dedf08166a
Added 863 files from NVIDIA/cccl sparse checkout: - c2h/ (27 files): Catch2 test helpers — generators, validators, runner - nvbench_helper/ (10 files): Benchmark harness utilities - cmake/ (29 files): CMake presets and build helpers - cudax/ (794 files): Experimental CUDA extensions - AGENTS.md: NVIDIA's official AI agent instructions for CCCL - CMakePresets.json: Standardized build configurations - cccl-version.json: Version tracking Also added CCCL_ASSET_MAP.md mapping all 4295 CCCL files to competition value and PRD items. cccl_upstream now covers 100% of competition-critical assets: - 27 tuning headers (SM80/90/100 benchmark data) - 32 dispatch headers (algorithm implementations) - 60 Thrust examples (correctness verification) - 217 CUB Catch2 tests (regression matrix) - 153 CUB benchmarks (parameter space search) - 18 CUB examples (API verification) - 27 test helpers + benchmark harness - 794 cudax experimental extensions
50 lines
1.6 KiB
Plaintext
50 lines
1.6 KiB
Plaintext
//===----------------------------------------------------------------------===//
|
|
//
|
|
// 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 with sections
|
|
*/
|
|
|
|
#include <cuda/experimental/stf.cuh>
|
|
|
|
using namespace cuda::experimental::stf;
|
|
|
|
int main()
|
|
{
|
|
// TODO (miscco): Make it work for windows
|
|
#if !_CCCL_COMPILER(MSVC)
|
|
context ctx;
|
|
auto lA = ctx.token().set_symbol("A");
|
|
auto lB = ctx.token().set_symbol("B");
|
|
auto lC = ctx.token().set_symbol("C");
|
|
|
|
// Begin a top-level section named "foo"
|
|
auto s_foo = ctx.dot_section("foo");
|
|
for (size_t i = 0; i < 2; i++)
|
|
{
|
|
// Section named "bar" using RAII
|
|
auto s_bar = ctx.dot_section("bar");
|
|
ctx.task(lA.read(), lB.rw()).set_symbol("t1")->*[](cudaStream_t) {};
|
|
for (size_t j = 0; j < 2; j++)
|
|
{
|
|
// Section named "baz" using RAII
|
|
auto s_bar = ctx.dot_section("baz");
|
|
ctx.task(lA.read(), lC.rw()).set_symbol("t2")->*[](cudaStream_t) {};
|
|
ctx.task(lB.read(), lC.read(), lA.rw()).set_symbol("t3")->*[](cudaStream_t) {};
|
|
// Implicit end of section "baz"
|
|
}
|
|
// Implicit end of section "bar"
|
|
}
|
|
s_foo.end(); // Explicit end of section "foo"
|
|
ctx.finalize();
|
|
#endif // !_CCCL_COMPILER(MSVC)
|
|
}
|