuda::std::span(buffer.data(), buffer.size()));
|
|
}
|
|
{
|
|
cuda::std::extents<size_t, 2, cuda::std::dynamic_extent, 4> mixed_extents{1};
|
|
auto buffer = make_buffer_for_mdspan(mixed_extents, 0);
|
|
cuda::std::mdspan<int, decltype(mixed_extents)> mixed_mdspan(buffer.data(), mixed_extents);
|
|
|
|
cuda::fill_bytes(stream, cuda::std::move(mixed_mdspan), fill_byte);
|
|
check_result_and_erase(stream, cuda::std::span(buffer.data(), buffer.size()));
|
|
}
|
|
{
|
|
cuda::mr::legacy_pinned_memory_resource host_resource;
|
|
using static_extents = cuda::std::extents<size_t, 2, 3, 4>;
|
|
auto size = cuda::std::layout_left::mapping<static_extents>().required_span_size();
|
|
cudax::weird_buffer<cuda::std::mdspan<int, static_extents>> buffer(host_resource, size);
|
|
|
|
cuda::fill_bytes(stream, buffer, fill_byte);
|
|
check_result_and_erase(stream, cuda::std::span(buffer.data, buffer.size));
|
|
}
|
|
}
|
|
|
|
C2H_TEST("Non exhaustive mdspan fill_bytes", "[data_manipulation]")
|
|
{
|
|
cuda::stream stream{cuda::device_ref{0}};
|
|
{
|
|
auto fake_strided_mdspan = create_fake_strided_mdspan();
|
|
|
|
try
|
|
{
|
|
cuda::fill_bytes(stream, fake_strided_mdspan, fill_byte);
|
|
}
|
|
catch (const ::std::invalid_argument& e)
|
|
{
|
|
CHECK(e.what() == ::std::string("fill_bytes supports only exhaustive mdspans"));
|
|
}
|
|
}
|
|
}
|