Philippe Tillet
|
78ebbe24c7
|
[FRONTEND] Added ExpandDimsOp primitive (#36)
|
2022-08-04 18:41:06 -07:00 |
|
Keren Zhou
|
a7b49b3227
|
[BACKEND] Memory allocation (#33)
|
2022-08-04 11:22:49 -07:00 |
|
Yan Chunwei
|
b988bae813
|
Init TritonGPU to LLVM dialect conversion (#32)
* add toLLVM pass
* update num-warps setting in mlir
|
2022-08-04 10:15:45 +08:00 |
|
Philippe Tillet
|
3236642e8f
|
[OPTIMIZER] Added memory coalescing pass (#31)
|
2022-07-31 20:59:31 -07:00 |
|
Philippe Tillet
|
d1593e6ca8
|
[TritonGPU] Improved documentation and semantics of layout encodings (#30)
|
2022-07-31 13:59:44 -07:00 |
|
Yan Chunwei
|
e02c82c765
|
[TritonIR] Convert Triton dialect's Combine pass to MLIR DRR based (#16)
|
2022-07-27 12:50:08 -07:00 |
|
Philippe Tillet
|
432c3df265
|
[BUILD] MacOS can now build compiler and run MLIR tests (#25)
|
2022-07-27 01:32:10 -07:00 |
|
Philippe Tillet
|
6d62d88d4f
|
[CI] run clang-format (#24)
|
2022-07-26 17:25:03 -07:00 |
|
Philippe Tillet
|
25357083e6
|
[CI] Added basic CI skeletons (#23)
Includes minor fixes to make things compile and pass static checks properly
|
2022-07-26 14:16:30 -07:00 |
|
Philippe Tillet
|
3265e0df5a
|
[PYTHON] Cleaned up legacy code; added simple standalone compilation API (#22)
|
2022-07-26 11:06:45 -07:00 |
|
Keren Zhou
|
96cc6fb563
|
[TritonGPU] Pretty printer for layouts (#21)
|
2022-07-26 10:50:11 -07:00 |
|
Philippe Tillet
|
27c9f3d8cb
|
[FRONTEND] Added comment on TensorSizeTrait::maxElement (#20)
|
2022-07-25 01:18:45 -07:00 |
|
Keren Zhou
|
7eda373a12
|
Add lit dependency (#9)
|
2022-07-24 19:14:52 -07:00 |
|
Philippe Tillet
|
a633d2b403
|
[Analysis] Added Axis Info Analysis (#8)
|
2022-07-19 13:38:48 -07:00 |
|
Philippe Tillet
|
df940aaab0
|
Merge pull request #7 from openai/broadcastAxis-fix
Fix blocked layout parser
|
2022-07-15 08:39:49 -07:00 |
|
Yan Da
|
63e6a85901
|
Fix blocked layout parser
|
2022-07-15 15:19:11 +08:00 |
|
Phil Tillet
|
65237f6117
|
[PACKAGING] Added FileCheck
|
2022-07-07 16:53:19 -07:00 |
|
Yan Da
|
9d1b5e3f79
|
special encoding for broadcast
|
2022-06-18 21:16:45 +08:00 |
|
Yan Da
|
53cf93ce6a
|
Revert "Remove TypeConverter from TritonToTritonGPU conversion"
This reverts commit 64d0b87ef0.
|
2022-06-18 14:57:41 +08:00 |
|
Yan Da
|
64d0b87ef0
|
Remove TypeConverter from TritonToTritonGPU conversion
|
2022-06-18 14:34:59 +08:00 |
|
Yan Da
|
9feb256b71
|
op combine in Triton Dialect: broadcast(cst) -> cst
|
2022-06-17 16:19:47 +08:00 |
|
Yan Da
|
35736aa44e
|
more progress on the testing infrastructure
|
2022-06-12 15:14:45 +08:00 |
|
Yan Da
|
22c65a53d9
|
more progress on test/CMakeLists.txt
|
2022-06-10 21:37:56 +08:00 |
|
Yan Da
|
0ee6e486f8
|
add cse pass to the pipeline & pass num-warps as an argument
|
2022-06-10 17:31:48 +08:00 |
|
Yan Da
|
117a402c1b
|
more comments to TypeConverter & update warpTileSize
|
2022-06-08 16:20:07 +08:00 |
|
Yan Da
|
49d1821149
|
conversion test
|
2022-06-08 16:19:15 +08:00 |
|
Yan Da
|
26fcc12afd
|
better unit tests
|
2022-06-07 19:35:38 +08:00 |
|
Yan Da
|
7b09b5f9e9
|
the pipeline pass now generates and accepts valid IR
|
2022-06-07 19:34:59 +08:00 |
|
Yan Da
|
560e29229b
|
register conversion in triton-opt
|
2022-06-07 19:33:51 +08:00 |
|
Yan Da
|
0e11435448
|
more tests
|
2022-06-06 21:10:28 +08:00 |
|
Yan Da
|
366dddc3bc
|
update mma encoding & triton-opt
|
2022-06-06 21:03:58 +08:00 |
|
Yan Da
|
7807f64ef3
|
rename sharded_layout => blocked_layout
|
2022-06-05 16:14:59 +08:00 |
|
Yan Da
|
bbf75b492f
|
more tests
|
2022-06-05 15:10:09 +08:00 |
|
Yan Da
|
a4a2c72173
|
default address space of PointerType 0 => 1
|
2022-06-05 15:09:41 +08:00 |
|
Yan Da
|
d5eca56cf3
|
more TritonGPU unit tests
|
2022-06-05 14:25:09 +08:00 |
|
Yan Da
|
55cf9a0a97
|
Add triton's opt
|
2022-06-04 22:10:00 +08:00 |
|
Yan Da
|
830fe19d58
|
Merge branch 'mlir-rewrite' of https://github.com/daadaada/mlir-rewrite into mlir-rewrite
|
2022-06-01 10:59:20 +08:00 |
|
Yan Da
|
935390dc03
|
update examples
|
2022-06-01 10:59:16 +08:00 |
|
Da Yan
|
e36a54eb86
|
more progress on the definition of layouts
|
2022-05-31 11:43:21 +00:00 |
|
Yan Da
|
41d338d848
|
Fix op mapping in pipeline.cpp
|
2022-05-26 13:57:01 +08:00 |
|
Yan Da
|
c529b462f5
|
more fixes on pipeline.cpp
|
2022-05-26 13:14:41 +08:00 |
|
Yan Da
|
71d1c10e19
|
Remove weird includes
|
2022-05-25 21:54:06 +08:00 |
|
Yan Da
|
9308e9c90c
|
A more general pipeliner
|
2022-05-25 21:52:51 +08:00 |
|
Yan Da
|
441fd7c3cc
|
assembly format
|
2022-05-25 17:53:24 +08:00 |
|
Yan Da
|
e6f89a5777
|
Fix ReduceOp conversion
|
2022-05-25 16:03:06 +08:00 |
|
Yan Da
|
9b670cfb9f
|
Add ReduceOp
|
2022-05-25 14:15:36 +08:00 |
|
Yan Da
|
a2c9f919a8
|
TritonGPU verifier
|
2022-05-24 19:48:56 +08:00 |
|
Yan Da
|
36c45ec687
|
make numStages an option in PipelinePass
|
2022-05-23 12:47:55 +08:00 |
|
Yan Da
|
39b1235082
|
fix atomic_cas
|
2022-05-22 19:43:04 +08:00 |
|
Yan Da
|
79298d61bc
|
fix a pipeline issue
|
2022-05-16 19:38:40 +08:00 |
|