mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-06-29 19:28:33 +00:00
2733e75900
[CK Tile] Async support pipeline V3 ## Motivation Optimize pipeline V3 for gfx950 by enabling buffer load to lds (async pipeline) ## Technical Details - Add `Async` bool to `Problem` struct to enable async pipeline in existing one - Add `static_move_ys` to load transpose. This generates offset in assembly instructions saving registers - Add `is_valid` to `async_get_vectorized_elements`. Before hard coded to true. It allows to support padding - Remove unnecessary restrictions to `is_a_load_tr` and `is_b_load_tr` (wider use of lds load transpose on gfx950) - Integrate async support in existing V3 pipeline (avoid pipelines duplication) - Create policy to support both async and default cases. This could be used by any async pipeline (next steps) - Define `wg_attr_num_access` separately for A and B. This allows to optimize ds_read instruction width for cases when one matrix is transposed and the other is not. Before in such cases, `ds_read_b64` was used instead of `ds_read_b128` - Add test for V3 async. Currently only supporting cases with A and B having the same type ## Test Plan New test `test_ck_tile_gemm_pipeline_compv3_async` ## Submission Checklist - [x] Look over the contributing guidelines at https://github.com/ROCm/ROCm/blob/develop/CONTRIBUTING.md#pull-requests.
107 lines
7.2 KiB
C++
107 lines
7.2 KiB
C++
// Copyright (c) Advanced Micro Devices, Inc., or its affiliates.
|
|
// SPDX-License-Identifier: MIT
|
|
#pragma once
|
|
|
|
#include "ck_tile/ops/gemm/block/block_gemm_areg_bgmem_creg_v1.hpp"
|
|
#include "ck_tile/ops/gemm/block/block_gemm_areg_bgmem_creg_v1_default_policy.hpp"
|
|
#include "ck_tile/ops/gemm/block/block_gemm_areg_breg_creg_eight_waves_v1.hpp"
|
|
#include "ck_tile/ops/gemm/block/block_gemm_areg_breg_creg_v1.hpp"
|
|
#include "ck_tile/ops/gemm/block/block_gemm_areg_breg_creg_v1_custom_policy.hpp"
|
|
#include "ck_tile/ops/gemm/block/block_gemm_areg_breg_creg_v1_default_policy.hpp"
|
|
#include "ck_tile/ops/gemm/block/block_gemm_areg_breg_creg_v2.hpp"
|
|
#include "ck_tile/ops/gemm/block/block_gemm_areg_breg_creg_v2_custom_policy.hpp"
|
|
#include "ck_tile/ops/gemm/block/block_gemm_areg_bsmem_creg_one_warp_v1.hpp"
|
|
#include "ck_tile/ops/gemm/block/block_gemm_areg_bsmem_creg_v1.hpp"
|
|
#include "ck_tile/ops/gemm/block/block_gemm_areg_bsmem_creg_v1_custom_policy.hpp"
|
|
#include "ck_tile/ops/gemm/block/block_gemm_areg_bsmem_creg_v1_default_policy.hpp"
|
|
#include "ck_tile/ops/gemm/block/block_gemm_areg_bsmem_creg_v2.hpp"
|
|
#include "ck_tile/ops/gemm/block/block_gemm_areg_bsmem_creg_v2_custom_policy.hpp"
|
|
#include "ck_tile/ops/gemm/block/block_gemm_areg_bsmem_creg_v2_default_policy.hpp"
|
|
#include "ck_tile/ops/gemm/block/block_gemm_areg_bsmem_creg_v2_prefetch_k.hpp"
|
|
#include "ck_tile/ops/gemm/block/block_gemm_areg_bsmem_creg_v2_prefetch_n.hpp"
|
|
#include "ck_tile/ops/gemm/block/block_gemm_areg_bsmem_creg_v2r1.hpp"
|
|
#include "ck_tile/ops/gemm/block/block_gemm_areg_bsmem_trload_creg_v2_prefetch_n.hpp"
|
|
#include "ck_tile/ops/gemm/block/block_gemm_asmem_breg_creg_v1.hpp"
|
|
#include "ck_tile/ops/gemm/block/block_gemm_asmem_breg_creg_v1_custom_policy.hpp"
|
|
#include "ck_tile/ops/gemm/block/block_gemm_asmem_breg_creg_v1_default_policy.hpp"
|
|
#include "ck_tile/ops/gemm/block/block_gemm_asmem_bsmem_creg_v1.hpp"
|
|
#include "ck_tile/ops/gemm/block/block_gemm_asmem_bsmem_creg_v1_custom_policy.hpp"
|
|
#include "ck_tile/ops/gemm/block/block_gemm_asmem_bsmem_creg_v1_default_policy.hpp"
|
|
#include "ck_tile/ops/gemm/block/block_gemm_mx_areg_bsmem_creg_v1.hpp"
|
|
#include "ck_tile/ops/gemm/block/block_gemm_mx_areg_bsmem_creg_v1_custom_policy.hpp"
|
|
#include "ck_tile/ops/gemm/block/block_gemm_problem.hpp"
|
|
#include "ck_tile/ops/gemm/block/block_universal_gemm_as_bs_cr.hpp"
|
|
#include "ck_tile/ops/gemm/block/block_wp_asmem_breg_creg.hpp"
|
|
#include "ck_tile/ops/gemm/block/block_wp_asmem_bsmem_creg_v1.hpp"
|
|
#include "ck_tile/ops/gemm/block/block_wp_asmem_bsmem_creg_v1_custom_policy.hpp"
|
|
#include "ck_tile/ops/gemm/kernel/batched_gemm_kernel.hpp"
|
|
#include "ck_tile/ops/gemm/kernel/gemm_kernel.hpp"
|
|
#include "ck_tile/ops/gemm/kernel/gemm_multi_abd_kernel.hpp"
|
|
#include "ck_tile/ops/gemm/kernel/gemm_multi_d_kernel.hpp"
|
|
#include "ck_tile/ops/gemm/kernel/gemm_tile_partitioner.hpp"
|
|
#include "ck_tile/ops/gemm/kernel/grouped_gemm_kernel.hpp"
|
|
#include "ck_tile/ops/gemm/kernel/mx_gemm_kernel.hpp"
|
|
#include "ck_tile/ops/gemm/kernel/mx_grouped_gemm_kernel.hpp"
|
|
#include "ck_tile/ops/gemm/kernel/streamk_gemm/streamk_gemm_coherency.hpp"
|
|
#include "ck_tile/ops/gemm/kernel/streamk_gemm/streamk_gemm_kernel.hpp"
|
|
#include "ck_tile/ops/gemm/kernel/streamk_gemm/streamk_gemm_tile_partitioner.hpp"
|
|
#include "ck_tile/ops/gemm/kernel/streamk_gemm/streamk_gemm_tile_partitioner_impl.hpp"
|
|
#include "ck_tile/ops/gemm/kernel/universal_gemm_kernel.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_base.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_comp_async.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_comp_async_default_policy.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_comp_async_eight_waves.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_comp_async_eight_waves_policy.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_comp_async_v2.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_comp_tdm_default_policy.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_comp_tdm_v1.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_comp_tdm_v2.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_comp_v3.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_comp_v4.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_comp_v4_default_policy.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_comp_v5.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_comp_v5_default_policy.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_comp_v6.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_comp_v6_default_policy.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_eight_waves_base.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_default_policy.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_mem.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_scheduler.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_wavelet.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_agmem_bgmem_creg_async_v1.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_agmem_bgmem_creg_v1.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_agmem_bgmem_creg_v1_default_policy.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_agmem_bgmem_creg_v2.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_agmem_bgmem_creg_v2_default_policy.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_problem.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/gemm_pipelines.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/gemm_universal_pipeline_ag_bg_cr_policy.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/tile_gemm_shape.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/tile_gemm_traits.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/wp_pipeline_agmem_bgmem_creg_base_policy.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/wp_pipeline_agmem_bgmem_creg_tdm.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/wp_pipeline_agmem_bgmem_creg_tdm_policy.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/wp_pipeline_agmem_bgmem_creg_v2.hpp"
|
|
#include "ck_tile/ops/gemm/warp/warp_gemm.hpp"
|
|
#include "ck_tile/ops/gemm/warp/warp_gemm_attribute_mfma.hpp"
|
|
#include "ck_tile/ops/gemm/warp/warp_gemm_attribute_mfma_impl.hpp"
|
|
#include "ck_tile/ops/gemm/warp/warp_gemm_attribute_smfmac.hpp"
|
|
#include "ck_tile/ops/gemm/warp/warp_gemm_attribute_smfmac_impl.hpp"
|
|
#include "ck_tile/ops/gemm/warp/warp_gemm_attribute_wmma.hpp"
|
|
#include "ck_tile/ops/gemm/warp/warp_gemm_attribute_wmma_impl.hpp"
|
|
#include "ck_tile/ops/gemm/warp/warp_gemm_attribute_wmma_impl_16bit_traits.hpp"
|
|
#include "ck_tile/ops/gemm/warp/warp_gemm_attribute_wmma_impl_8bit_traits.hpp"
|
|
#include "ck_tile/ops/gemm/warp/warp_gemm_attribute_wmma_impl_base_traits.hpp"
|
|
#include "ck_tile/ops/gemm/warp/warp_gemm_attribute_wmma_impl_highprec_traits.hpp"
|
|
#include "ck_tile/ops/gemm/warp/warp_gemm_dispatcher.hpp"
|
|
#include "ck_tile/ops/gemm/warp/warp_gemm_impl.hpp"
|
|
#include "ck_tile/ops/gemm/warp/warp_gemm_params.hpp"
|
|
#include "ck_tile/ops/gemm/warp/warp_gemm_smfmac_impl.hpp"
|
|
#include "ck_tile/ops/gemm/warp/warp_wmma_gemm.hpp"
|
|
#include "ck_tile/ops/gemm/warp/warp_wmma_gemm_gfx11_utils.hpp"
|
|
#include "ck_tile/ops/common/generic_2d_block_shape.hpp"
|
|
#include "ck_tile/ops/common/load_and_convert_tile.hpp"
|
|
#include "ck_tile/ops/common/streamk_common.hpp"
|
|
#include "ck_tile/ops/common/tensor_layout.hpp"
|
|
#include "ck_tile/ops/common/utils.hpp"
|