mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-03-17 05:37:38 +00:00
a1679e38ee
Changed the include order of the new WMMA/MFMA unification framework (#5241) Those changes are to fix the include order and make header files independent of one another. Also the `remod.py` sript has run and changed the `grouped_convolution.hpp` and `core.hpp` files. ## Motivation Some headers appear to depend on include order. For example, when moving `#include "wmma/wmma.hpp"` in [amdgcn_mma.hpp](https://github.com/ROCm/rocm-libraries/blob/develop/projects/composablekernel/include/ck_tile/core/arch/mma/amdgcn_mma.hpp) later in the include list, it is causing compilation errors. Also the pre-commit script `remod.py` is shuffling includes to be in alphabetical order and is causing compilation issues. Expected behaviour: Headers should be independent of one another: no header should require another to be included first. Each header should compile correctly on its own. ## Test Plan The CI (that runs `remod.py`) should compile. ## Test Result Existing CI should compile and be green. ## Submission Checklist - [x] Look over the contributing guidelines at https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.
118 lines
5.8 KiB
C++
118 lines
5.8 KiB
C++
// Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
|
|
// SPDX-License-Identifier: MIT
|
|
#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_buffer_coherence.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/mma/amdgcn_mma.hpp"
|
|
#include "ck_tile/core/arch/mma/mfma/mfma.hpp"
|
|
#include "ck_tile/core/arch/mma/mfma/mfma_gfx9.hpp"
|
|
#include "ck_tile/core/arch/mma/mfma/mfma_selector.hpp"
|
|
#include "ck_tile/core/arch/mma/mfma/mfma_traits.hpp"
|
|
#include "ck_tile/core/arch/mma/mfma/mfma_transforms.hpp"
|
|
#include "ck_tile/core/arch/mma/mma.hpp"
|
|
#include "ck_tile/core/arch/mma/mma_op_family.hpp"
|
|
#include "ck_tile/core/arch/mma/mma_selector.hpp"
|
|
#include "ck_tile/core/arch/mma/mma_traits.hpp"
|
|
#include "ck_tile/core/arch/mma/mma_transforms.hpp"
|
|
#include "ck_tile/core/arch/mma/sparse/mfma/selector.hpp"
|
|
#include "ck_tile/core/arch/mma/sparse/mfma/sparse_gfx9.hpp"
|
|
#include "ck_tile/core/arch/mma/sparse/sparse.hpp"
|
|
#include "ck_tile/core/arch/mma/sparse/sparse_selector.hpp"
|
|
#include "ck_tile/core/arch/mma/sparse/sparse_traits.hpp"
|
|
#include "ck_tile/core/arch/mma/sparse/sparse_transforms.hpp"
|
|
#include "ck_tile/core/arch/mma/sparse/wmma/selector.hpp"
|
|
#include "ck_tile/core/arch/mma/sparse/wmma/sparse_gfx12.hpp"
|
|
#include "ck_tile/core/arch/mma/utility/tile_distribution_encoding_register_mapper.hpp"
|
|
#include "ck_tile/core/arch/mma/wmma/wmma.hpp"
|
|
#include "ck_tile/core/arch/mma/wmma/wmma_gfx11.hpp"
|
|
#include "ck_tile/core/arch/mma/wmma/wmma_gfx12.hpp"
|
|
#include "ck_tile/core/arch/mma/wmma/wmma_selector.hpp"
|
|
#include "ck_tile/core/arch/mma/wmma/wmma_traits.hpp"
|
|
#include "ck_tile/core/arch/mma/wmma/wmma_transforms.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/static_array.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/e8m0.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/mxfp_convert.hpp"
|
|
#include "ck_tile/core/numeric/null_type.hpp"
|
|
#include "ck_tile/core/numeric/numeric.hpp"
|
|
#include "ck_tile/core/numeric/pk_fp4.hpp"
|
|
#include "ck_tile/core/numeric/pk_fp6.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/debug.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/gemm_validation.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/mixed_prec_compute_type.hpp"
|
|
#include "ck_tile/core/utility/persistent_async_input_scheduler.hpp"
|
|
#include "ck_tile/core/utility/philox_rand.hpp"
|
|
#include "ck_tile/core/utility/print.hpp"
|
|
#include "ck_tile/core/utility/random.hpp"
|
|
#include "ck_tile/core/utility/reduce_operator.hpp"
|
|
#include "ck_tile/core/utility/reduce_operator_accumulate.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"
|