Google Git
Sign in
opensecura / 3p / openxla / iree / f2abfa8b5bdf17ad363cad0af198278c2e700113
  1. f2abfa8 [HAL] Add option to disable executable linking (#19028) by Quinn Dawkins · 3 months ago
  2. 0344341 [NFC] Move the util passes to new-style boilerplate (#19327) by Krzysztof Drewniak · 3 months ago
  3. 886f801 [Codegen][llvmgpu] Refactor op cloning in prefetch shared memory pass (#19196) by Zhuoran Yin · 3 months ago
  4. ecd87d8 [Codegen] Add pass to materialize tuning specs (#19337) by Jakub Kuderski · 3 months ago
  5. 1684c56 Integrate llvm-project at be81df25178f4e301df9e4de75c5cbbd6f773891 (#19338) by Jakub Kuderski · 4 months ago
  6. fc1d402 [VectorDistribution] Allow 0-d vectors in scf.for distribution (#19317) by Kunwar Grover · 4 months ago
  7. b124695 [VectorDistribution] Remove signatures after distribution (#19319) by Kunwar Grover · 4 months ago
  8. d3eef09 Integrate llvm-project at 07a8ebed56cfa223d1587903e4de0d5788b5f777 (#19334) by Jakub Kuderski · 4 months ago
  9. 7f99587 Add sharktank model test to presubmits (#19329) by Rob Suderman · 4 months ago
  10. 9789438 [iree.build] Make the fetch_http action more robust. (#19330) by Stella Laurenzo · 4 months ago
  11. d182e57 Set MLIR_DISABLE_CONFIGURE_PYTHON_DEV_PACKAGES to disable MLIR python config. (#19328) by Stella Laurenzo · 4 months ago
  12. 991594e [DT][NFC] Refactor encoding utilities. (1/n) (#19310) by Han-Chung Wang · 4 months ago
  13. 516ff10 [python] Overhaul iree.build console output and error handling. (#19314) by Stella Laurenzo · 4 months ago
  14. 8272490 AMDGPU ukernels: Bazel build, separate bitcode files, c-embed archives. (#19274) by Benoit Jacob · 4 months ago
  15. 677ae42 [Global Opt] Fix transpose propagation failure (#19322) by Ian Wood · 4 months ago
  16. ad4cf1a [Codegen][LLVM] Annotate pointers an noundef + nonnull, consants as noundef (#19309) by Krzysztof Drewniak · 4 months ago
  17. 9db3473 [Codegen] Load transform library only once in MaterializeUserConfigs (#19313) by Jakub Kuderski · 4 months ago
  18. 8cf2077 Integrate with llvm-project at a807bbea6f48b368388cd796782724e3a53f58a0 (#19321) by Jakub Kuderski · 4 months ago
  19. ee3797d Add SDXL EulerDiscreteScheduler compilation test (#19315) by saienduri · 4 months ago
  20. 7adf8c1 [mlperf][pkgci] Update punet-fp8 with reduction dim as last dim (#19316) by Stanley Winata · 4 months ago
  21. 615e7ff [Codegen][NFC] Remove the HAL dependency from the Codegen dialect. (#19311) by Han-Chung Wang · 4 months ago
  22. 41115bb [Codegen] Bubble up Transpose attention V and try fuse with others before attention (#19250) by Stanley Winata · 4 months ago
  23. 5708d42 [python] Make detection of TimeoutError compatible with 3.10. (#19308) by Stella Laurenzo · 4 months ago
  24. 031accb [GPU] Use affine.linearize_index (and delinearize_index) where possible (#19122) by Krzysztof Drewniak · 4 months ago
  25. 746ad1e [GPU] Add C promotion capability in promote matmul operands pass (#19256) by Nirvedh Meshram · 4 months ago
  26. cef4178 [Codegen][NFC] Switch Dim::Kind output stream to use existing methods. (#19293) by Han-Chung Wang · 4 months ago
  27. 2e2c109 Integrate llvm-project at db6f627f3fd4072fe1814805653a352694527a91 (#19304) by Jakub Kuderski · 4 months ago
  28. a4c6f35 [LLVMGPU] Disable scf.forall distribution for matmulSimt (#19302) by Prashant Kumar · 4 months ago
  29. 8677a61 [Codegen][NFC] Move encoding structs to IREECodegenTypes.h (#19292) by Han-Chung Wang · 4 months ago
  30. 77ff99c [Python] Disable build_api concurrency test (#19298) by Jakub Kuderski · 4 months ago
  31. 4e3e898 Use `llvm::filter_to_vector`. NFC. (#19297) by Jakub Kuderski · 4 months ago
  32. ef4ecf3 [iree.build] Wire up out of process concurrency. (#19291) by Stella Laurenzo · 4 months ago
  33. 53e9601 Integrate llvm-project at fe3c23b439b9a2d00442d9bc6a4ca86f73066a3d (#19287) by Jakub Kuderski · 4 months ago
  34. 1a7b51d [Codegen][Tuner] Add pass to link tuning specs (#19281) by Jakub Kuderski · 4 months ago
  35. 3129fa9 Bump torch-mlir to 99115dcdc8cff8ce07bd027a12b001ddd7e957f3 (#19277) by saienduri · 4 months ago
  36. ee6749d Update PJRT plugin API version to 0.57 (#19241) by Twice · 4 months ago
  37. dfcb594 Replace iree-compiler with iree-base-compiler in deps of PJRT plugin (#19278) by Twice · 4 months ago
  38. fdc2d6a [NFC][GPU] Move lowering_config dictionary getter/setters out of attr (#19268) by Kunwar Grover · 4 months ago
  39. 691b65f [LLVMGPUVectorDistribute] Add a flag to enable shared memory reuse (#19266) by Manupa Karunaratne · 4 months ago
  40. 265570a Split and rename AMDGPU ukernels (#19273) by Benoit Jacob · 4 months ago
  41. 5de0f06 [Codegen] Implement serialization for MaterializeEncodingInfo struct. (#19260) by Han-Chung Wang · 4 months ago
  42. a67b00b Implement (in)equality operator and serialization for TileSwizzle. (#19257) by Han-Chung Wang · 4 months ago
  43. 3201efb Don't update snapshot branch on patch releases (#19267) by Marius Brehler · 4 months ago
  44. 7850ea9 Improve integer divisibilty inference for util.assume.int with 0 cases (#19254) by Krzysztof Drewniak · 4 months ago
  45. 38d8d0a Add build and test workflow for PJRT plugin in pkgci (#19222) by Twice · 4 months ago
  46. 12476d9 Fix GCC dangling pointer warning in ConfigTrackingListener (#19265) by Quinn Dawkins · 4 months ago
  47. 4a5187d [GPU][NFC] Move gpu pipeline transformations out of iree_gpu dialect (#19248) by Kunwar Grover · 4 months ago
  48. a467b73 [Flow] Drop transform dialect based dispatch formation (#19261) by Jakub Kuderski · 4 months ago
  49. f55a590 Update actions/cache version to latest release. (#19258) by Scott Todd · 4 months ago
  50. 2602a2a [LLVMGPU] Use scf.forall for workgroup distribution (#18826) by Prashant Kumar · 4 months ago
  51. e179a6e [LLVMCPU] Migrate to TileRootAndFuseProducerConsumer pipeline (#19163) by Prashant Kumar · 4 months ago
  52. 17fde4d [RVV] Optimize Generic RVV Matmul codegen (#18986) by Bruce Lai · 4 months ago
  53. 205af92 [Global Opt] Turn on transpose propagation by default (#19253) by Ian Wood · 4 months ago
  54. 1f9bf3a [Codegen][NFC] Move encoding related containers to Dialect/Codegen/Utils (#19234) by Han-Chung Wang · 4 months ago
  55. c49303b [compiler] Restructure unittests for iree/compiler. (#19237) by Han-Chung Wang · 4 months ago
  56. 16e51af [Encoding] Introduce "layouts" field to EncodingAttr. (#19215) by Han-Chung Wang · 4 months ago
  57. 4ee5d19 Add iree_codegen and iree_gpu dialects to Python readthedocs. (#19255) by Scott Todd · 4 months ago
  58. 4f4881e [LLVMGPU] add unit test for GPU shared memory reuse (#19204) by Manupa Karunaratne · 4 months ago
  59. 099ffd5 Fix util.assume.int ignoring possible zeroe values sometimes (#19252) by Krzysztof Drewniak · 4 months ago
  60. 16a22e2 [Encoding] Introduce EncodingLayoutAttrInterface. (#19216) by Han-Chung Wang · 4 months ago
  61. b9d73cf Add iree.build to readthedocs, fix a few warnings, refresh readme. (#19236) by Scott Todd · 4 months ago
  62. 81ca183 [Codegen] Harden yielding logic in TileDispatchUsingForall (#19212) by Quinn Dawkins · 4 months ago
  63. dd4c91c Ignore multi-line git trailers in configure_ci.py. (#19244) by Scott Todd · 4 months ago
  64. 204fe98 Delete no longer used build_tools/github_actions/runner/. (#19242) by Scott Todd · 4 months ago
  65. 41dcee9 Integrate LLVM at d7d6fb1804415b0f3e7f1cc9290bfb3d711cb707 (#19245) by Kunwar Grover · 4 months ago
  66. d704051 Port existing ROCM ukernels from HIP to C. (#19194) by Benoit Jacob · 4 months ago
  67. 6583762 [Codegen] Remove depreciated vector distribution transform codegen path (#19233) by Kunwar Grover · 4 months ago
  68. e1ce3fa [tuner]: add c/python binding for querying mma intrinsic (#19218) by Bangtian Liu · 4 months ago
  69. 1654ce6 Bump iree-test-suites commit used for testing onnx ops. (#19229) by Scott Todd · 4 months ago
  70. b5b8059 [LLVMGPUVectorDistribute] Fix vector step distribute (#19227) by Manupa Karunaratne · 4 months ago
  71. 1aada43 fix(TensorSliceOp::fold): ignore DenseResourceElementsAttr (#19182) by Christopher McGirr · 4 months ago
  72. 901db6e [i1] Do not emit `arith.trunci` cast from i1 to i1 (#19176) by lialan · 4 months ago
  73. 8fd3e0d Add arith-expand pass to lower ceildiv, floordiv ops (#19200) by harsh-nod · 4 months ago
  74. 26ef79a [Util] Fix AssumeIntOp::inferResultRanges bug (#19195) by James Bartlett · 4 months ago
  75. 47432c6 [Codegen] Add pass to verify workgroup distribution (#19186) by Quinn Dawkins · 4 months ago
  76. 35b495b Use `iree-import-onnx --opset-version N` in ImportOnnxAction. (#19210) by Scott Todd · 4 months ago
  77. cd4aa72 [runtime][python] Fix device array deepcopy when not mappable (#19213) by Boian Petkantchin · 4 months ago
  78. 82a89e3 Improving linking support for ROCM and ukernels. (#19211) by Ben Vanik · 4 months ago
  79. f510664 Adding `HoistExecutableObjectsPass`. by Ben Vanik · 4 months ago
  80. 89feab6 Allowing #hal.executable.object data to be any serializable attr. by Ben Vanik · 4 months ago
  81. 4396bf1 [Codegen] Clean up MaterializeUserConfigs. NFC. (#19207) by Jakub Kuderski · 4 months ago
  82. 23c32c6 Use `gfx942`, not `gfx940` for MI300. (#19206) by Benoit Jacob · 4 months ago
  83. c0619db Replace unmaintained `create-release` action (#19205) by Marius Brehler · 4 months ago
  84. bc9cbaa Fix compiler errors in CUDA PJRT plugin (#19203) by Twice · 4 months ago
  85. 495adc6 [tuner] two new utility functions which are more friendly for c binding (#19199) by Bangtian Liu · 4 months ago
  86. 45df99d Add linkBitcodeObjects to ROCMTarget. by Ben Vanik · 4 months ago
  87. 5b0740c Adapt `test_ukernel.py` to an API change (#19197) by Benoit Jacob · 4 months ago
  88. b68c535 Check `isIntOrFloat` before querying bitwidth (#19172) by Ian Wood · 4 months ago
  89. 540cebf Reland "[DispatchCreation] Run preprocessing before..." (#18939) by Ian Wood · 4 months ago
  90. 1ab3b49 [Util] Erase state of modified ops (#19187) by Ian Wood · 4 months ago
  91. df83f8e [DispatchCreation] Enable bubble up extract slice for `linalg.generic` op with a single use. (#19174) by MaheshRavishankar · 4 months ago
  92. c581951 Update documentation for release promotion process. (#19191) by Scott Todd · 4 months ago
  93. 50a001f [DispatchCreation] Add CSE before canonicalization of `flow.dispatch.workgroups` (#19178) by MaheshRavishankar · 4 months ago
  94. 957ae60 Modify concat decomposition to only decompose non-outer concats. (#19177) by MaheshRavishankar · 4 months ago
  95. d144f06 Bump version to 3.1.0 after releasing 3.0.0. (#19190) by Scott Todd · 4 months ago
  96. d01432b Turn on blocking of contractions by default (#19171) by MaheshRavishankar · 4 months ago
  97. 3ed07da Document the versioning scheme (#19114) by Marius Brehler · 4 months ago
  98. 480c4f4 Integrate LLVM at 2f925d75dee8b4012d747d889ac4bb1d8a31d5a0 (#19184) by Kunwar Grover · 4 months ago
  99. 29c451b Yet more IREEGPUAttrs cleanup: drop `get{A,B,C}SingleSubgroupLayout` methods (#19169) by Benoit Jacob · 4 months ago
  100. e10342d e2e matmul test improvements (#19016) by Benoit Jacob · 4 months ago