cutlass/include/cutlass/conv/kernel/sm90_implicit_gemm_tma_warpspecialized.hpp

/***************************************************************************************************
 * Copyright (c) 2023 - 2024 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.
 *
 **************************************************************************************************/
#pragma once

#include "cutlass/cutlass.h"
#include "cutlass/fast_math.h"
#include "cutlass/kernel_hardware_info.hpp"

#include "cute/tensor.hpp"
#include "cute/arch/cluster_sm90.hpp"

#include "cutlass/conv/detail.hpp"
#include "cutlass/conv/convolution.h"
#include "cutlass/conv/dispatch_policy.hpp"
#include "cutlass/gemm/dispatch_policy.hpp"
#include "cutlass/pipeline/sm90_pipeline.hpp"
#include "cutlass/gemm/kernel/gemm_universal.hpp"
#include "cutlass/gemm/kernel/tile_scheduler.hpp"

///////////////////////////////////////////////////////////////////////////////

namespace cutlass::conv::kernel {

///////////////////////////////////////////////////////////////////////////////

template <
  class ProblemShape_,
  class CollectiveMainloop_,
  class CollectiveEpilogue_,
  class TileScheduler_
>
class ConvUniversal<
  ProblemShape_,
  CollectiveMainloop_,
  CollectiveEpilogue_,
  TileScheduler_,
  cute::enable_if_t<cute::is_base_of_v<KernelImplicitTmaWarpSpecializedSm90, typename CollectiveMainloop_::DispatchPolicy::Schedule>>
> : public cutlass::gemm::kernel::GemmUniversal< 
  ProblemShape_, 
  CollectiveMainloop_, 
  CollectiveEpilogue_, 
  TileScheduler_
>
{};
///////////////////////////////////////////////////////////////////////////////

} // namespace cutlass::conv::kernel