Commit Graph
Select branches
Hide Pull Requests
fix-extelemwise-in-combine-ops
gh-pages
jit-hook
keren/assert
keren/improve-hook
keren/insert-slice-other-nonzero
keren/perf-debug
keren/v100-perf-regression
master
phil/fused-attention-perf-fixup
phil/mma-v1-is-row-debug
phil/swizzle-bug-repro
port-fma
rocm
#10
#100
#1000
#1001
#1002
#1004
#1006
#1007
#1008
#101
#1010
#1012
#1013
#1013
#1014
#1018
#1019
#102
#1020
#1020
#1025
#1027
#1028
#1029
#103
#1030
#1033
#1034
#1036
#1037
#1038
#1039
#104
#1042
#1043
#1043
#105
#106
#107
#108
#109
#11
#11
#110
#111
#112
#114
#116
#118
#119
#120
#121
#123
#124
#125
#126
#127
#128
#129
#13
#131
#132
#133
#134
#135
#136
#137
#138
#139
#140
#141
#142
#143
#144
#145
#146
#147
#148
#149
#15
#151
#152
#158
#164
#165
#167
#168
#172
#173
#178
#179
#18
#180
#185
#186
#188
#19
#190
#192
#193
#195
#198
#199
#20
#200
#203
#204
#205
#207
#209
#212
#219
#22
#222
#224
#225
#228
#23
#23
#231
#24
#240
#249
#250
#251
#253
#255
#256
#257
#258
#259
#260
#261
#268
#271
#272
#273
#276
#279
#28
#280
#281
#282
#283
#285
#286
#287
#288
#291
#292
#293
#294
#295
#296
#297
#298
#299
#3
#300
#301
#302
#303
#304
#305
#306
#307
#308
#309
#311
#312
#313
#314
#317
#318
#320
#324
#326
#331
#336
#337
#338
#342
#344
#345
#346
#347
#348
#349
#35
#350
#351
#356
#357
#358
#361
#362
#367
#368
#372
#373
#374
#377
#379
#38
#380
#381
#382
#383
#386
#387
#388
#390
#391
#392
#393
#394
#395
#396
#397
#399
#40
#400
#401
#403
#406
#407
#408
#409
#41
#413
#414
#415
#417
#418
#420
#421
#422
#423
#424
#425
#426
#427
#428
#430
#431
#432
#436
#438
#439
#440
#442
#444
#445
#446
#447
#448
#449
#45
#450
#451
#453
#455
#456
#457
#458
#462
#463
#464
#467
#468
#469
#470
#471
#473
#474
#478
#481
#482
#483
#484
#485
#487
#488
#490
#491
#492
#493
#495
#499
#500
#501
#502
#503
#505
#507
#510
#513
#514
#515
#516
#519
#52
#520
#522
#523
#524
#526
#527
#528
#53
#531
#533
#534
#535
#538
#538
#539
#541
#545
#546
#547
#548
#549
#551
#552
#553
#555
#556
#557
#559
#560
#561
#562
#564
#565
#567
#569
#57
#570
#571
#572
#575
#575
#577
#578
#579
#58
#582
#587
#588
#59
#590
#595
#598
#60
#600
#601
#602
#604
#606
#607
#608
#61
#614
#614
#617
#62
#623
#63
#632
#636
#637
#644
#65
#650
#651
#652
#653
#654
#655
#657
#658
#66
#660
#661
#662
#663
#664
#665
#666
#667
#668
#669
#670
#671
#672
#678
#68
#682
#683
#684
#685
#689
#69
#691
#692
#693
#694
#696
#697
#699
#7
#70
#700
#701
#702
#703
#704
#706
#708
#709
#71
#710
#711
#712
#715
#716
#718
#722
#724
#726
#727
#728
#729
#73
#732
#733
#735
#736
#738
#739
#740
#742
#746
#747
#749
#75
#750
#751
#752
#753
#754
#755
#757
#758
#759
#764
#765
#766
#767
#769
#77
#774
#775
#776
#777
#78
#780
#782
#784
#785
#786
#788
#789
#790
#791
#792
#794
#796
#797
#798
#799
#80
#800
#801
#803
#804
#805
#809
#81
#812
#814
#815
#816
#817
#818
#819
#82
#820
#821
#822
#823
#825
#826
#827
#829
#83
#830
#831
#833
#834
#835
#836
#837
#838
#839
#840
#841
#842
#843
#844
#845
#847
#848
#849
#850
#851
#852
#853
#854
#856
#857
#858
#859
#86
#862
#863
#864
#867
#868
#869
#87
#872
#873
#874
#875
#876
#877
#878
#879
#88
#880
#881
#883
#885
#886
#887
#887
#888
#889
#89
#890
#890
#894
#896
#897
#898
#899
#90
#901
#902
#903
#904
#906
#907
#908
#909
#91
#910
#912
#913
#914
#915
#916
#917
#918
#92
#920
#921
#922
#923
#924
#925
#926
#927
#928
#929
#93
#930
#931
#933
#936
#937
#938
#939
#94
#941
#943
#944
#945
#946
#947
#947
#948
#95
#951
#952
#953
#956
#957
#958
#959
#96
#960
#961
#962
#963
#964
#966
#968
#969
#97
#970
#971
#972
#973
#975
#976
#977
#978
#979
#980
#982
#982
#983
#985
#987
#988
#990
#991
#993
#994
#995
#996
#997
#998
#999
isaac
legacy-backend
v0.1
v0.2.3
v0.4
v1.0
v1.1
v1.1.1
v1.1.2
Select branches
Hide Pull Requests
fix-extelemwise-in-combine-ops
gh-pages
jit-hook
keren/assert
keren/improve-hook
keren/insert-slice-other-nonzero
keren/perf-debug
keren/v100-perf-regression
master
phil/fused-attention-perf-fixup
phil/mma-v1-is-row-debug
phil/swizzle-bug-repro
port-fma
rocm
#10
#100
#1000
#1001
#1002
#1004
#1006
#1007
#1008
#101
#1010
#1012
#1013
#1013
#1014
#1018
#1019
#102
#1020
#1020
#1025
#1027
#1028
#1029
#103
#1030
#1033
#1034
#1036
#1037
#1038
#1039
#104
#1042
#1043
#1043
#105
#106
#107
#108
#109
#11
#11
#110
#111
#112
#114
#116
#118
#119
#120
#121
#123
#124
#125
#126
#127
#128
#129
#13
#131
#132
#133
#134
#135
#136
#137
#138
#139
#140
#141
#142
#143
#144
#145
#146
#147
#148
#149
#15
#151
#152
#158
#164
#165
#167
#168
#172
#173
#178
#179
#18
#180
#185
#186
#188
#19
#190
#192
#193
#195
#198
#199
#20
#200
#203
#204
#205
#207
#209
#212
#219
#22
#222
#224
#225
#228
#23
#23
#231
#24
#240
#249
#250
#251
#253
#255
#256
#257
#258
#259
#260
#261
#268
#271
#272
#273
#276
#279
#28
#280
#281
#282
#283
#285
#286
#287
#288
#291
#292
#293
#294
#295
#296
#297
#298
#299
#3
#300
#301
#302
#303
#304
#305
#306
#307
#308
#309
#311
#312
#313
#314
#317
#318
#320
#324
#326
#331
#336
#337
#338
#342
#344
#345
#346
#347
#348
#349
#35
#350
#351
#356
#357
#358
#361
#362
#367
#368
#372
#373
#374
#377
#379
#38
#380
#381
#382
#383
#386
#387
#388
#390
#391
#392
#393
#394
#395
#396
#397
#399
#40
#400
#401
#403
#406
#407
#408
#409
#41
#413
#414
#415
#417
#418
#420
#421
#422
#423
#424
#425
#426
#427
#428
#430
#431
#432
#436
#438
#439
#440
#442
#444
#445
#446
#447
#448
#449
#45
#450
#451
#453
#455
#456
#457
#458
#462
#463
#464
#467
#468
#469
#470
#471
#473
#474
#478
#481
#482
#483
#484
#485
#487
#488
#490
#491
#492
#493
#495
#499
#500
#501
#502
#503
#505
#507
#510
#513
#514
#515
#516
#519
#52
#520
#522
#523
#524
#526
#527
#528
#53
#531
#533
#534
#535
#538
#538
#539
#541
#545
#546
#547
#548
#549
#551
#552
#553
#555
#556
#557
#559
#560
#561
#562
#564
#565
#567
#569
#57
#570
#571
#572
#575
#575
#577
#578
#579
#58
#582
#587
#588
#59
#590
#595
#598
#60
#600
#601
#602
#604
#606
#607
#608
#61
#614
#614
#617
#62
#623
#63
#632
#636
#637
#644
#65
#650
#651
#652
#653
#654
#655
#657
#658
#66
#660
#661
#662
#663
#664
#665
#666
#667
#668
#669
#670
#671
#672
#678
#68
#682
#683
#684
#685
#689
#69
#691
#692
#693
#694
#696
#697
#699
#7
#70
#700
#701
#702
#703
#704
#706
#708
#709
#71
#710
#711
#712
#715
#716
#718
#722
#724
#726
#727
#728
#729
#73
#732
#733
#735
#736
#738
#739
#740
#742
#746
#747
#749
#75
#750
#751
#752
#753
#754
#755
#757
#758
#759
#764
#765
#766
#767
#769
#77
#774
#775
#776
#777
#78
#780
#782
#784
#785
#786
#788
#789
#790
#791
#792
#794
#796
#797
#798
#799
#80
#800
#801
#803
#804
#805
#809
#81
#812
#814
#815
#816
#817
#818
#819
#82
#820
#821
#822
#823
#825
#826
#827
#829
#83
#830
#831
#833
#834
#835
#836
#837
#838
#839
#840
#841
#842
#843
#844
#845
#847
#848
#849
#850
#851
#852
#853
#854
#856
#857
#858
#859
#86
#862
#863
#864
#867
#868
#869
#87
#872
#873
#874
#875
#876
#877
#878
#879
#88
#880
#881
#883
#885
#886
#887
#887
#888
#889
#89
#890
#890
#894
#896
#897
#898
#899
#90
#901
#902
#903
#904
#906
#907
#908
#909
#91
#910
#912
#913
#914
#915
#916
#917
#918
#92
#920
#921
#922
#923
#924
#925
#926
#927
#928
#929
#93
#930
#931
#933
#936
#937
#938
#939
#94
#941
#943
#944
#945
#946
#947
#947
#948
#95
#951
#952
#953
#956
#957
#958
#959
#96
#960
#961
#962
#963
#964
#966
#968
#969
#97
#970
#971
#972
#973
#975
#976
#977
#978
#979
#980
#982
#982
#983
#985
#987
#988
#990
#991
#993
#994
#995
#996
#997
#998
#999
isaac
legacy-backend
v0.1
v0.2.3
v0.4
v1.0
v1.1
v1.1.1
v1.1.2
-
66fa2f2975
.
phil/fused-attention-perf-fixup
Philippe Tillet
2023-01-09 23:11:51 -08:00 -
b162c44d59
. y
Philippe Tillet
2023-01-09 22:58:40 -08:00 -
2fa0dfbce9
.
Phil Tillet
2023-01-09 22:50:38 -08:00 -
993bc17311
cleanup
Phil Tillet
2023-01-09 22:35:00 -08:00 -
ff04a5e9b6
.
Philippe Tillet
2023-01-09 22:11:00 -08:00 -
d88353a5a4
.
Phil Tillet
2023-01-09 20:14:06 -08:00 -
bae4c40379
reorder conversions to dot operand
Phil Tillet
2023-01-09 20:11:22 -08:00 -
c98c889d7f
.
Phil Tillet
2023-01-09 19:08:51 -08:00 -
fc1007278d
.
Phil Tillet
2023-01-09 18:45:44 -08:00 -
0c101e0c33
.
Phil Tillet
2023-01-09 16:30:28 -08:00 -
3fefcd78d4
.
Phil Tillet
2023-01-09 16:29:45 -08:00 -
137e866bd2
more work
Phil Tillet
2023-01-09 16:20:10 -08:00 -
8ebb593bbb
more work
Phil Tillet
2023-01-09 15:45:06 -08:00 -
d9392c0fd3
Pass function arguments to JITFunction's call_hook
jit-hook
Da Yan
2023-01-09 20:53:20 +00:00 -
0f5c6e619c
[BUILD] Add the missing triton/impl to setup.py (#1042)
master
Da Yan
2023-01-09 11:03:45 -08:00 -
c20215dad1
[FRONTEND] Update PTX/SM support for LLVM14 (PR #1038 redux) (#1039)
Connor Baker
2023-01-09 13:31:55 -05:00 -
6c750b6856
Added verifier for trans
Phil Tillet
2023-01-08 14:29:17 -08:00 -
733301ff31
[Backend] Rewrite code for linking external library to expose more inlining opportunities (#1037)
Keren Zhou
2023-01-08 16:44:29 -05:00 -
42421fabc5
.
Phil Tillet
2023-01-06 20:35:57 -08:00 -
600bcefb12
more optimizations
Phil Tillet
2023-01-06 20:27:49 -08:00 -
ff399fbc20
[Build] Support GCC 8.x to build Triton (#1036)
Shintaro Iwasaki
2023-01-06 19:36:14 -08:00 -
18c7a72973
more pass template
Philippe Tillet
2023-01-06 14:26:06 -08:00 -
b16aeb6541
added missing file
Phil Tillet
2023-01-06 13:39:54 -08:00 -
a81345f7c1
SinkConversionsFromShared template
Phil Tillet
2023-01-06 13:01:08 -08:00 -
874ee11ab5
More optimizations
Philippe Tillet
2023-01-06 11:04:20 -08:00 -
e6f1a9ad34
commenting dq but not load/store
Philippe Tillet
2023-01-05 23:25:41 -08:00 -
6f997f4ecb
dq now mma
Philippe Tillet
2023-01-05 20:46:15 -08:00 -
520b69fe70
more reassociation
Phil Tillet
2023-01-05 16:05:11 -08:00 -
4037f3b921
Add comment
keren/assert
Jokeren
2023-01-05 16:09:44 -05:00 -
fcff1a6e75
Add comment
Jokeren
2023-01-05 16:09:03 -05:00 -
764134ee34
trying to decrease register pressure
Phil Tillet
2023-01-05 13:02:38 -08:00 -
2920f6f50f
Simple assert
Jokeren
2023-01-05 15:04:08 -05:00 -
4023149ee3
[Frontend] Convert constexpr to value for store and load ops (#1030)
Keren Zhou
2023-01-05 14:40:16 -05:00 -
2193bee94e
[Example] Fix the compile function in copy_strided.py (#1029)
Gregory Axler
2023-01-05 10:37:41 -08:00 -
411bacb2a8
[FRONTEND] Add logical operations on constexprs (#1033)
Sophia Wisdom
2023-01-04 18:06:32 -08:00 -
1bde80b1e8
Added ptx code
Phil Tillet
2023-01-04 17:22:38 -08:00 -
268d2cd18d
better convert + write-back
Phil Tillet
2023-01-04 17:08:08 -08:00 -
29a1e20b58
tweak convert + trans
Phil Tillet
2023-01-04 17:02:31 -08:00 -
a601309d87
Merge branch 'master' into keren/improve-hook
keren/improve-hook
Jokeren
2023-01-04 17:40:10 -05:00 -
36da342893
.
Phil Tillet
2023-01-04 11:25:03 -08:00 -
e70e1e76b4
swizzling
Phil Tillet
2023-01-04 11:21:19 -08:00 -
e3c3d9fc65
16 spills
Phil Tillet
2023-01-04 00:01:22 -08:00 -
bc73bbb12c
[FRONTEND] Fix argmin/max output type (#1012)
Sharad Vikram
2023-01-04 15:12:16 +08:00 -
ee86ea9c90
100 spills
Phil Tillet
2023-01-03 20:52:00 -08:00 -
645fa5c1cd
.
Phil Tillet
2023-01-03 18:34:05 -08:00 -
8df1fa5e5b
Merge remote-tracking branch 'origin/master' into phil/fused-attention-perf-fixup
Phil Tillet
2023-01-03 18:31:34 -08:00 -
8460ea3df1
[Frontend] Fix import for libdevice (#1028)
Keren Zhou
2023-01-03 18:48:05 -05:00 -
678b9f53a2
[Backend] Use post-order traversal for liveness numbering (#1027)
Keren Zhou
2023-01-03 18:11:54 -05:00 -
737e43a627
more tests
Phil Tillet
2023-01-03 09:48:08 -08:00 -
08366b2d59
Repro swizzling bug
phil/swizzle-bug-repro
Phil Tillet
2023-01-02 23:44:25 -08:00 -
5c01c567b9
.
Phil Tillet
2023-01-02 23:13:12 -08:00 -
05920e0b8b
reduced some spilling
Phil Tillet
2023-01-02 19:28:54 -08:00 -
c11fe351e1
.
Phil Tillet
2023-01-02 19:16:06 -08:00 -
b246d85fad
trying to figure out spilling root cause
Phil Tillet
2022-12-30 15:21:00 -08:00 -
4dce8dd709
Merge remote-tracking branch 'origin/master' into phil/fused-attention-perf-fixup
Phil Tillet
2022-12-30 11:53:49 -08:00 -
0e8590f1c9
[BACKEND] Add generic support of convert_layout from distributed to shared (#1025)
goostavz
2022-12-31 03:29:58 +08:00 -
7388fb1de9
manual ttgir in bwd pass
Phil Tillet
2022-12-29 15:53:38 -08:00 -
194ba103b1
[BUILD] Fixed error when compiling in systems with multiple versions of python installed (#1019)
fdrocha
2022-12-29 23:10:34 +00:00 -
71e3143eaf
.
Phil Tillet
2022-12-29 14:40:27 -08:00 -
1d3029faf8
[Backend] Add value cache in emitting indices calculation and some refinement (#1018)
goostavz
2022-12-30 03:19:59 +08:00 -
263ad883a6
.
Phil Tillet
2022-12-28 14:23:59 -08:00 -
54ae3e8d6e
cleanup
Phil Tillet
2022-12-28 13:42:43 -08:00 -
7aba2a60d6
trying out another change
Phil Tillet
2022-12-27 21:51:51 -08:00 -
eefc9d1274
Added TTGIR kernel
Phil Tillet
2022-12-27 21:49:28 -08:00 -
0d6e6cf578
trying more things
Phil Tillet
2022-12-27 20:58:31 -08:00 -
2ba74d2729
[OPTIMIZER] Update the versionMinor in MMA layout for volta (#1014)
Yan Chunwei
2022-12-28 12:24:01 +08:00 -
4182e90862
less math
Philippe Tillet
2022-12-24 00:31:05 -08:00 -
fd2da4aff6
[BACKEND] Support splat constant on the DotOperandLayout (#1008)
Keren Zhou
2022-12-22 00:48:46 -08:00 -
925d3d7f98
[FRONTEND] Export
broadcast
andbroadcast_to
intriton.language
(#1007)Sharad Vikram
2022-12-21 17:57:33 -08:00 -
033e82060d
.
Philippe Tillet
2022-12-21 14:02:10 -08:00 -
88e572e54d
.
Phil Tillet
2022-12-21 13:54:30 -08:00 -
b5aafb0dab
[FRONTEND] Fix 3d indexing (#1006)
Keren Zhou
2022-12-21 12:52:32 -08:00 -
20100a7254
Merge
triton-mlir
branch - Complete rewrite of the backend from scratch (#1004)Philippe Tillet
2022-12-21 01:30:50 -08:00 -
65896aef9d
Debugging
keren/v100-perf-regression
Jokeren
2022-12-13 11:17:40 -08:00 -
d8d6b9f3f1
Fix v100 fp32
Jokeren
2022-12-12 15:52:16 -08:00 -
3a1c140385
Add script
Jokeren
2022-12-12 12:10:40 -08:00 -
0cfe909df8
[Triton-MLIR][BACKEND] some code clean on the backend (#978)
Yan Chunwei
2022-12-12 17:46:16 +08:00 -
e5cfa0f633
[FRONTEND] Added a few assertions in
semantic.dot
(#977)Philippe Tillet
2022-12-12 00:07:14 -08:00 -
e552219104
[FRONTEND] Add possibility for user to force a GPU threadsync barrier (#976)
Philippe Tillet
2022-12-11 23:03:52 -08:00 -
52accd4c2b
[BACKEND] Add isRow attribute for DotOp tensors whose parent is mmav1 (#970)
Philippe Tillet
2022-12-11 19:01:57 -08:00 -
4fb048873a
[Triton-MLIR][CI] Fix v100 tests to avoid skiping tests mistakely (#975)
Yan Chunwei
2022-12-11 12:57:51 +08:00 -
be2f70699c
[BACKEND][FRONTEND] Fix problems with test_matmul (#973)
Keren Zhou
2022-12-10 20:34:58 -08:00 -
58d2867fe6
testing things...
phil/mma-v1-is-row-debug
Phil Tillet
2022-12-09 19:31:34 -08:00 -
24fd953f9a
[BACKEND] Refine v100 tests and fix mmav1 numwarps>1 hang issue (#971)
Yan Chunwei
2022-12-09 23:41:22 +08:00 -
793012b4c4
[Triton-MLIR][Backend] Fix mmav1 in case of numWarps > 1 (#972)
goostavz
2022-12-09 18:36:05 +08:00 -
fa6dbbff60
.
Phil Tillet
2022-12-08 21:36:47 -08:00 -
13644e7ac4
adapt isMMAv1Row in backend (#969)
Yan Chunwei
2022-12-09 12:52:43 +08:00 -
0d27912554
[OPTIMIZER] Added isRow attribute for dotOperandEncoding of MMAv1 layout
Phil Tillet
2022-12-08 18:31:16 -08:00 -
3ed36dcb4d
[BACKEND] MMA->DotOperand conversion for chain dot of float32 tensors (#962)
Keren Zhou
2022-12-08 12:11:51 -08:00 -
83f3b9165b
[FRONTEND][BACKEND] Fix bool and int8 load when the other operand is given (#968)
Keren Zhou
2022-12-08 11:52:18 -08:00 -
71c35bcf9c
[Triton-MLIR][BACKEND] Mark float to integer in Arithmetic Dialect as legal (#963)
Keren Zhou
2022-12-08 09:07:01 -08:00 -
c7cf9c6a32
[TRITON-MLIR][BACKEND]fix atomic_rmw for vector (#966)
Dongdong Li
2022-12-08 20:03:40 +08:00 -
f0885e9caf
[Triton-MLIR][BACKEND] Tiny patch for MMAv1 and code clean (#964)
Yan Chunwei
2022-12-08 16:39:32 +08:00 -
18e683d9bb
[Triton-MLIR][BACKEND] Pass compute capability from the frontend and code cleanup (#961)
Keren Zhou
2022-12-07 15:03:46 -08:00 -
4eab9dcedf
[Triton-MLIR][BACKEND] make MMAv1 splitk works (#960)
Yan Chunwei
2022-12-07 16:58:38 +08:00 -
b2b793dfb5
[FRONTEND][BACKEND] Fixes for cat / reshape / addptr (#959)
Philippe Tillet
2022-12-06 23:29:50 -08:00 -
981aee7f1e
[FRONTEND] Frontend fixes for uint / for loops / random (#958)
Philippe Tillet
2022-12-06 20:25:47 -08:00 -
43408fef5a
Fix
keren/insert-slice-other-nonzero
Jokeren
2022-12-06 17:09:09 -08:00 -
e817fdf1b9
Fix
Jokeren
2022-12-06 13:46:21 -08:00 -
8dd099beef
Fix
Jokeren
2022-12-06 13:31:42 -08:00