ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-04 13:41:24 +00:00
Code Issues Packages Projects Releases Wiki Activity

GEMM Multi D for CK Tile Engine (#2660)

Browse Source 
* Readme for GEMM Multi D

* GEMM Multi D partial Progress

* GEMM Multi D partial Progress!

* CK Tile Engine GEMM Multi D : All Python files generated

* Partial Progress

* Partial Progress

* Partial Progress

* Partial Progress : Incorrect Result

* Partial Progress : Debugging

* Partial Progress : Correct Results

* Partial Progress - Incorrect Results

* Partial Progress - Commenting Passthrough bypass logic

* Changing Passthrough to MultiplyMultiply

* Correct Results!

* Fix and debug the pass through feature

* Sample commit

* Correct Results : MultiplyMultiply

* Code Cleanup

* Removing Failed Instances

* Working code before Unary element support

* Custom Elementwise Function support and working implementation for Mul and Add

* Updating README

* Working for Passthrough

* Review Comments : Minor Fixes

* Review Comments : Minor Fixes

* Readme Updated

* Partial Changes after Rebase

* Working Code : Changes after Rebase

* Updating Jenkins file

* Removing default value changed while testing

* Configuration changes in config files

* Tile Handler changes in GEMM Multi D Tile Engine

* Tile Handler changes in GEMM Multi D Example

* Change log for Gemm Multi D in CK Tile Engine

* Configuration changes in config files

---------

Co-authored-by: ThomasNing <thomasning@amd.com>
This commit is contained in:
Thrupti Raj Lakshmana Gowda
2025-08-12 18:05:05 -05:00
committed by GitHub
parent 30dafe8281
commit 3f57ec3d2d
18 changed files with 2547 additions and 291 deletions
Download Patch File Download Diff File Expand all files Collapse all files

80
tile_engine/ops/gemm_multi_d/configs/custom_ci_config.json Normal file
View File

@@ -0,0 +1,80 @@
{
"tile_config": {
"tile_m": {
"values": [
256 ]
},
"tile_n": {
"values": [
128
]
},
"tile_k": {
"values": [
32
]
},
"warp_m": {
"values": [
2
]
},
"warp_n": {
"values": [
2
]
},
"warp_k": {
"values": [
1
]
},
"warp_tile_m": {
"values": [
16
]
},
"warp_tile_n": {
"values": [
16
]
},
"warp_tile_k": {
"values": [
16
]
}
},
"trait_config": {
"pipeline": {
"values": [
"compv3"
]
},
"scheduler": {
"values": [
"intrawave"
]
},
"epilogue": {
"values": [
"cshuffle"
]
},
"pad_m": {
"values": [
false
]
},
"pad_n": {
"values": [
false
]
},
"pad_k": {
"values": [
false
]
}
}
}

84
tile_engine/ops/gemm_multi_d/configs/default_config.json Normal file
View File

@@ -0,0 +1,84 @@
{
"tile_config": {
"tile_m": {
"values": [
256
]
},
"tile_n": {
"values": [
128
]
},
"tile_k": {
"values": [
32
]
},
"warp_m": {
"values": [
2
]
},
"warp_n": {
"values": [
2
]
},
"warp_k": {
"values": [
1
]
},
"warp_tile_m": {
"values": [
16
]
},
"warp_tile_n": {
"values": [
16
]
},
"warp_tile_k": {
"values": [
16
]
}
},
"trait_config": {
"pipeline": {
"values": [
"compv3",
"compv4",
"mem"
]
},
"scheduler": {
"values": [
"intrawave",
"interwave"
]
},
"epilogue": {
"values": [
"cshuffle"
]
},
"pad_m": {
"values": [
false
]
},
"pad_n": {
"values": [
false
]
},
"pad_k": {
"values": [
false
]
}
}
}

81
tile_engine/ops/gemm_multi_d/configs/user_provided_config.json Normal file
View File

@@ -0,0 +1,81 @@
{
"tile_config": {
"tile_m": {
"values": [
256
]
},
"tile_n": {
"values": [
256
]
},
"tile_k": {
"values": [
64
]
},
"warp_m": {
"values": [
2
]
},
"warp_n": {
"values": [
2
]
},
"warp_k": {
"values": [
1
]
},
"warp_tile_m": {
"values": [
32
]
},
"warp_tile_n": {
"values": [
32
]
},
"warp_tile_k": {
"values": [
16
]
}
},
"trait_config": {
"pipeline": {
"values": [
"compv3"
]
},
"scheduler": {
"values": [
"intrawave"
]
},
"epilogue": {
"values": [
"cshuffle"
]
},
"pad_m": {
"values": [
false
]
},
"pad_n": {
"values": [
false
]
},
"pad_k": {
"values": [
false
]
}
}
}