[INFRA] Import NVIDIA/CCCL upstream as optimization reference library
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
This commit is contained in:
48
cccl_upstream/cudax/test/stf/dot/basic.cu
Normal file
48
cccl_upstream/cudax/test/stf/dot/basic.cu
Normal file
@@ -0,0 +1,48 @@
|
||||
//===----------------------------------------------------------------------===//
|
||||
//
|
||||
// Part of CUDASTF 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) 2022-2024 NVIDIA CORPORATION & AFFILIATES.
|
||||
//
|
||||
//===----------------------------------------------------------------------===//
|
||||
|
||||
/**
|
||||
* @file
|
||||
* @brief This test makes sure we can generate a dot file
|
||||
*/
|
||||
|
||||
#include <cuda/experimental/stf.cuh>
|
||||
|
||||
using namespace cuda::experimental::stf;
|
||||
|
||||
int main()
|
||||
{
|
||||
// TODO (miscco): Make it work for windows
|
||||
#if !_CCCL_COMPILER(MSVC)
|
||||
// Generate a random filename
|
||||
int r = rand();
|
||||
|
||||
char filename[64];
|
||||
snprintf(filename, 64, "output_%d.dot", r);
|
||||
// fprintf(stderr, "filename %s\n", filename);
|
||||
setenv("CUDASTF_DOT_FILE", filename, 1);
|
||||
|
||||
stream_ctx ctx;
|
||||
|
||||
auto lA = ctx.logical_data(shape_of<slice<char>>(64));
|
||||
ctx.task(lA.write())->*[](cudaStream_t, auto) {};
|
||||
ctx.task(lA.rw())->*[](cudaStream_t, auto) {};
|
||||
ctx.finalize();
|
||||
|
||||
// Call this explicitly for the purpose of the test
|
||||
reserved::dot::instance().finish();
|
||||
|
||||
// Make sure the file exists, and erase it
|
||||
// fprintf(stderr, "ERASE. ...\n");
|
||||
EXPECT(access(filename, F_OK) != -1);
|
||||
|
||||
EXPECT(unlink(filename) == 0);
|
||||
#endif // !_CCCL_COMPILER(MSVC)
|
||||
}
|
||||
Reference in New Issue
Block a user