/***************************************************************************************************
 * Copyright (c) 2025 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
 * SPDX-License-Identifier: BSD-3-Clause
 *
 * Redistribution and use in source and binary forms, with or without
 * modification, are permitted provided that the following conditions are met:
 *
 * 1. Redistributions of source code must retain the above copyright notice, this
 * list of conditions and the following disclaimer.
 *
 * 2. 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.
 *
 * 3. Neither the name of the copyright holder 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 HOLDER 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.
 *
 **************************************************************************************************/

/// Helper to initialize a block of device data
template <class Element, class Layout>
bool initialize_tensor(
    cutlass::TensorView<Element, Layout> view,
    cutlass::Distribution::Kind dist_kind,
    uint64_t seed) {

  if (dist_kind == cutlass::Distribution::Uniform) {

    double scope_max, scope_min;
    int bits_input = cutlass::sizeof_bits<Element>::value;

    if (bits_input == 1) {
      scope_max = 2;
      scope_min = 0;
    } 
    else if (bits_input <= 8) {
      scope_max = 2;
      scope_min = -2;
    } 
    else if (bits_input == 16) {
      scope_max = 5;
      scope_min = -5;
    } 
    else {
      scope_max = 8;
      scope_min = -8;
    }

    cutlass::reference::host::TensorFillRandomUniform(
      view, seed, scope_max, scope_min, 0);
  }
  else if (dist_kind == cutlass::Distribution::AllZeros) {
    cutlass::reference::host::TensorFill(view);
  }
  else if (dist_kind == cutlass::Distribution::Identity) {

    cutlass::reference::host::TensorFillIdentity(view);
  }
  else if (dist_kind == cutlass::Distribution::Gaussian) {

    cutlass::reference::host::TensorFillRandomGaussian(view, seed, 0, 0.5);
  }
  else if (dist_kind == cutlass::Distribution::Sequential) {
    cutlass::reference::host::BlockFillSequential(view.data(), view.capacity());
  }
  else {
    throw std::runtime_error("Not implementated.");
  }

  return true;
}