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
52 lines
1.6 KiB
Plaintext
52 lines
1.6 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 <cuda/experimental/__stream/stream.cuh>
|
|
#include <cuda/experimental/__utility/ensure_current_device.cuh>
|
|
#include <cuda/experimental/launch.cuh>
|
|
|
|
#include <utility.cuh>
|
|
|
|
namespace driver = cuda::__driver;
|
|
|
|
void recursive_check_device_setter(int id)
|
|
{
|
|
int cudart_id;
|
|
cudax::__ensure_current_device setter(cuda::device_ref{id});
|
|
REQUIRE(test::count_driver_stack() == cuda::devices.size() - id);
|
|
auto ctx = driver::__ctxGetCurrent();
|
|
REQUIRE_CUDART(cudaGetDevice(&cudart_id));
|
|
REQUIRE(cudart_id == id);
|
|
|
|
if (id != 0)
|
|
{
|
|
recursive_check_device_setter(id - 1);
|
|
|
|
REQUIRE(test::count_driver_stack() == cuda::devices.size() - id);
|
|
REQUIRE(ctx == driver::__ctxGetCurrent());
|
|
REQUIRE_CUDART(cudaGetDevice(&cudart_id));
|
|
REQUIRE(cudart_id == id);
|
|
}
|
|
}
|
|
|
|
C2H_TEST("ensure current device", "[device]")
|
|
{
|
|
test::empty_driver_stack();
|
|
// If possible use something different than REQUIRE_CUDART default 0
|
|
int target_device = static_cast<int>(cuda::devices.size() - 1);
|
|
|
|
SECTION("device setter")
|
|
{
|
|
recursive_check_device_setter(target_device);
|
|
|
|
REQUIRE(test::count_driver_stack() == 0);
|
|
}
|
|
}
|