/* 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.
 */

#ifndef _SIMPLETEXTURE_KERNEL_H_
#define _SIMPLETEXTURE_KERNEL_H_
#include <cuda.h>

////////////////////////////////////////////////////////////////////////////////
//! Transform an image using texture lookups
//! @param g_odata  output data in global memory
////////////////////////////////////////////////////////////////////////////////
extern "C" __global__ void transformKernel(float *g_odata, int width,
                                           int height, float theta,
                                           CUtexObject tex) {
  // calculate normalized texture coordinates
  unsigned int x = blockIdx.x * blockDim.x + threadIdx.x;
  unsigned int y = blockIdx.y * blockDim.y + threadIdx.y;

  float u = (float)x - (float)width / 2;
  float v = (float)y - (float)height / 2;
  float tu = u * cosf(theta) - v * sinf(theta);
  float tv = v * cosf(theta) + u * sinf(theta);

  tu /= (float)width;
  tv /= (float)height;

  // read from texture and write to global memory
  g_odata[y * width + x] = tex2D<float>(tex, tu + 0.5f, tv + 0.5f);
}

#endif  // #ifndef _SIMPLETEXTURE_KERNEL_H_