mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-04 05:31:24 +00:00
a2f01141aa
* add transpose load; no real logic * fix some compile errors * fix some issues * update transpose load logic * add some fixes * fix a distribution issue * update some codes * add some fix * can pass; but no logic * transpose load enable * update tile transpose * miss output tile distribution mapping * hack for transpose 16x16 * update output tensor distribution * delete unused variables * fix transpose related codes * update transpose load example * exchange the iteration order * fix 16x16 related dimension transpose * fix a transpose index issue * fix a transpose index issue * fix clang format check * update load tile transpose related codes * fix compile errors and pass 16x16 tests * fix a typo * update logic * check other data types * add transpose load api * update transpose load api * fix clang format check * change file name * refactor codes * update code name * delete some unused codes * delete the unused oob flag for transpose load * update tensor view api for transpose load * update for testing * fix a typo error * move transpose ops to example directory * update transpose api * update include file * fix for pr review * fix compile errors * add transpose load; no real logic * fix some compile errors * fix some issues * update transpose load logic * add some fixes * fix a distribution issue * update some codes * add some fix * can pass; but no logic * transpose load enable * update tile transpose * miss output tile distribution mapping * hack for transpose 16x16 * update output tensor distribution * delete unused variables * fix transpose related codes * update transpose load example * exchange the iteration order * fix 16x16 related dimension transpose * fix a transpose index issue * fix a transpose index issue * fix clang format check * update load tile transpose related codes * fix compile errors and pass 16x16 tests * fix a typo * update logic * check other data types * add transpose load api * update transpose load api * fix clang format check * change file name * refactor codes * update code name * delete some unused codes * delete the unused oob flag for transpose load * update tensor view api for transpose load * update for testing * fix a typo error * move transpose ops to example directory * update transpose api * update include file * fix for pr review * fix compile errors * change directory name * delete the duplicated directory * update cmakelists file * delete the unused codes * update function names * update transpose policy * update code after remod.py * update codes * add some comment * Polish the instr infrastructure * build up the fixed instr * redesign the transpose api, currently it has numerical error * add the bf16 transpose * fix some issues * add some comments * update document * Finished the refactor of API and pass through the verification * fix the merging issue --------- Co-authored-by: ThomasNing <thomas.ning@amd.com>
81 lines
3.8 KiB
C++
81 lines
3.8 KiB
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2018-2025, Advanced Micro Devices, Inc. All rights reserved.
|
|
|
|
#pragma once
|
|
|
|
#include "ck_tile/core/algorithm/cluster_descriptor.hpp"
|
|
#include "ck_tile/core/algorithm/coordinate_transform.hpp"
|
|
#include "ck_tile/core/algorithm/indexing_adaptor.hpp"
|
|
#include "ck_tile/core/algorithm/space_filling_curve.hpp"
|
|
#include "ck_tile/core/algorithm/static_encoding_pattern.hpp"
|
|
#include "ck_tile/core/arch/amd_buffer_addressing.hpp"
|
|
#include "ck_tile/core/arch/amd_buffer_addressing_builtins.hpp"
|
|
#include "ck_tile/core/arch/amd_transpose_load_encoding.hpp"
|
|
#include "ck_tile/core/arch/arch.hpp"
|
|
#include "ck_tile/core/arch/generic_memory_space_atomic.hpp"
|
|
#include "ck_tile/core/arch/utility.hpp"
|
|
#include "ck_tile/core/arch/workgroup_barrier.hpp"
|
|
#include "ck_tile/core/config.hpp"
|
|
#include "ck_tile/core/container/array.hpp"
|
|
#include "ck_tile/core/container/container_helper.hpp"
|
|
#include "ck_tile/core/container/map.hpp"
|
|
#include "ck_tile/core/container/meta_data_buffer.hpp"
|
|
#include "ck_tile/core/container/multi_index.hpp"
|
|
#include "ck_tile/core/container/sequence.hpp"
|
|
#include "ck_tile/core/container/span.hpp"
|
|
#include "ck_tile/core/container/statically_indexed_array.hpp"
|
|
#include "ck_tile/core/container/thread_buffer.hpp"
|
|
#include "ck_tile/core/container/tuple.hpp"
|
|
#include "ck_tile/core/numeric/bfloat16.hpp"
|
|
#include "ck_tile/core/numeric/float8.hpp"
|
|
#include "ck_tile/core/numeric/half.hpp"
|
|
#include "ck_tile/core/numeric/int8.hpp"
|
|
#include "ck_tile/core/numeric/integer.hpp"
|
|
#include "ck_tile/core/numeric/integral_constant.hpp"
|
|
#include "ck_tile/core/numeric/math.hpp"
|
|
#include "ck_tile/core/numeric/null_type.hpp"
|
|
#include "ck_tile/core/numeric/numeric.hpp"
|
|
#include "ck_tile/core/numeric/pk_int4.hpp"
|
|
#include "ck_tile/core/numeric/type_convert.hpp"
|
|
#include "ck_tile/core/numeric/vector_type.hpp"
|
|
#include "ck_tile/core/tensor/buffer_view.hpp"
|
|
#include "ck_tile/core/tensor/load_tile.hpp"
|
|
#include "ck_tile/core/tensor/load_tile_transpose.hpp"
|
|
#include "ck_tile/core/tensor/null_tensor.hpp"
|
|
#include "ck_tile/core/tensor/null_tile_window.hpp"
|
|
#include "ck_tile/core/tensor/shuffle_tile.hpp"
|
|
#include "ck_tile/core/tensor/slice_tile.hpp"
|
|
#include "ck_tile/core/tensor/static_distributed_tensor.hpp"
|
|
#include "ck_tile/core/tensor/store_tile.hpp"
|
|
#include "ck_tile/core/tensor/sweep_tile.hpp"
|
|
#include "ck_tile/core/tensor/tensor_adaptor.hpp"
|
|
#include "ck_tile/core/tensor/tensor_adaptor_coordinate.hpp"
|
|
#include "ck_tile/core/tensor/tensor_coordinate.hpp"
|
|
#include "ck_tile/core/tensor/tensor_descriptor.hpp"
|
|
#include "ck_tile/core/tensor/tensor_view.hpp"
|
|
#include "ck_tile/core/tensor/tile_distribution.hpp"
|
|
#include "ck_tile/core/tensor/tile_distribution_encoding.hpp"
|
|
#include "ck_tile/core/tensor/tile_elementwise.hpp"
|
|
#include "ck_tile/core/tensor/tile_scatter_gather.hpp"
|
|
#include "ck_tile/core/tensor/tile_window.hpp"
|
|
#include "ck_tile/core/tensor/tile_window_base.hpp"
|
|
#include "ck_tile/core/tensor/tile_window_linear.hpp"
|
|
#include "ck_tile/core/tensor/tile_window_utils.hpp"
|
|
#include "ck_tile/core/tensor/transpose_tile.hpp"
|
|
#include "ck_tile/core/tensor/update_tile.hpp"
|
|
#include "ck_tile/core/utility/bit_cast.hpp"
|
|
#include "ck_tile/core/utility/env.hpp"
|
|
#include "ck_tile/core/utility/functional.hpp"
|
|
#include "ck_tile/core/utility/functional_with_tuple.hpp"
|
|
#include "ck_tile/core/utility/ignore.hpp"
|
|
#include "ck_tile/core/utility/literals.hpp"
|
|
#include "ck_tile/core/utility/magic_div.hpp"
|
|
#include "ck_tile/core/utility/philox_rand.hpp"
|
|
#include "ck_tile/core/utility/random.hpp"
|
|
#include "ck_tile/core/utility/reduce_operator.hpp"
|
|
#include "ck_tile/core/utility/static_counter.hpp"
|
|
#include "ck_tile/core/utility/to_sequence.hpp"
|
|
#include "ck_tile/core/utility/transpose_vectors.hpp"
|
|
#include "ck_tile/core/utility/type_traits.hpp"
|
|
#include "ck_tile/core/utility/unary_element_function.hpp"
|