/* 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.
 */

__global__ void Copy(TColor *dst, int imageW, int imageH,
                     cudaTextureObject_t texImage) {
  const int ix = blockDim.x * blockIdx.x + threadIdx.x;
  const int iy = blockDim.y * blockIdx.y + threadIdx.y;
  // Add half of a texel to always address exact texel centers
  const float x = (float)ix + 0.5f;
  const float y = (float)iy + 0.5f;

  if (ix < imageW && iy < imageH) {
    float4 fresult = tex2D<float4>(texImage, x, y);
    dst[imageW * iy + ix] = make_color(fresult.x, fresult.y, fresult.z, 0);
  }
}

extern "C" void cuda_Copy(TColor *d_dst, int imageW, int imageH,
                          cudaTextureObject_t texImage) {
  dim3 threads(BLOCKDIM_X, BLOCKDIM_Y);
  dim3 grid(iDivUp(imageW, BLOCKDIM_X), iDivUp(imageH, BLOCKDIM_Y));

  Copy<<<grid, threads>>>(d_dst, imageW, imageH, texImage);
}