Philippe Tillet
20100a7254
Merge triton-mlir branch - Complete rewrite of the backend from scratch ( #1004 )
...
This PR merges the `triton-mlir` branch, in which we have been quietly
rewriting the Triton backend from scratch to increase maintainability,
stability and ultimately performance. Changes to the runtime are
minimal, and this new version aims to remain backward-compatible with
the previous commit. The legacy backend is now officially deprecated,
but can still be accessed via the `legacy-backend` tag.
Co-authored-by: Keren Zhou <kerenzhou@openai.com >
Co-authored-by: Yan Chunwei <yanchunwei@outlook.com >
Co-authored-by: goostavz <109190422+goostavz@users.noreply.github.com >
Co-authored-by: Shintaro Iwasaki <siwasaki@fb.com >
Co-authored-by: Yan Da <dyanab@connect.ust.hk >
Co-authored-by: Jun Yang <yangjunpro@gmail.com >
Co-authored-by: Ian Bearman <ianb@microsoft.com >
Co-authored-by: Jason Ansel <jansel@jansel.net >
Co-authored-by: Qingyi Liu <qingyil@nvidia.com >
Co-authored-by: ben-zhang-609 <110140741+ben-zhang-609@users.noreply.github.com >
Co-authored-by: Chenggang Zhao <lyricz@yeah.net >
Co-authored-by: ben-zhang-609 <benzh609@gmail.com >
Co-authored-by: dongdongl <dongdongl@nvidia.com >
2022-12-21 01:30:50 -08:00
Yang Hau
8650b4d1cb
[DRIVER] Fix typos ( #939 )
2022-12-02 11:13:46 -08:00
Yanbo Liang
5ca1ed0101
Add bf16/fp16/fp64 support for ty_to_cpp ( #800 )
...
In ```torch._inductor```, we [convert 0d CPU tensor to scalar during
triton codegen](https://github.com/pytorch/pytorch/pull/87329 ), so need
add missing triton support for bf16/fp16/fp64.
2022-10-24 19:41:25 -07:00
Philippe Tillet
af76c989eb
[RUNTIME] Make entry point cache key depend on triton version hash ( #765 )
2022-10-11 13:24:30 -07:00
Keren Zhou
11345e9b74
[RUNTIME] Add callback functions for external tools ( #738 )
2022-10-05 14:46:55 -07:00
Philippe Tillet
bdfdb9a1d2
[RUNTIME] Fixed JIT bug that leg some constexpr values to be overriden by specialization parameters ( #742 )
2022-10-05 11:00:32 -07:00
shenggan
77c752dc78
[RUNTIME] remove fixed cu_include_dir ( #739 )
...
Use environment variable `CUDA_HOME` with default value`/usr/local/cuda` for `cu_include_dir` #731
2022-10-04 19:49:57 -07:00
fdrocha
2b0f877fad
[RUNTIME] Support environments with multiple cudalibs ( #733 )
2022-10-03 18:36:24 +00:00
Keren Zhou
4a2d3b7d79
[RUNTIME] Dump llvm, ttir, and sass to help debugging ( #732 )
2022-10-03 00:39:52 +00:00
Jason Ansel
998fd5f9af
[FRONTEND] Make triton.compile work without a cuda context ( #708 )
...
This allows compiling in a subprocess. I'm not seeing a ton of speedup from this, but figure it is a good change anyway.
2022-09-24 13:41:47 -07:00
Philippe Tillet
8c3d4d5749
[RUNTIME] now decoupling entry point from cubin ( #696 )
2022-09-22 16:44:22 -07:00
Jason Ansel
6abe813d1c
Fix issue breaking cudagraphs ( #685 )
...
@ngimel figured this one out.
The errors we were seeing from cudagraphs capture were coming from
`cuStreamGetCtx` which is not allowed while a stream is capturing.
It appears the result of `cuStreamGetCtx()` isn't even used, so I
believe it can just be removed.
2022-09-21 10:20:48 -07:00
Philippe Tillet
48f30550f1
[FRONTEND] Now using raw compiler syscalls when possible ( #678 )
2022-09-19 21:01:36 -07:00
Jason Ansel
49f6bc3f2b
[FRONTEND] Fix filename too long error in new runtime ( #669 )
2022-09-18 21:26:29 +00:00
Jason Ansel
e647402fd3
Fix warning in generated C code ( #667 )
2022-09-18 12:57:32 -07:00
Philippe Tillet
4a77dfb042
[FRONTEND] Complete rewrite of the runtime ( #644 )
...
This PR completely rewrites the runtime of Triton to be more lean and
clearly separate the compilation step from the just-in-time caching logic.
This should substantially reduce launch overhead.
2022-09-18 08:51:48 -07:00
