/* Copyright (c) 2022, 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.
 */

// includes, kernels
#include "sharedmem.cuh"

////////////////////////////////////////////////////////////////////////////////
//! Simple test kernel for device functionality
//! @param g_idata  input data in global memory
//! @param g_odata  output data in global memory
////////////////////////////////////////////////////////////////////////////////

template <class T>
__device__ void testKernel(T *g_idata, T *g_odata) {
  // Shared mem size is determined by the host app at run time
  SharedMemory<T> smem;

  T *sdata = smem.getPointer();

  // access thread id
  const unsigned int tid = threadIdx.x;

  // access number of threads in this block
  const unsigned int num_threads = blockDim.x;

  // read in input data from global memory
  sdata[tid] = g_idata[tid];

  __syncthreads();

  // perform some computations
  sdata[tid] = (T)num_threads * sdata[tid];

  __syncthreads();

  // write data to global memory
  g_odata[tid] = sdata[tid];
}

extern "C" __global__ void testFloat(float *p1, float *p2) {
  testKernel<float>(p1, p2);
}

extern "C" __global__ void testInt(int *p1, int *p2) {
  testKernel<int>(p1, p2);
}