/* Copyright (c) 2021, NVIDIA CORPORATION. All rights reserved.
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions
 * are met:
 *  * Redistributions of source code must retain the above copyright
 *    notice, this list of conditions and the following disclaimer.
 *  * Redistributions in binary form must reproduce the above copyright
 *    notice, this list of conditions and the following disclaimer in the
 *    documentation and/or other materials provided with the distribution.
 *  * Neither the name of NVIDIA CORPORATION nor the names of its
 *    contributors may be used to endorse or promote products derived
 *    from this software without specific prior written permission.
 *
 * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS ``AS IS'' AND ANY
 * EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
 * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR
 * PURPOSE ARE DISCLAIMED.  IN NO EVENT SHALL THE COPYRIGHT OWNER OR
 * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL,
 * EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO,
 * PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR
 * PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY
 * OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 * OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */

/*
 * This application demonstrates how to use the CUDA API to use multiple GPUs.
 *
 * Note that in order to detect multiple GPUs in your system you have to disable
 * SLI in the nvidia control panel. Otherwise only one GPU is visible to the
 * application. On the other side, you can still extend your desktop to screens
 * attached to both GPUs.
 */

#ifndef SIMPLEMULTIGPU_H
#define SIMPLEMULTIGPU_H

typedef struct {
  // Host-side input data
  int dataN;
  float *h_Data;

  // Partial sum for this GPU
  float *h_Sum;

  // Device buffers
  float *d_Data, *d_Sum;

  // Reduction copied back from GPU
  float *h_Sum_from_device;

  // Stream for asynchronous command execution
  cudaStream_t stream;

} TGPUplan;

extern "C" void launch_reduceKernel(float *d_Result, float *d_Input, int N,
                                    int BLOCK_N, int THREAD_N, cudaStream_t &s);

#endif