mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-05 14:11:29 +00:00
* tmp save
* fix batch deterministic bugs
* fix group deterministic bugs
* codegen update
* reorder files
* bias support
* hd256 bias support
* bwd smoke test update
* simplify convert dq
* fix hd256 dropout scratch
* do{}while() -> while(){}
* comments
* remove FmhaBwdTilePartitioner
* save clear_tile
* refactor dropout
* code cleanup
* code cleanup
* comments
* fix epilogue problem
* fix fwd dropout
* group convert_dq opt
* fix dq alignment
* Do not store storerandval in bwd for flash attention integration
* fix hd32 error and boost performance
* revert
* Remove duplicated WarpGemm definitions in the policy file
* dropout patch for mrepeat 16*16
* code sync up
* dq_acc stride
* dq_acc stride stuff
* codegen update
* fwd dropout revert
* fix hd128 scratches and boost performance
* receipt 3 for simplified smoke test
* more strides for fa integration
* fix hd64 scratches and boost performance
* non-iglp pipeline for headdim padding cases
* dpad same as dvpad for flash attention integration
* unpadded lse&d for group mode
* Support unpad layout for group lse
* Support unpad lse layout for splitkv
* Fix stride for splitkv kernel
* fix unpadded lse issue in fwd splitkv
* comment
* solve lds read&write conflicts
* rename
* bias rename
* tile index revert
---------
Co-authored-by: danyao12 <danyao12>
Co-authored-by: rocking <ChunYu.Lai@amd.com>
Co-authored-by: Qianfeng Zhang <Qianfeng.Zhang@amd.com>
36 lines
2.3 KiB
C++
36 lines
2.3 KiB
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2018-2024, Advanced Micro Devices, Inc. All rights reserved.
|
|
|
|
#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_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_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_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_problem.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/block_gemm_pipeline_agmem_bgmem_creg_v1.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/block_gemm_pipeline_agmem_bgmem_creg_v1_default_policy.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/block_gemm_pipeline_agmem_bgmem_creg_v2.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/block_gemm_pipeline_agmem_bgmem_creg_v2_default_policy.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/block_gemm_pipeline_problem.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/tile_gemm_shape.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_dispatcher.hpp"
|
|
#include "ck_tile/ops/gemm/warp/warp_gemm_impl.hpp"
|
|
#include "ck_tile/ops/common/tensor_layout.hpp"
|