mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-03 13:11:25 +00:00
7b6451b68e
* Pooling 2D/3D with refernce * Tests & cleanup - added test for ppoling - cleanup - removed 2d example * Comment resolution - README added - example target name rectified - appropriate arg description and comments added * clang-format * appropriate blocksize calc * modifications for future indexing addition - instead of transforming views we now transform the descriptors, so that the same descriptor can be re-used for index tensor in the future * some basic fixes * comment resolutions * comment resolutions --------- Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
34 lines
1.1 KiB
C++
34 lines
1.1 KiB
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2025, Advanced Micro Devices, Inc. All rights reserved.
|
|
|
|
#pragma once
|
|
|
|
#include "ck_tile/core.hpp"
|
|
|
|
namespace ck_tile {
|
|
|
|
template <typename InDataType_,
|
|
typename OutDataType_,
|
|
typename ComputeDataType_,
|
|
typename IndexDataType_,
|
|
typename ReduceOp_,
|
|
bool OutputIndex_,
|
|
bool PropagateNan_,
|
|
typename BlockShape_>
|
|
struct PoolProblem
|
|
{
|
|
using InDataType = remove_cvref_t<InDataType_>;
|
|
using OutDataType = remove_cvref_t<OutDataType_>;
|
|
using ComputeDataType = remove_cvref_t<ComputeDataType_>;
|
|
using IndexDataType = remove_cvref_t<IndexDataType_>;
|
|
using BlockShape = remove_cvref_t<BlockShape_>;
|
|
using ReduceOp = ReduceOp_;
|
|
using OutputIndex = bool_constant<OutputIndex_>;
|
|
using PropagateNan = bool_constant<PropagateNan_>;
|
|
|
|
static constexpr bool kNeedCrossLaneSync = BlockShape::ThreadPerWarp_N > 1;
|
|
static constexpr bool kNeedCrossWarpSync = BlockShape::WarpPerBlock_N > 1;
|
|
};
|
|
|
|
} // namespace ck_tile
|