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

Mono Color

• c529b462f5 more fixes on pipeline.cpp Yan Da 2022-05-26 13:14:41 +08:00
• 0e2883020a [BACKEND] Fixed typo in alignment analysis (#528) Philippe Tillet 2022-05-25 20:01:19 -07:00
• 43fec2adca [FRONTEND] Add binding for create_int_to_ptr (#526) Bert Maher 2022-05-25 18:26:18 -04:00
• 71d1c10e19 Remove weird includes Yan Da 2022-05-25 21:54:06 +08:00
• 9308e9c90c A more general pipeliner Yan Da 2022-05-25 21:52:51 +08:00
• 441fd7c3cc assembly format Yan Da 2022-05-25 17:53:24 +08:00
• e6f89a5777 Fix ReduceOp conversion Yan Da 2022-05-25 16:03:06 +08:00
• 9b670cfb9f Add ReduceOp Yan Da 2022-05-25 14:15:36 +08:00
• 011bc83c1b [FRONTEND] For loops now promote initial value (#524) Philippe Tillet 2022-05-24 13:20:10 -07:00
• 96bff90471 [FRONTEND] faster jit function launch (#523) Natalia Gimelshein 2022-05-24 12:08:49 -07:00
• d5eaa8dfa0 Making the generated Triton IR deterministic & a script to compare cached assembly (#522) daadaada 2022-05-24 23:56:36 +08:00
• a2c9f919a8 TritonGPU verifier Yan Da 2022-05-24 19:48:56 +08:00
• 80f6a2698b [FRONTEND] Ensure version_key is called at most once (#519) Shantanu 2022-05-23 13:40:08 -07:00
• 36c45ec687 make numStages an option in PipelinePass Yan Da 2022-05-23 12:47:55 +08:00
• 39b1235082 fix atomic_cas Yan Da 2022-05-22 19:43:04 +08:00
• 205a493b10 [FRONTEND] Fix a bug in atomic_cas (correct cmp to val) & more tests on atomic_cas (#520) daadaada 2022-05-22 00:45:54 +08:00
• 79298d61bc fix a pipeline issue Yan Da 2022-05-16 19:38:40 +08:00
• c3c4ac3733 TritonGPU combiner Yan Da 2022-05-16 19:17:15 +08:00
• e3916c3a46 TritonGPU combiner Yan Da 2022-05-16 19:16:01 +08:00
• 0e68e6eb59 delete erroneous include Yan Da 2022-05-15 22:30:26 +08:00
• 7027af9666 The pipeline pass is now functional Yan Da 2022-05-15 22:29:27 +08:00
• abea3dc2c6 [FRONTEND] provide device kwargs && fix fstring error for py<3.8 (#515) Jiabao Lei 2022-05-15 07:21:46 +08:00
• d35617bea1 [BACKEND][CODEGEN] Faster reduction for scanline layout (#516) Philippe Tillet 2022-05-14 15:26:13 -07:00
• 7e0e7ec365 more progress on the pipeline pass Yan Da 2022-05-14 22:04:36 +08:00
• d1a22a94e6 [FRONTEND] Add empty return value and remove protect to open the access to contained_tys_vec_t (#514) Mengchi Zhang 2022-05-13 11:46:12 -07:00
• 978463ba39 more progress on the pipeline pass Yan Da 2022-05-13 21:32:35 +08:00
• d954a05989 [FRONTEND] Handle torch.uint8 args (#513) Jason Ansel 2022-05-12 13:07:39 -07:00
• 0835a4fb05 [TUTORIALS] Removed #noformat in layer norm tutorial Philippe Tillet 2022-05-12 12:41:25 -07:00
• c736ba7c3e [TUTORIALS] Fixed formatting Philippe Tillet 2022-05-12 12:30:36 -07:00
• cd30a99aa2 [TUTORIALS] fixed formatting Philippe Tillet 2022-05-12 12:28:15 -07:00
• d23d7b244c More on the pipeline pass Yan Da 2022-05-11 20:31:08 +08:00
• 1a4fbed25b Skeleton for the pipeline pass Yan Da 2022-05-11 16:13:53 +08:00
• 96876a46d1 More progress on Triton=>TritonGPU conversion (works for matmul) Yan Da 2022-05-09 21:19:53 +08:00
• d87435e536 [TUTORIALS] Layer norm tutorial now uses residency control (#510) Philippe Tillet 2022-05-05 19:53:54 -07:00
• ebf28cdc4b [GH-PAGES] Updated website Philippe Tillet 2022-05-06 00:44:25 +00:00
• 0c5319eed9 More progress on SCF type conversion Yan Da 2022-05-05 20:56:55 +08:00
• 7c9bc5a47b [CODEGEN] Change return type of generator::packed_type to appease build warnings (#507) Sriram Murali 2022-05-04 20:03:37 -07:00
• 19398e6d8a [GH-PAGES] Updated website Philippe Tillet 2022-05-05 00:44:03 +00:00
• 26c59e4718 More on SCF conversion Yan Da 2022-05-04 21:50:32 +08:00
• a96fe07e1c DotOp conversion Yan Da 2022-05-04 15:56:24 +08:00
• 2d281cbc0a ConstantOp conversion pattern Yan Da 2022-05-04 15:35:43 +08:00
• b9279d2e3b More progress on TritonGPU conversion Yan Da 2022-05-04 14:54:31 +08:00
• 3ad7bee35e More conversion patterns Yan Da 2022-05-04 12:50:02 +08:00
• d420763e0b [GH-PAGES] Updated website Philippe Tillet 2022-05-04 00:43:20 +00:00
• af77440e1b [GH-PAGES] Updated website Philippe Tillet 2022-05-03 00:45:18 +00:00
• 5f08e2fdae More arith patterns Yan Da 2022-05-02 22:31:29 +08:00
• 75d32e2442 More on TritonGPU conversion Yan Da 2022-05-02 21:51:00 +08:00
• 567aa8d4fc [GH-PAGES] Updated website Philippe Tillet 2022-05-02 00:42:39 +00:00
• 1428185c9c More progress on TritonGPUTypeConverter & TritonGPUConversionTarget Yan Da 2022-05-01 22:06:54 +08:00
• 4ece9fd1f3 Move dependentDialects from .cpp to .td Yan Da 2022-05-01 13:06:51 +08:00
• d9017f8593 add basic template for legalizing arithmetic op Phil Tillet 2022-04-30 20:42:25 -07:00
• 0bce260523 [GH-PAGES] Updated website Philippe Tillet 2022-05-01 00:49:06 +00:00
• 2c6a213131 [TRITONGPU] Added template for Triton -> TritonGPU conversion Phil Tillet 2022-04-30 14:31:18 -07:00
• 95feb10ec9 [FRONTEND] fixup (#505) Philippe Tillet 2022-04-30 14:25:06 -07:00
• e15e7e5ae2 [GH-PAGES] Updated website Philippe Tillet 2022-04-30 00:47:08 +00:00
• 11a908655d [FRONTEND] Fixup Philippe Tillet 2022-04-29 14:35:09 -07:00
• cd78ce4888 [FRONTEND] Improved error message when assigning None to non-constexpr Phil Tillet 2022-04-29 09:17:54 -07:00
• ea296daf2a [GH-PAGES] Updated website Philippe Tillet 2022-04-29 00:42:56 +00:00
• 2239ac1998 more progress on TritonGPU Yan Da 2022-04-28 18:51:31 +08:00
• e7903f3c77 [GH-PAGES] Updated website Philippe Tillet 2022-04-28 00:46:19 +00:00
• 012e8c5b2b fixup Philippe Tillet 2022-04-27 16:39:27 -07:00
• 513bcaee50 Added some ASCII art for encoding documentation Philippe Tillet 2022-04-27 16:28:27 -07:00
• 29859605ee Remove unused files Yan Da 2022-04-27 21:20:07 +08:00
• 38d13ae618 Some progress on TritonGPU Yan Da 2022-04-27 21:16:45 +08:00
• edca91bf8f Update traits (NoSideEffect) Yan Da 2022-04-27 19:41:07 +08:00
• 8dfe78f6cf Add TritonCombineOps Yan Da 2022-04-27 19:28:21 +08:00
• c70f6b666e Merge previous changes Yan Da 2022-04-27 14:06:55 +08:00
• 74585fb970 Add Triton CombineOps Yan Da 2022-04-27 13:45:56 +08:00
• 9bf9b2f3d8 [GH-PAGES] Updated website Philippe Tillet 2022-04-27 00:47:37 +00:00
• 81001d318c Putting Triton dialect in its own folder Philippe Tillet 2022-04-26 14:38:28 -07:00
• 62a64ff29b Fixed Python link bug in CMakeLists Philippe Tillet 2022-04-25 11:38:16 -07:00
• ae2a1ab225 [BACKEND] Alignment pass improvements (#503) Philippe Tillet 2022-04-25 21:16:00 -07:00
• b0a569b724 [GH-PAGES] Updated website Philippe Tillet 2022-04-26 00:43:32 +00:00
• 7d544799a0 [BACKEND] Now disabling L2 eviction policy for sm < 80 Philippe Tillet 2022-04-25 09:35:36 -07:00
• 21613349ac [GH-PAGES] Updated website Philippe Tillet 2022-04-25 00:41:43 +00:00
• 3ca792043f [TEST] Added test for vectorization Philippe Tillet 2022-04-24 13:32:35 -07:00
• 1581cf9d79 [GH-PAGES] Updated website Philippe Tillet 2022-04-24 00:44:07 +00:00
• bda209002e [BACKEND][CODEGEN] vectorization bugfix (#502) Philippe Tillet 2022-04-23 13:18:33 -07:00
• 31dd4ab60e [GH-PAGES] Updated website Philippe Tillet 2022-04-23 00:44:46 +00:00
• 0cc3b1129b [BACKEND][CODE_GEN] eviction policies now also apply to L2 (#501) Philippe Tillet 2022-04-21 23:56:01 -07:00
• 7d6c504e8d [TESTING] Added testing utilities for fixing clock and using cuda-memcheck (#500) Philippe Tillet 2022-04-21 22:40:10 -07:00
• cb69ba73a9 [GH-PAGES] Updated website Philippe Tillet 2022-04-22 00:44:52 +00:00
• ab04e47bf2 [GH-PAGES] Updated website Philippe Tillet 2022-04-21 00:45:25 +00:00
• 8d0e47d73e [GH-PAGES] Updated website Philippe Tillet 2022-04-20 00:43:07 +00:00
• 245e5ab128 [GH-PAGES] Updated website Philippe Tillet 2022-04-19 00:42:04 +00:00
• abcd11edba [GH-PAGES] Updated website Philippe Tillet 2022-04-18 00:44:04 +00:00
• 51e029840e [GH-PAGES] Updated website Philippe Tillet 2022-04-17 00:44:02 +00:00
• 9b0ee317d9 [GH-PAGES] Updated website Philippe Tillet 2022-04-16 00:44:44 +00:00
• 9e304cf79d Allow JITFunction to return multiple results Yan Da 2022-04-15 15:38:19 +08:00
• 1c52bd587d Device function & PassManager Yan Da 2022-04-15 14:41:57 +08:00
• 073be1d2ee [FRONTEND] check that tensors have power-of-two number of elements (#499) Philippe Tillet 2022-04-14 19:30:02 -07:00
• 824d060dfb [GH-PAGES] Updated website Philippe Tillet 2022-04-15 00:42:31 +00:00
• 5c7122004c [TUTORIALS] Tutorial shouldn't expose clock. Just removed it. Philippe Tillet 2022-04-14 17:33:44 -07:00
• dc4d40faec [FRONTEND] now mangle constexpr float containing "e-" Philippe Tillet 2022-04-14 10:26:48 -07:00
• 2a53636c23 [GH-PAGES] Updated website Philippe Tillet 2022-04-14 00:44:57 +00:00
• 25f6689508 [FRONTEND] rename current stream monkey patch (#495) Philippe Tillet 2022-04-13 11:45:55 -07:00
• 9d65bf62fb [GH-PAGES] Updated website Philippe Tillet 2022-04-13 00:45:31 +00:00
• 76bfac9f15 [FRONTEND] Improved constexpr handling (#493) Philippe Tillet 2022-04-12 00:02:54 -07:00
• 44d75cf9bb Bugfix in ptxas path. (#487) apd10 2022-03-30 22:45:41 -05:00
• 9be2d655a3 [DRIVER] LLVM driver fixup (#482) Philippe Tillet 2022-03-23 00:24:45 -07:00