// MIT License
//
// Copyright (c) 2025 Advanced Micro Devices, Inc. All rights reserved.
//
// Permission is hereby granted, free of charge, to any person obtaining a copy
// of this software and associated documentation files (the "Software"), to deal
// in the Software without restriction, including without limitation the rights
// to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
// copies of the Software, and to permit persons to whom the Software is
// furnished to do so, subject to the following conditions:
//
// The above copyright notice and this permission notice shall be included in all
// copies or substantial portions of the Software.
//
// THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
// IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
// FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
// AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
// LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
// OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
// SOFTWARE.

// [sphinx-start]
#include <hip/hip_runtime.h>

#include <cstddef>
#include <cstdlib>
#include <iostream>

#define HIP_CHECK(expression)                \
{                                            \
    const hipError_t status = expression;    \
    if(status != hipSuccess)                 \
    {                                        \
            std::cerr << "HIP error "        \
                << status << ": "            \
                << hipGetErrorString(status) \
                << " at " << __FILE__ << ":" \
                << __LINE__ << std::endl;    \
    }                                        \
}

__device__ unsigned long long fibonacci(unsigned long long n)
{
    if (n == 0 || n == 1)
    {
        return n;
    }
    return fibonacci(n - 1) + fibonacci(n - 2);
}

__global__ void kernel(unsigned long long n)
{
    unsigned long long result = fibonacci(n);
    const std::size_t x = threadIdx.x + blockDim.x * blockIdx.x;

    if (x == 0)
        printf("%llu! = %llu \n", n, result);
}

int main()
{
    kernel<<<1, 1>>>(10);
    HIP_CHECK(hipDeviceSynchronize());

    // With -O0 optimization option hit the stack limit
    // kernel<<<1, 256>>>(2048);
    // HIP_CHECK(hipDeviceSynchronize());

    return EXIT_SUCCESS;
}
// [sphinx-end]