// Copyright (c) 2022, ETH Zurich and UNC Chapel Hill.
// 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 ETH Zurich and UNC Chapel Hill 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 AND CONTRIBUTORS "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 HOLDERS 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.
//
// Author: Johannes L. Schoenberger (jsch-at-demuc-dot-de)

#include "mvs/gpu_mat_prng.h"

namespace colmap {
namespace mvs {
namespace {

__global__ void InitRandomStateKernel(GpuMat<curandState> output) {
  const size_t row = blockIdx.y * blockDim.y + threadIdx.y;
  const size_t col = blockIdx.x * blockDim.x + threadIdx.x;

  const size_t uniqueBlockIndex = blockIdx.y * gridDim.x + blockIdx.x;
  const size_t id = uniqueBlockIndex * blockDim.y * blockDim.x +
                    threadIdx.y * blockDim.x + threadIdx.x;

  // Each thread gets same seed, a different sequence number, no offset.
  if (col < output.GetWidth() && row < output.GetHeight()) {
    curand_init(id, 0, 0, &output.GetRef(row, col));
  }
}

}  // namespace

GpuMatPRNG::GpuMatPRNG(const int width, const int height)
    : GpuMat(width, height) {
  InitRandomStateKernel<<<gridSize_, blockSize_>>>(*this);
}

}  // namespace mvs
}  // namespace colmap