mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-01 12:11:19 +00:00
3af1a0aafc
[CK TILE] Refactor sequence_reverse_inclusive_scan ## Proposed changes Refactor ck tile `sequence_reverse_inclusive_scan` from recursive to for-loop. Tracking issue: #4229 This pull request introduces a new lightweight array type, `static_array`, and refactors the sequence utilities to use it for improved constexpr support and simplicity. The changes also include updates to the build system to add container-related tests. **Core Library Improvements:** * Added a new header `static_array.hpp` that defines the `static_array` type, a constexpr-friendly array with basic accessors and no custom constructors. * Updated includes in `core.hpp` and `sequence.hpp` to import `static_array`. [[1]](diffhunk://#diff-14b406eccf59794051a16c0c9c1a7e11234324bfdd107a5bbe0f173cd25bcddcR44) [[2]](diffhunk://#diff-5042e5b47bb2ba78bbab2d284338cf0503bc8fb76a7d631cc2684ad6ca832a76R7) **Refactoring to Use `static_array`:** * Refactored sequence utilities in `sequence.hpp` to use `static_array` instead of the previously forward-declared `array` type, including in histogram and array generation logic. [[1]](diffhunk://#diff-5042e5b47bb2ba78bbab2d284338cf0503bc8fb76a7d631cc2684ad6ca832a76L1108-R1133) [[2]](diffhunk://#diff-5042e5b47bb2ba78bbab2d284338cf0503bc8fb76a7d631cc2684ad6ca832a76L1130-R1146) * Rewrote the implementation of `sequence_reverse_inclusive_scan` to use `static_array` for intermediate storage, improving constexpr evaluation and clarity. **Build System and Testing:** * Added a new test subdirectory for container tests and a GoogleTest executable for `unit_sequence.cpp` to the CMake build configuration. [[1]](diffhunk://#diff-5d35ff7555d3f0b438d45cde06b661eb1332cdbec66287ac7ec3c478d688aae5R5) [[2]](diffhunk://#diff-1f54f0d2b431b7fc74f7b4ffb66e80c381c904c3383b1d27987467e3482d6d7aR1-R7) Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
108 lines
5.2 KiB
C++
108 lines
5.2 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_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/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"
|