gaspersic/triton
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
629 Commits 14 Branches 9 Tags
137e866bd2999eec9db650ac5bc6de14e3e8ce80
Commit Graph

629 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Phil Tillet
137e866bd2 more work 2023-01-09 16:20:10 -08:00
Phil Tillet
8ebb593bbb more work 2023-01-09 15:45:06 -08:00
Phil Tillet
6c750b6856 Added verifier for trans 2023-01-08 14:29:17 -08:00
Phil Tillet
42421fabc5 . 2023-01-06 20:35:57 -08:00
Phil Tillet
600bcefb12 more optimizations 2023-01-06 20:27:49 -08:00
Philippe Tillet
18c7a72973 more pass template 2023-01-06 14:26:06 -08:00
Phil Tillet
b16aeb6541 added missing file 2023-01-06 13:39:54 -08:00
Phil Tillet
a81345f7c1 SinkConversionsFromShared template 2023-01-06 13:01:08 -08:00
Philippe Tillet
874ee11ab5 More optimizations 2023-01-06 11:04:20 -08:00
Philippe Tillet
e6f1a9ad34 commenting dq but not load/store 2023-01-05 23:25:41 -08:00
Philippe Tillet
6f997f4ecb dq now mma 2023-01-05 21:14:55 -08:00
Phil Tillet
520b69fe70 more reassociation 2023-01-05 16:05:11 -08:00
Phil Tillet
764134ee34 trying to decrease register pressure 2023-01-05 13:02:38 -08:00
Phil Tillet
1bde80b1e8 Added ptx code 2023-01-04 17:23:16 -08:00
Phil Tillet
268d2cd18d better convert + write-back 2023-01-04 17:12:35 -08:00
Phil Tillet
29a1e20b58 tweak convert + trans 2023-01-04 17:12:28 -08:00
Phil Tillet
36da342893 . 2023-01-04 11:25:03 -08:00
Phil Tillet
e70e1e76b4 swizzling 2023-01-04 11:21:19 -08:00
Phil Tillet
e3c3d9fc65 16 spills 2023-01-04 00:01:22 -08:00
Phil Tillet
ee86ea9c90 100 spills 2023-01-03 20:52:00 -08:00
Phil Tillet
645fa5c1cd . 2023-01-03 18:34:05 -08:00
Phil Tillet
8df1fa5e5b Merge remote-tracking branch 'origin/master' into phil/fused-attention-perf-fixup 2023-01-03 18:31:34 -08:00
Keren Zhou
8460ea3df1 [Frontend] Fix import for libdevice (#1028) 
This is a hotfix for issue 1 in
https://github.com/openai/triton/issues/1017
 2023-01-03 15:48:05 -08:00
Keren Zhou
678b9f53a2 [Backend] Use post-order traversal for liveness numbering (#1027) 
Also add tests for `tt.trans`.
 2023-01-03 15:11:54 -08:00
Phil Tillet
737e43a627 more tests 2023-01-03 09:48:08 -08:00
Phil Tillet
5c01c567b9 . 2023-01-02 23:13:12 -08:00
Phil Tillet
05920e0b8b reduced some spilling 2023-01-02 19:28:54 -08:00
Phil Tillet
c11fe351e1 . 2023-01-02 19:16:06 -08:00
Phil Tillet
b246d85fad trying to figure out spilling root cause 2022-12-30 15:21:00 -08:00
Phil Tillet
4dce8dd709 Merge remote-tracking branch 'origin/master' into phil/fused-attention-perf-fixup 2022-12-30 11:53:49 -08:00
goostavz
0e8590f1c9 [BACKEND] Add generic support of convert_layout from distributed to shared (#1025) 2022-12-30 11:29:58 -08:00
Phil Tillet
7388fb1de9 manual ttgir in bwd pass 2022-12-29 15:53:38 -08:00
fdrocha
194ba103b1 [BUILD] Fixed error when compiling in systems with multiple versions of python installed (#1019) 2022-12-29 15:10:34 -08:00
Phil Tillet
71e3143eaf . 2022-12-29 14:40:27 -08:00
goostavz
1d3029faf8 [Backend] Add value cache in emitting indices calculation and some refinement (#1018) 
1, add explicit value cache in emitting indices calculation;
2, move the indices calculation emitting logics into
ConvertTritonGPUOpToLLVMPatternBase to avoid the redundant build cost by
templates. Refer to the discussion in this thread by @LyricZhao :
https://triton-lang.slack.com/archives/C042VBSQWNS/p1671336755922969
 2022-12-29 11:19:59 -08:00
Phil Tillet
263ad883a6 . 2022-12-28 14:23:59 -08:00
Phil Tillet
54ae3e8d6e cleanup 2022-12-28 13:42:43 -08:00
Phil Tillet
7aba2a60d6 trying out another change 2022-12-27 21:51:51 -08:00
Phil Tillet
eefc9d1274 Added TTGIR kernel 2022-12-27 21:49:28 -08:00
Phil Tillet
0d6e6cf578 trying more things 2022-12-27 20:58:31 -08:00
Yan Chunwei
2ba74d2729 [OPTIMIZER] Update the versionMinor in MMA layout for volta (#1014) 
Continue the work https://github.com/openai/triton/pull/990

# Background
The `versionMinor` in MmaEncodingAttr holds some states of DotOp's
operands in Volta, while such operands will be modified by some
patterns, making the states out-of-date.

This PR helps to correct the states.

# Implementation
It adds three new patterns:

1. `CollectMmaToUpdateForVolta` helps to collect and build a map holding
the MmaEncodingAttr instances with wrong states and create new correct
ones for them,
2. `UpdateMMAVersionMinorForVolta` helps to replace the Ops generating
the wrong MmaEncodingAttr instances with new correct ones, currently it
supports the following Ops
    a. `convert_layout[X -> mma]`
    b. `arith.constant SplatAttr : !tensor<mma>`
    c. `dot ... : !tensor<mma>`

# Limitation
This PR chooses the mapping way to bypass the IR walk complexity from
the circular dependency between dot_operand[parent] and mma.
We use the MmaEncodingAttr instance as the mapping key, but there might
be multiple DotOp holding different DotOprand(IsMMAv1Row) that have the
same wrong MmaEncodingAttr instance.
To make each DotOp's (wrong) MmaEncodingAttr unique, we might need an ID
field to MmaEncodingAttr.
 2022-12-28 12:24:01 +08:00
Philippe Tillet
4182e90862 less math 2022-12-24 00:31:05 -08:00
Keren Zhou
fd2da4aff6 [BACKEND] Support splat constant on the DotOperandLayout (#1008) 2022-12-22 00:48:46 -08:00
Sharad Vikram
925d3d7f98 [FRONTEND] Export broadcast and broadcast_to in triton.language (#1007) 2022-12-22 01:57:33 +00:00
Philippe Tillet
033e82060d . 2022-12-21 14:02:10 -08:00
Phil Tillet
88e572e54d . 2022-12-21 13:54:30 -08:00
Keren Zhou
b5aafb0dab [FRONTEND] Fix 3d indexing (#1006) 2022-12-21 12:52:32 -08:00
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) legacy-backend 2022-12-02 11:13:46 -08:00
Crutcher Dunnavant
44f577984d Fix format double substitution bug: {i} => {{i}} (#886) 
The previous `{i}` was silently expanding to the `i` from the
enumeration loop on `regular_args` (when it wasn't empty).
 2022-11-20 11:44:42 -08:00