Google Git
Sign in
opensecura / 3p / openxla / iree / ebb5b7d4a3c59b8dac9c5a4fe4ba78f0c736dc7f / llvm-external-projects
  1. 671b092 Split transform.tile_and_decompose_attention (#15516) by Kunwar Grover · 1 year, 5 months ago
  2. db7311b Use rewriter based methods for replacing in TileAndDecomposeAttention (#15514) by Kunwar Grover · 1 year, 5 months ago
  3. 5137b95 [DataTiling] Add supports for materializing elementwise ops. (#15507) by Max191 · 1 year, 5 months ago
  4. d5ab0f0 Revert "[DataTiling] Add supports for materializing elementwise ops. (#15446)" by Stella Laurenzo · 1 year, 5 months ago
  5. bd60372 [DataTiling] Add supports for materializing elementwise ops. (#15446) by Max191 · 1 year, 5 months ago
  6. 7ab3509 Record narrow static M/N sizes in `EncodingAttr` and rationalize MaterializeEncoding for narrow shapes. (#15431) by bjacob · 1 year, 5 months ago
  7. ddb0d7d Let `EncodingAttr` use `struct(params)` assembly format (#15434) by bjacob · 1 year, 5 months ago
  8. 668c020 Cast tensor.empty type to TypeConverter's type during materialization. (#15375) by Han-Chung Wang · 1 year, 5 months ago
  9. 03d655a Fix size calculation in the tensor.empty materialization pattern. (#15359) by Han-Chung Wang · 1 year, 5 months ago
  10. 546e372 Add fallback for undo-ing encodings. (#15302) by Han-Chung Wang · 1 year, 5 months ago
  11. 11debb4 bump LLVM to acc6f3e9c1af6c7445aae6f10d4b016ac84112d3 (#15296) by bjacob · 1 year, 5 months ago
  12. 39afb04 [Winograd] Adapt winograd for tiling + implement tiling/decompose (#15250) by Abhishek Varma · 1 year, 5 months ago
  13. e9f4b1e [Flow] Add TensorBitCastOp (#15260) by Quinn Dawkins · 1 year, 5 months ago
  14. 78e9dbc [FlashAttention] Adapt attention for tiling + implement tiling/decompose (#15217) by Abhishek Varma · 1 year, 5 months ago
  15. 3a70dda Improving the `*.tensor.trace` op to carry shapes/encodings. (#15228) by Ben Vanik · 1 year, 6 months ago
  16. e8f184d Revert "[LLVMGPU] Splitting TensorCoreVectorization to two passes." (#15225) by Han-Chung Wang · 1 year, 6 months ago
  17. a9d7aa5 [Cleanup] Retire filter-based vectorization patterns. (#15185) by Han-Chung Wang · 1 year, 6 months ago
  18. 46a2305 Integrate llvm 20231012 (#15163) by Stella Laurenzo · 1 year, 6 months ago
  19. 9d7a4ba Data-tiling encodings: take the element types out of the enums. (#15182) by bjacob · 1 year, 6 months ago
  20. 89031fc Delete duplicate canonicalization patterns from LinalgExt dialect. (#12124) by Han-Chung Wang · 1 year, 6 months ago
  21. 9c424c4 [LinalgExt] Remove LinalgExt::Softmax and use upstream linalg::softmax (#15021) by Abhishek Varma · 1 year, 6 months ago
  22. fee7f6a [LLVMExternalProjects] Drop the IREE LinalgTransformDialect (#15067) by Quinn Dawkins · 1 year, 6 months ago
  23. 4e6d841 Integrate LLVM 2023-09-27 (#15048) by Stella Laurenzo · 1 year, 6 months ago
  24. de51b22 Integrate llvm 20230922 (#15020) by Stella Laurenzo · 1 year, 6 months ago
  25. fb9e1b6 Adding `--iree-vulkan-experimental-indirect-bindings=true` flag. (#14977) by Ben Vanik · 1 year, 7 months ago
  26. 04259d0 Integrate llvm-project at f66cd9e9556a53142a26a5c21a72e21f1579217c (#14980) by Stella Laurenzo · 1 year, 7 months ago
  27. 6e41b55 Fix build warning (-Wreturn-type) in MaterializeEncoding.cpp with GCC (#14981) by Jie Fu (傅杰) · 1 year, 7 months ago
  28. 02a355e Integrate llvm-project and bump dependencies 20230909 (#14941) by Diego Caballero · 1 year, 7 months ago
  29. 118ccdd [LLVMCPU] Set encoding on batch_matmul ops (#14870) by Jerry Wu · 1 year, 7 months ago
  30. a705de3 Materialize batch_matmul to batch_mmt4d (#14731) by Jerry Wu · 1 year, 7 months ago
  31. 8314b5c Support default configs for BATCH_MATMUL_* in MaterializeEncoding pass (#14762) by Jerry Wu · 1 year, 7 months ago
  32. 5142828 [IREEInput] Add iree_input.buffer.subspan operation (#14756) by Eugene Zhulenev · 1 year, 7 months ago
  33. 858dcfe Add materialization of set/unset encoding for `batch_matmul` (#14705) by Jerry Wu · 1 year, 8 months ago
  34. 7e37aeb Integrate llvm-project at 030e315ee771 (#14678) by Han-Chung Wang · 1 year, 8 months ago
  35. 528fdd5 Integrate llvm-project at 913f21ae5c46 (#14659) by Han-Chung Wang · 1 year, 8 months ago
  36. 1ef5acf Integrate llvm-project@679c076ae446 (#14573) by Okwan Kwon · 1 year, 8 months ago
  37. 93f86d9 Integrate llvm-project@3eebf005ca07 (#14543) by Okwan Kwon · 1 year, 8 months ago
  38. 24e9133 Integrate llvm-project at 2dc1a27449a9 (#14532) by Han-Chung Wang · 1 year, 8 months ago
  39. 01a763e Integrate llvm-project at 4706251a3186 (#14505) by Han-Chung Wang · 1 year, 8 months ago
  40. a5a6b67 [IREEInput] Add !iree_input.byte_buffer and byte buffer constants (#14486) by Eugene Zhulenev · 1 year, 8 months ago
  41. 299e16a Remove `RematerializeParallelOps` pass. (#14453) by MaheshRavishankar · 1 year, 9 months ago
  42. 5bee76d [IREEInput] Add missing iree_input.buffer_view.create builders (#14429) by Eugene Zhulenev · 1 year, 9 months ago
  43. bfe32bd [TransformStrategies] Add implicit gemm for aligned convolutions in CUDA (#13449) by Quinn Dawkins · 1 year, 9 months ago
  44. 09685ee data-tiling: introduce `upper_bound_tile_size` op to defer padding-size choice to MaterializeEncoding. (#14349) by bjacob · 1 year, 9 months ago
  45. deb69a2 Generate doc pages for iree-dialects. (#14388) by Scott Todd · 1 year, 9 months ago
  46. 17d1c85 Update tile and decompose attention pass (#13950) by harsh-nod · 1 year, 9 months ago
  47. 0061355 Change LinalgExt::EncodingAttr from enum to structured. (#14336) by bjacob · 1 year, 9 months ago
  48. ac34d7b [NFC] IREEInput/Util: Simplify loops with llvm range helpers (#14334) by Eugene Zhulenev · 1 year, 9 months ago
  49. 55b4d17 Integrate llvm-project at d6e9efab8 (#14304) by Han-Chung Wang · 1 year, 9 months ago
  50. 08f969a LinalgExt: remove EncodingAttr, redundant with TensorEncodingAttr (#14323) by bjacob · 1 year, 9 months ago
  51. 3cee690 [IREEInput] Add executable source and dispatch operations (#14290) by Eugene Zhulenev · 1 year, 9 months ago
  52. 0b1cacd [IREEInput] Add TiedOpInterface and optimization barrier op (#14289) by Eugene Zhulenev · 1 year, 9 months ago
  53. c1ec61d [IREEInput] Add support for buffers and constructing buffer views (#14278) by Eugene Zhulenev · 1 year, 9 months ago
  54. 3a64294 Extend TD strategy to support batched matmul (#14292) by Oleksandr "Alex" Zinenko · 1 year, 9 months ago
  55. 52b967c data-tiling for `f16` and `bf16` matmuls (#14207) by bjacob · 1 year, 9 months ago
  56. 2b7d51e Integrate llvm-project at d179421099314431a91b85c01977ba0086ffd6db (#14188) by Kojo Acquah · 1 year, 9 months ago
  57. ae70815 Pipeclean byo_llvm, add docs and support requested features. (#14164) by Stella Laurenzo · 1 year, 9 months ago
  58. 928a590 Integrate llvm-project at 88f07a31 (#14165) by Matthias Springer · 1 year, 9 months ago
  59. be24f02 Use Black to format Python files (#14161) by Jakub Kuderski · 1 year, 10 months ago
  60. 2e4487d [iree-dialects][test] Remove dead code from the transfrom script (#14127) by qcolombet · 1 year, 10 months ago
  61. 8357ea4 Use upstreamed ApplyPatternsOp in buildCanonicalizationAndEnablingTransforms (#14026) by Matthias Springer · 1 year, 10 months ago
  62. c12bf50 Harden the PadOp matcher (#14024) by Nicolas Vasilache · 1 year, 10 months ago
  63. c620ab2 Clean up CapturingOpMatcher and derived classes, NFC (#14022) by Oleksandr "Alex" Zinenko · 1 year, 10 months ago
  64. f3d0369 Add codegen strategy for GPU padding (#14000) by Nicolas Vasilache · 1 year, 10 months ago
  65. 377d27a Integrate llvm-project at https://github.com/llvm/llvm-project/commit/85b77b13e3bcccffeb84b09365e0ab96565467fa (#13975) by MaheshRavishankar · 1 year, 10 months ago
  66. 4c1ceb2 Make reduction/matmul/conv matchers optionally partial (#13981) by Oleksandr "Alex" Zinenko · 1 year, 10 months ago
  67. 815e843 Make IREEDialectsTransforms cmake target export includes (#13980) by Oleksandr "Alex" Zinenko · 1 year, 10 months ago
  68. 5b0c36e [NFC] Switch to_vector(map_range(...)) to map_to_vector (#13931) by Han-Chung Wang · 1 year, 10 months ago
  69. 22f04e9 Better TrackingListener error messages (#13756) by Matthias Springer · 1 year, 10 months ago
  70. a6aa49b Bump LLVM to llvm/llvm-project@2d731904 (#13800) by Matthias Springer · 1 year, 10 months ago
  71. f72ed79 Add shaped value transform matchers and small refactor (#13843) by Oleksandr "Alex" Zinenko · 1 year, 10 months ago
  72. 7a462a5 Update transform op definitions to use transform types (#13774) by Lei Zhang · 1 year, 10 months ago
  73. 15917f1 Extend linalg-ext attention to support cross attention (#13761) by harsh-nod · 1 year, 10 months ago
  74. 2787dd5 Update LLVM to llvm/llvm-project@33da608 (#13666) by Murali Vijayaraghavan · 1 year, 10 months ago
  75. f4642c6 Adding the inliner interface to the linalg_ext dialect. (#13673) by Ben Vanik · 1 year, 11 months ago
  76. ebde1b1 Cleanup: Use upstream TransformInterpreterPassBase (#13633) by Matthias Springer · 1 year, 11 months ago
  77. 29c6e8d Clarify comment in transform matchers and improve debug statements (#13546) by Quinn Dawkins · 1 year, 11 months ago
  78. 8f387c6 [Transform] Capture the element types of the matmul in the matcher (#13497) by Quinn Dawkins · 1 year, 11 months ago
  79. ebf8e51 Integrate llvm-project at 0c852dc88e9276b74532fd7d233dd23ec1bbed6f (#13486) by Jakub Kuderski · 1 year, 11 months ago
  80. f3e7043 Fix bug in tile and decompose attention with dynamic shapes (#13485) by harsh-nod · 1 year, 11 months ago
  81. a97c63f Reassemble 32-bit float complex into a 64-bit float for splats. (#13363) by Balaji V. Iyer · 1 year, 11 months ago
  82. 2ded79b Fix broken tests (#13406) by Matthias Springer · 1 year, 11 months ago
  83. 354fea5 Integrate llvm/llvm-project@dc275fd03254 (#13338) by Lei Zhang · 1 year, 11 months ago
  84. ebf8490 Integrate llvm/llvm-project@be9c91843bab (#13296) by Lei Zhang · 2 years ago
  85. 3537df7 Stop preserving `"encoding"` attribute on `pack` op. (#13293) by bjacob · 2 years ago
  86. 52861ca Integrate llvm-project at 9e9b1effac34 and bump dependencies (#13232) by Kojo Acquah · 2 years ago
  87. c59cf83 NFC - Improve debug messages around transform dialect matching (#13226) by Nicolas Vasilache · 2 years ago
  88. cf3d786 Add a transform dialect CUDA strategy for unaligned f32 matmul that are still divisible by 4 (#13098) by Thomas · 2 years ago
  89. 87ef655 Add a structured op matcher for 2d convolutions (#12805) by Quinn Dawkins · 2 years ago
  90. 4ce5fb6 Switch to upstream the TrackingListener (#12775) by Matthias Springer · 2 years ago
  91. 862f414 Loosen requirements on iree_linalg_ext.scatter for complex types (#13055) by Rob Suderman · 2 years ago
  92. df7522b Integrate LLVM at llvm/llvm-project@203cd159 (#13001) by Thomas · 2 years ago
  93. 9364cf7 Fix check on iree_linalg_ext.scatter for dynamic shapes (#12996) by Rob Suderman · 2 years ago
  94. 4052d2d Add operand to lower_to_llvm transform op (#12951) by Matthias Springer · 2 years ago
  95. af4c377 Introduce LLVMCPUVectorLowering to get rid of StrategyLowerVectors pass. (#12845) by Han-Chung Wang · 2 years ago
  96. eeb7189 Migrate LLVMCPU vectorization to its own pass. (#12837) by Han-Chung Wang · 2 years ago
  97. 89f4b4d Enable vectorization of tosa.resize (#12288) by Diego Caballero · 2 years ago
  98. 4067e74 Delete upstreamed AffineBuilder. (#12863) by Han-Chung Wang · 2 years ago
  99. 3fe488b Delete SCFTilingPattern declaration which was missed in previous commit. (#12864) by Han-Chung Wang · 2 years ago
  100. 72247dd Delete LinalgExt FoldIntoPackAndUnpackOps pass. (#12860) by Han-Chung Wang · 2 years ago