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
76 lines
1.7 KiB
Plaintext
76 lines
1.7 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 An example of Fibonacci sequence illustrating how we can use
|
|
* dynamically created logical data
|
|
*/
|
|
|
|
#include <cuda/experimental/stf.cuh>
|
|
|
|
using namespace cuda::experimental::stf;
|
|
|
|
int fibo_ref(int n)
|
|
{
|
|
if (n < 2)
|
|
{
|
|
return n;
|
|
}
|
|
else
|
|
{
|
|
return fibo_ref(n - 1) + fibo_ref(n - 2);
|
|
}
|
|
}
|
|
|
|
__global__ void add(slice<int> out, const slice<const int> in1, const slice<const int> in2)
|
|
{
|
|
out(0) = in1(0) + in2(0);
|
|
}
|
|
|
|
__global__ void set(slice<int> out, int val)
|
|
{
|
|
out(0) = val;
|
|
}
|
|
|
|
logical_data<slice<int>> compute_fibo(context& ctx, int n)
|
|
{
|
|
auto out = ctx.logical_data(shape_of<slice<int>>(1));
|
|
if (n < 2)
|
|
{
|
|
ctx.task(out.write())->*[=](cudaStream_t s, auto sout) {
|
|
set<<<1, 1, 0, s>>>(sout, n);
|
|
};
|
|
}
|
|
else
|
|
{
|
|
auto fib1 = compute_fibo(ctx, n - 1);
|
|
auto fib2 = compute_fibo(ctx, n - 2);
|
|
ctx.task(fib1.read(), fib2.read(), out.write())->*[=](cudaStream_t s, auto s1, auto s2, auto sout) {
|
|
add<<<1, 1, 0, s>>>(sout, s1, s2);
|
|
};
|
|
}
|
|
|
|
return out;
|
|
}
|
|
|
|
int main(int argc, char** argv)
|
|
{
|
|
int n = (argc > 1) ? atoi(argv[1]) : 4;
|
|
|
|
context ctx; // = graph_ctx();
|
|
auto result = compute_fibo(ctx, n);
|
|
ctx.host_launch(result.read())->*[&](auto res) {
|
|
EXPECT(res(0) == fibo_ref(n));
|
|
};
|
|
ctx.finalize();
|
|
}
|