mirror of
https://github.com/ROCm/composable_kernel.git
synced 2026-05-14 18:17:44 +00:00
* WMMA GEMM F16 Implementation
Signed-off-by: root <tianyuwu@amd.com>
* Self-review
Signed-off-by: root <tianyuwu@amd.com>
* ASIC check minor tweak
Signed-off-by: root <tianyuwu@amd.com>
* add missing include file
* Set GPU_TARGETS to gfx11/12 generic
Signed-off-by: root <tianyuwu@amd.com>
* INT8 GFX12
Signed-off-by: root <tianyuwu@amd.com>
* add int8x16 branch
* Fix CI script
Signed-off-by: root <tianyuwu@amd.com>
* Fix typo
Signed-off-by: root <tianyuwu@amd.com>
* Add CK_Tile WMMA example
Signed-off-by: Tianyuan Wu <tianyuwu@amd.com>
* Fix CI
Signed-off-by: Tianyuan Wu <tianyuwu@amd.com>
* fix clang format
* Set M/N_Warp Back to Constant
Signed-off-by: Tianyuan Wu <tianyuwu@amd.com>
* Use GemmConfigComputeV3 by default
Signed-off-by: TianyuanWu <Tianyuan.Wu@amd.com>
* Enable CK_TILE_USE_AMD_BUFFER_ATOMIC_ADD_FLOAT for gfx12
Signed-off-by: TianyuanWu <Tianyuan.Wu@amd.com>
* Remove CK_Tile wmma gemm examples from the CI list
Signed-off-by: TianyuanWu <Tianyuan.Wu@amd.com>
* Add atomic add fallback method for gfx11
Signed-off-by: TianyuanWu <Tianyuan.Wu@amd.com>
* Fix typo
Signed-off-by: TianyuanWu <Tianyuan.Wu@amd.com>
* Omit copyright year
Signed-off-by: TianyuanWu <Tianyuan.Wu@amd.com>
* Support non-square cases
Signed-off-by: TianyuanWu <Tianyuan.Wu@amd.com>
* Fix CI
Signed-off-by: TianyuanWu <Tianyuan.Wu@amd.com>
* Add get_device_ip()
Signed-off-by: TianyuanWu <Tianyuan.Wu@amd.com>
* Revert "Add atomic add fallback method for gfx11"
This reverts commit 4f664969c01b37976c8518c19833d9f1574cd746.
Signed-off-by: Tianyuan Wu <Tianyuan.Wu@amd.com>
* Revert "Enable CK_TILE_USE_AMD_BUFFER_ATOMIC_ADD_FLOAT for gfx12"
This reverts commit 949129a3858a825b2a2c4d3ec01663df18a165a5.
* Revise method name and typos
Signed-off-by: Tianyuan Wu <Tianyuan.Wu@amd.com>
* clang-format
Signed-off-by: TianyuanWu <Tianyuan.Wu@amd.com>
* Try fix CI
Signed-off-by: TianyuanWu <Tianyuan.Wu@amd.com>
* Revert "Try fix CI"
This reverts commit 084c683227e64ab6a8137db00c8165fb05bdc902.
* clang-format
Signed-off-by: TianyuanWu <Tianyuan.Wu@amd.com>
* Fix typo caused by merge
Signed-off-by: Tianyuan Wu <Tianyuan.Wu@amd.com>
* Fix typo caused by merging
Signed-off-by: Tianyuan Wu <Tianyuan.Wu@amd.com>
---------
Signed-off-by: root <tianyuwu@amd.com>
Signed-off-by: Tianyuan Wu <tianyuwu@amd.com>
Signed-off-by: TianyuanWu <Tianyuan.Wu@amd.com>
Signed-off-by: Tianyuan Wu <Tianyuan.Wu@amd.com>
Co-authored-by: joye <joye@amd.com>
Co-authored-by: Illia Silin <98187287+illsilin@users.noreply.github.com>
Co-authored-by: illsilin_amdeng <Illia.Silin@amd.com>
[ROCm/composable_kernel commit: 68134b60e4]
73 lines
4.7 KiB
C++
73 lines
4.7 KiB
C++
// SPDX-License-Identifier: MIT
|
|
// Copyright (c) 2018-2025, 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_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_v2r1.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/block/block_universal_gemm_as_bs_cr.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_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/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_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_mem.hpp"
|
|
#include "ck_tile/ops/gemm/pipeline/gemm_pipeline_ag_bg_cr_scheduler.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_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_v1.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_dispatcher.hpp"
|
|
#include "ck_tile/ops/gemm/warp/warp_gemm_impl.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/common/generic_2d_block_shape.hpp"
|
|
#include "ck_tile/ops/common/tensor_layout.hpp"
|
|
#include "ck_tile/ops/common/utils.hpp"
|