ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-01 20:21:23 +00:00
Code Issues Packages Projects Releases Wiki Activity

Enabling diff datatypes for tile_engine and build with more granularity (#2392)

Browse Source 
* merging recent changes to universal gemm to tile_engine

* Reducing Linking time by generating less intermediate files

* make small libs to build faster

* Reducing the instances

* reducing instances

* Restoring default config

* Restoring default config

* warp_n reverted in default config

* Adding diff json files for fp8 and fp16, cmake changes for fp8

* Restructure the CMake File

* Added more granularity for build and some debugging code

* removed some of debugging statements

* added fp8 instances

* tahe datatype from command line to enable both type of json files

* updated README file

* code cleanup

* code cleanup

* updated jenkinsfile

* enable tile_engine daily builds

* updating cmake file

* updated CMakeLists.txt

* Updating CMake code fixing gfx12 build

* Updating CMake code fixing gfx12 build

* Fix CMake file null checks

* fixed traces of rebase

* Update tile_engine/ops/gemm/README.md

Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com>

* Update tile_engine/ops/gemm/README.md

Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com>

* Update tile_engine/ops/gemm/README.md

Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com>

* fixing rebase issue

---------

Co-authored-by: khushbu <khuagarw@gmail.com>
Co-authored-by: ThomasNing <thomas.ning@amd.com>
Co-authored-by: illsilin_amdeng <Illia.Silin@amd.com>
Co-authored-by: AviralGoelAMD <aviral.goel@amd.com>
Co-authored-by: spolifroni-amd <Sandra.Polifroni@amd.com>
This commit is contained in:
Khushbu Agarwal
2025-06-25 15:18:24 -07:00
committed by GitHub
parent e03293ebce
commit a14753b86f
10 changed files with 458 additions and 292 deletions
Download Patch File Download Diff File Expand all files Collapse all files

241
tile_engine/ops/gemm/configs/default_config.json
View File

@@ -1,136 +1,115 @@
{
"problem": {
"layout_a": {
"values": [
"r"
]
},
"layout_b": {
"values": [
"c"
]
},
"layout_c": {
"values": [
"r"
]
},
"datatype_a": {
"values": [
"fp16"
]
},
"datatype_b": {
"values": [
"fp16"
]
},
"datatype_c": {
"values": [
"fp16"
]
}
"problem": {
"layout_a": {
"values": [
"r"
]
},
"tile_config": {
"tile_m": {
"max": 256,
"min": 64,
"step": 64,
"exclude": []
},
"tile_n": {
"max": 256,
"min": 64,
"step": 32,
"exclude": []
},
"tile_k": {
"max": 256,
"min": 64,
"step": 64,
"exclude": [192]
},
"warp_m": {
"values": [
4,
2,
1
]
},
"warp_n": {
"values": [
4,
2,
1
]
},
"warp_k": {
"values": [
1
]
},
"warp_tile_m": {
"values": [
4,
8,
16,
32,
64
]
},
"warp_tile_n": {
"values": [
4,
8,
16,
32,
64
]
},
"warp_tile_k": {
"values": [
8,
16,
32,
64,
128
]
}
"layout_b": {
"values": [
"c"
]
},
"trait_config": {
"pipeline": {
"values": [
"compv4",
"compv3",
"mem"
]
},
"scheduler": {
"values": [
"intrawave",
"interwave"
]
},
"epilogue": {
"values": [
"default",
"cshuffle"
]
},
"pad_m": {
"values": [
false
]
},
"pad_n": {
"values": [
false
]
},
"pad_k": {
"values": [
false
]
}
"layout_c": {
"values": [
"r"
]
}
},
"tile_config": {
"tile_m": {
"values": [
256
]
},
"tile_n": {
"values": [
128,
256
]
},
"tile_k": {
"values": [
32
]
},
"warp_m": {
"values": [
1,
2,
4
]
},
"warp_n": {
"values": [
1,
2,
4
]
},
"warp_k": {
"values": [
1
]
},
"warp_tile_m": {
"values": [
4,
16,
32
]
},
"warp_tile_n": {
"values": [
16,
32,
64
]
},
"warp_tile_k": {
"values": [
8,
16,
32,
64,
128
]
}
},
"trait_config": {
"pipeline": {
"values": [
"compv3",
"compv4",
"mem"
]
},
"scheduler": {
"values": [
"intrawave",
"interwave"
]
},
"epilogue": {
"values": [
"cshuffle",
"default"
]
},
"pad_m": {
"values": [
false
]
},
"pad_n": {
"values": [
false
]
},
"pad_k": {
"values": [
false
]
}
}
}