Yan Da
7027af9666
The pipeline pass is now functional
2022-05-15 22:29:27 +08:00
Yan Da
d23d7b244c
More on the pipeline pass
2022-05-11 20:31:08 +08:00
Yan Da
1a4fbed25b
Skeleton for the pipeline pass
2022-05-11 16:13:53 +08:00
Yan Da
2d281cbc0a
ConstantOp conversion pattern
2022-05-04 15:35:43 +08:00
Yan Da
b9279d2e3b
More progress on TritonGPU conversion
2022-05-04 14:54:31 +08:00
Yan Da
75d32e2442
More on TritonGPU conversion
2022-05-02 21:51:00 +08:00
Yan Da
1428185c9c
More progress on TritonGPUTypeConverter & TritonGPUConversionTarget
2022-05-01 22:06:54 +08:00
Yan Da
4ece9fd1f3
Move dependentDialects from .cpp to .td
2022-05-01 13:06:51 +08:00
Phil Tillet
2c6a213131
[TRITONGPU] Added template for Triton -> TritonGPU conversion
2022-04-30 16:00:39 -07:00
Yan Da
2239ac1998
more progress on TritonGPU
2022-04-28 18:51:31 +08:00
Philippe Tillet
012e8c5b2b
fixup
2022-04-27 16:39:27 -07:00
Philippe Tillet
513bcaee50
Added some ASCII art for encoding documentation
2022-04-27 16:28:27 -07:00
Yan Da
38d13ae618
Some progress on TritonGPU
2022-04-27 21:16:45 +08:00
Yan Da
edca91bf8f
Update traits (NoSideEffect)
2022-04-27 19:41:07 +08:00
Yan Da
8dfe78f6cf
Add TritonCombineOps
2022-04-27 19:28:21 +08:00
Yan Da
c70f6b666e
Merge previous changes
2022-04-27 14:06:55 +08:00
Yan Da
74585fb970
Add Triton CombineOps
2022-04-27 13:45:56 +08:00
Philippe Tillet
81001d318c
Putting Triton dialect in its own folder
2022-04-26 14:39:27 -07:00
Philippe Tillet
62a64ff29b
Fixed Python link bug in CMakeLists
2022-04-26 14:39:18 -07:00
Yan Da
fcbbb3c10e
Fix visit_While issues
2022-04-10 16:16:13 +08:00
Yan Da
f1cc67bbc3
triton -> tt
2022-04-10 12:07:19 +08:00
Yan Da
28e96bbfd1
Remove the dependency on TensorDialect
2022-04-08 19:43:09 +08:00
Yan Da
62f7609612
More on type inference & assembly format
2022-04-08 19:37:57 +08:00
Yan Da
13aead4808
Use TableGen to define new types
2022-04-08 16:32:46 +08:00
Yan Da
6002340456
Better textual representation
2022-04-07 20:44:41 +08:00
Yan Da
62f772123c
now kernel functions return nothing (instead of none)
2022-04-07 20:22:17 +08:00
Yan Da
040a2b6c75
Fix OpBuilder
2022-04-07 20:01:31 +08:00
Yan Da
6b4da6f016
Documentation
2022-04-07 16:00:53 +08:00
Yan Da
16d44e5c4c
Verify power-of-2
2022-04-07 15:28:02 +08:00
Yan Da
9cf4107990
Add TensorSizeTrait
2022-04-07 15:18:43 +08:00
Yan Da
9dafa0e2e3
Update trtion dependencies
2022-04-01 20:16:07 +08:00
Yan Da
2041b67fbf
Now vecadd works
2022-03-30 20:21:47 +08:00
Yan Da
38e67b4293
Add more Ops
2022-03-28 19:50:23 +08:00
Yan Da
0d139ec460
Introducing SCF
2022-03-26 17:02:32 +08:00
Yan Da
5e117966d0
CatOp
2022-03-25 14:17:17 +08:00
Yan Da
f2ab318614
New python binding
2022-03-22 21:53:22 +08:00
Yan Da
419bbe0f6e
Reverts back to MLIR 14 & updates CMakeLists
2022-03-20 16:41:48 +08:00
Yan Da
a2c31ff434
Init commit
2022-03-17 20:40:55 +08:00
daadaada
539961072c
[FRONTEND] Semantic analysis refactor ( #473 )
...
Moved dispatch.cc to semantic.py
Integer signedness now moved from C++ to python
Cleaner frontend type
Co-authored-by: Phil Tillet <phil@openai.com >
2022-03-16 21:25:30 -07:00
Philippe Tillet
bb5765df5c
[CODEGEN] Now padding shared memory for layout conversion ( #468 )
2022-03-03 22:19:05 -08:00
daadaada
d9dd97492f
Use unique_ptr in ir::context_impl ( #462 )
...
Co-authored-by: Philippe Tillet <Phil.Tillet@gmail.com >
2022-02-24 16:07:10 -08:00
Philippe Tillet
98ed7db8c1
[CODEGEN] Improvements and bugfixes ( #463 )
2022-02-24 14:56:24 -08:00
Philippe Tillet
807d8a1945
[ALL] Merge master ( #447 )
2022-01-30 20:21:20 -08:00
Philippe Tillet
bef76b142a
[BACKEND] float division is now approximate by default ( #446 )
2022-01-29 18:29:29 -08:00
daadaada
59d371c6eb
[BACKEND] Added Int8 mma ( #440 )
2022-01-27 09:12:44 -08:00
Benjamin Lefaudeux
3a23c1dd33
[BACKEND] minor, hotfix for gcc compilation ( #439 )
2022-01-23 14:24:02 -08:00
Philippe Tillet
4c94359199
[FRONTEND] Alignment fix-up ( #428 )
2022-01-11 23:11:58 -08:00
daadaada
94a2e10fe5
[BACKEND] Add bf16 & tf32 mma supports (on A100) ( #426 )
2022-01-11 10:20:31 -08:00
Madeleine Thompson
0ab9d67bad
uint8, uint16, uint32, and uint64 in kernels ( #413 )
...
A forthcoming PR will update the RNG to use these types.
Also:
- Add tests for the `//`, `<<`, and `>>` operators.
- Change `TensorWrapper` to unwrap objects when the resulting object would be simpler.
- Clean up `throw_unreachable`, since it was triggering compiler warnings.
2022-01-05 15:27:17 -08:00
Philippe Tillet
03f1256f60
[FRONTEND] Added volatile flag for load ( #407 )
2021-12-30 22:33:24 -08:00
