Google Git
Sign in
opensecura / 3p / openxla / iree / 9fb3343534f44dabd8ccdd8648ff8ae0be1dbd76
  1. 9fb3343 [LLVMGPU] Remove old LLVMGPULayoutAnalysisAndDistribution (#18115) by Kunwar Grover · 7 months ago
  2. 60b65f3 Bump LLVM to llvm/llvm-project@4dbaef6 (#18348) by MaheshRavishankar · 7 months ago
  3. bd78854 [torch] Support `torch.aten.view.dtype` conversion to `flow` (#18346) by Rob Suderman · 7 months ago
  4. f8d8e60 Bump torch-mlir (#18345) by Rob Suderman · 7 months ago
  5. d8f0fc3 Add hoist support for index type (#18303) by jinchen · 7 months ago
  6. cc44a85 Rework special model testing to avoid shared cache interference. (#18344) by saienduri · 7 months ago
  7. eb694f1 [Codegen][GPU] Handle dynamic and unaligned cases in DerivedThreadConfig (#18281) by Quinn Dawkins · 7 months ago
  8. e3936dc [GPU][NFC] Update comments for MMAAttr attribute (#18339) by Han-Chung Wang · 7 months ago
  9. 70d212b Enable riscv64 ci jobs in pkgci.yml. (#18274) by Alex Chiang · 7 months ago
  10. 56ecef7 Integrate LLVM at llvm/llvm-project@84aa02d3fa1f1f614c4f3c144ec118b2f05ae6b0 (#18334) by Kunwar Grover · 7 months ago
  11. 5c576ca [Codegen][Common] Reorder layout analysis to preserve anchored to_layout (#18304) by Stanley Winata · 7 months ago
  12. a0945cc [Flow] Add pass to bubble and hoist encoding ops out of dispatch regions (#18063) by Max191 · 7 months ago
  13. c6924b6 [EmitC] Remove array related macros from `ops_emitc.h` (#18335) by Simon Camphausen · 7 months ago
  14. 8da4564 Revert "[Flow] Convert from tensor.cast to flow.tensor.reshape early …(#18256)" (#18331) by Nirvedh Meshram · 7 months ago
  15. 588732c Re-land e2e attention test suite. (#18320) by erman-gurses · 7 months ago
  16. c44d29b [compiler] Make cuda/hip/vulkan target cl options consistent (#17710) by Lei Zhang · 7 months ago
  17. d1ccc8c [Codegen] Disable transform dialect jit by default (#18305) by Nithin Meganathan · 7 months ago
  18. 292f2d4 [Stream] fix ordering issue in EmplaceAllocations (#18321) by Nirvedh Meshram · 7 months ago
  19. e7a1898 Disable Vulkan driver in macOS runtime packages. (#18324) by Scott Todd · 7 months ago
  20. 86ecf39 [hip][cuda] Merge the tracing implementations. (#18299) by Andrew Woloszyn · 7 months ago
  21. 8e42839 [Codegen][GPU] Add pass to combine value_barrier ops (#18298) by Kunwar Grover · 7 months ago
  22. 5170872 Always run GPU test jobs, regardless of path filters. (#18312) by Scott Todd · 7 months ago
  23. 6ca0613 Integrate LLVM at llvm/llvm-project@7aa22f013e24d20291aad745368ff907baa9dfa4 (#18286) by Kunwar Grover · 7 months ago
  24. e6d7bb2 Switch from w7900 to using any persistent cache runner for CPU. (#18322) by saienduri · 7 months ago
  25. b306e93 Remove pre checkout MI300 step from workflows. (#18318) by saienduri · 7 months ago
  26. d1140ae Remove unnecessary environment variables from workflows. (#18317) by saienduri · 7 months ago
  27. 1c0c5a6 [Flow] Convert from tensor.cast to flow.tensor.reshape early (#18256) by Nirvedh Meshram · 7 months ago
  28. dd8abf7 Avoid running `sudo apt update` on mi250 and mi300 runners. (#18316) by Scott Todd · 7 months ago
  29. 4c8913b Remove device "gpu number" specifications from model benchmarks. (#18315) by Scott Todd · 7 months ago
  30. 8dd1db3 Bubble expand shapes through `AttentionOp`s (#18074) by Ian Wood · 7 months ago
  31. 6a92fb7 Add onnx to InputType enum (#18310) by Tim Gymnich · 7 months ago
  32. 7c8fedc Remove PyYAML dependency from Python bindings. (#18262) by Scott Todd · 7 months ago
  33. 192c342 [Python] copy _runtime python files to install folder (#18243) by Yun Hsiang · 7 months ago
  34. 3a06719 [compiler][stream] Avoid circular dependencies between partitions in execution scheduling (#18217) by Boian Petkantchin · 7 months ago
  35. 45be749 Run GPU test jobs on changes to more paths. (#18307) by Scott Todd · 7 months ago
  36. cea581f Move LinalgQuantized* passes to GlobalOptimization (#18287) by Quinn Dawkins · 7 months ago
  37. 3af05b9 [Flow] Make CollapseDimensions iterative (#18203) by Ian Wood · 7 months ago
  38. 0247962 Revert "Add e2e test suite for the Attention - CPU Backend" (#18302) by Scott Todd · 7 months ago
  39. 137e365 [Codegen][GPU] Add pass to annotate memory spaces on allocations (#18251) by Quinn Dawkins · 7 months ago
  40. 5beb9ad [LinalgExt] Better doc for FP8 attention clamping. (#18301) by Stanley Winata · 7 months ago
  41. 5ba9a89 [LinalgExt] Reland QK scaling for attention decomp and further optimizations of it. (#18293) by Stanley Winata · 7 months ago
  42. ab0d4c6 [Codegen][GPU] Rework scf.forall fusion to support different thread counts (#18280) by Quinn Dawkins · 7 months ago
  43. 87084d5 [Codegen][GPU] Remove insert_slice semantics from shuffle_tensor (#18279) by Quinn Dawkins · 7 months ago
  44. 5f4235a Build flag IREE_EMBED_RELEASE_INFO should be IREE_EMBEDDED_RELEASE_INFO (#18285) by Cullen Rhodes · 7 months ago
  45. 95d5562 [vulkan] Update default RDNA GPU subgroup size to 32 (#18207) by Nithin Meganathan · 7 months ago
  46. 30040c7 [Codegen] Add pass to tile and distribute workgroups using `scf.forall` op. (#18266) by MaheshRavishankar · 7 months ago
  47. ed512a2 [HAL][Loader] Switch to tablegen pass generation (#18282) by Marius Brehler · 7 months ago
  48. da958c4 [HAL][Inline] Switch to tablegen pass generation (#18278) by Marius Brehler · 7 months ago
  49. eaeac86 Fix link to onnx ops test suite. (#18288) by Scott Todd · 7 months ago
  50. f224bc8 [ConstEval] Switch to tablegen pass generation (#18228) by Marius Brehler · 7 months ago
  51. 2d629c6 Add e2e test suite for the Attention - CPU Backend (#17751) by erman-gurses · 7 months ago
  52. b637a30 Refactor how `linux_x64_clang_debug` uses Docker and scripts. (#18255) by Scott Todd · 7 months ago
  53. d5c6370 Make `iree_gpu.value_barrier` accept multiple operands (and return multiple results) (#18192) by Kunwar Grover · 7 months ago
  54. aeda149 [InputConversion] Switch to tablegen pass generation (#18245) by Marius Brehler · 7 months ago
  55. 10ba28d [Codegen][GPU] Add kernel config for LLVMGPUTileAndFuse (#17791) by Quinn Dawkins · 7 months ago
  56. 7cf3fc6 [Codegen][GPU] Fix allocation space in iree_gpu.shuffle_tensor lowering (#18250) by Quinn Dawkins · 7 months ago
  57. b7efdff No-op iree_event_pool_free. by Ben Vanik · 7 months ago
  58. a884b93 Bump LLVM to llvm/llvm-project@ddda37a (#18258) by Stanley Winata · 7 months ago
  59. 0e152d2 [Codegen] Add `DeviceMappingAttr` that maps to workgroup IDs. (#18264) by MaheshRavishankar · 7 months ago
  60. f1319fc Switch some workflows to use `container:` instead of docker_run.sh. (#18252) by Scott Todd · 7 months ago
  61. 9862e99 Switch ONNX ops test suite to use iree-org/iree-test-suites. (#18223) by Scott Todd · 7 months ago
  62. 1f3ae94 Update Github runner in template to 2.319.1 (#18260) by Nancy Yuen · 7 months ago
  63. 6a12043 Deprecate c2-standard-60 in gcp scripts. (#18259) by Nancy Yuen · 7 months ago
  64. 40258db [CodeGen][DT] Make the TypeConverter carry targetAttr info. (#18242) by Han-Chung Wang · 7 months ago
  65. d25712c [VMVX] Switch to tablegen pass generation (#18248) by Marius Brehler · 8 months ago
  66. 1cbd8b7 [hip][cuda] Free resources on the completion thread. (#18247) by Andrew Woloszyn · 8 months ago
  67. 803b3bb Only build the deferred_work_queue when threading is enabled. (#18234) by Andrew Woloszyn · 8 months ago
  68. 8a1d78b [Codegen][CPU] Enable scalable transfer lowerings (#18170) by Benjamin Maxwell · 8 months ago
  69. 551cd54 [TOSA] Switch to tablegen pass generation (#18227) by Marius Brehler · 8 months ago
  70. 878a99b [torch] Switch to tablegen pass generation (#18226) by Marius Brehler · 8 months ago
  71. 12e2eb4 Fix broken link on website and stop publishing some asset files. (#18237) by Scott Todd · 8 months ago
  72. 41f1f49 [Codegen] Add a pass option to control input -> dest pattern (#18240) by Quinn Dawkins · 8 months ago
  73. 5d773e8 Remove fixed XFAILED test. by Alan Li · 8 months ago
  74. 78f54c2 [Codegen][GPU] Add a pass for basic distribution verification (#18236) by Quinn Dawkins · 8 months ago
  75. b6602e8 Updated naming in deferred work queue. (#18230) by Andrew Woloszyn · 8 months ago
  76. 3fdfb33 [hip][cuda] Added finer grained tracing options to hip. (#18180) by Andrew Woloszyn · 8 months ago
  77. 66ed138 [CPU] Make VectorPreProcStrategy consider undefined behaviors (#18146) by lialan · 8 months ago
  78. 75ad937 [hip][cuda] Merged pending_queue_actions implementations. (#18220) by Andrew Woloszyn · 8 months ago
  79. 3f97c02 [cuda][hip] Fixed tracing when device tracing is disabled at runtime (#18171) by Andrew Woloszyn · 8 months ago
  80. b144e90 [test] Check depthwise conv is vectorized in test (NFC) (#18225) by Benjamin Maxwell · 8 months ago
  81. 53a7bc4 Replace `iree_compiler::VscaleRange` with `vector::VscaleRange` (NFC) (#18218) by Benjamin Maxwell · 8 months ago
  82. 55759fa Bump torch-mlir of iree to commit 334633b (#18211) by Chi_Liu · 8 months ago
  83. 00cc478 Cleanup unused Dockerfiles and build_all.yml workflow. (#18222) by Scott Todd · 8 months ago
  84. 300af39 [codegen] Add max_workgroup_counts to TargetWgpAttr (#17771) by Krzysztof Drewniak · 8 months ago
  85. 9b05f17 Delete all in-tree benchmark infrastructure code. (#18144) by Scott Todd · 8 months ago
  86. 7d60397 [LinalgExt] Switch to new pass generation tablegen definitions. (#18216) by Han-Chung Wang · 8 months ago
  87. fe638b0 [Codegen][CPU] Eliminate all-true vector masks after vectorization (#18190) by Benjamin Maxwell · 8 months ago
  88. c71fe1a [WGSL][NFC] Switch to new pass generation tablegen definitions. (#18215) by Han-Chung Wang · 8 months ago
  89. 7cac1b2 [SPIRV] Switch to new pass generation tablegen definitions. (#18214) by Han-Chung Wang · 8 months ago
  90. a72e78b [LLVMGPU] Switch to new pass generation tablegen definitions. (#18213) by Han-Chung Wang · 8 months ago
  91. 0c2f51b [LLVMGPU] Drop WorkgroupSpecializationPass (#18212) by Nirvedh Meshram · 8 months ago
  92. 868f41e [ROCM] fix layout for WMMA_F16_16x16x16_F16 intrinsic (#18206) by Nirvedh Meshram · 8 months ago
  93. 08583d5 Bump LLVM to llvm/llvm-project@6b7afaa9db8f (#18197) by Stanley Winata · 8 months ago
  94. b297d5b [Codegen][GPU] Add bank conflict reduction pass to TileAndFuse (#18204) by Quinn Dawkins · 8 months ago
  95. 2ea9b14 [Codegen] Add support for memref.expand_shape to propagation util (#18202) by Quinn Dawkins · 8 months ago
  96. 9c951ca [Flow] Generalize horizontal contraction fusion to cover more cases. (#17880) by MaheshRavishankar · 8 months ago
  97. 7812c77 [Codegen][GPU] Add support for all other intrinsics to TileAndFuse (#18179) by Quinn Dawkins · 8 months ago
  98. 3901e62 [GPU][NFC] Update the comment of intrinsic format. (#18194) by Han-Chung Wang · 8 months ago
  99. ad2f0f8 [LLVMCPU] Add option `onlyFuseProducerInputOperands` to tileRootFuseConsumerProducer Pass (#18114) by Prashant Kumar · 8 months ago
  100. 6ac6be6 [GlobalOpt] Improve unary elementwise propagation to consider broadcasted operands (#17903) by Quinn Dawkins · 8 months ago