mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-02 20:51:23 +00:00
b9c6cb1452
* First look at mfma / wmma unification * Refactor * Re-org file structure * Restructure transform selection and WaveWiseMma class * Update license files. Add missing gfx1151 support. Change wave size for HOST to 1. Update datatypes naming consistency * Fixes default MmaSelector implentation * Adds unit tests for amdgcn_mma and arch * Consolidate common arch id checks to constexpr functions. Strongly type ids as amdgcn_target_arch_id object. * Refactor is_any_value_of * Fixes mma_selector logic * Fix typo * Add mma selector test for tile decomposition * Fix compilation of mma.hpp * Revert back to c++17 compatibility * Fix compiler error by returning index_t from get_warp_size() * Apply suggestions from code review Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com> * Fixes compiler error for missing is_wave32() function * Fixes compiler error for host wave_size() should be 64 * Fixes compiler errors where __cpp_concepts is not defined * Fixes compiler errors where __cpp_concepts is not defined * Fix test failure for host is wave64 by default --------- Co-authored-by: Chris Millette <you@example.com> Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
104 lines
4.9 KiB
C++
104 lines
4.9 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/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/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_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/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"
|