Google Git
Sign in
opensecura / 3p / openxla / iree / dad3f33757fdd8ca40984700a0e8e9b9abe1dc4e
  1. dad3f33 [cuda] Enable various HAL CTS and e2e single-op tests (#14327) by Lei Zhang · 1 year, 9 months ago
  2. 69a5481 [cuda] Port over existing graph command buffer impl (#14326) by Lei Zhang · 1 year, 9 months ago
  3. 9ff5234 Removing dead VM serialization rodata encoding. (#14368) by Ben Vanik · 1 year, 9 months ago
  4. 1d5e20a Assert when `createTargetMachine` fails (#13990) by bjacob · 1 year, 9 months ago
  5. 62a7f35 Make IREE_COMPILER_BUILTIN_PLUGIN_PATHS extensible by super-projects. (#14356) by Stella Laurenzo · 1 year, 9 months ago
  6. 0061355 Change LinalgExt::EncodingAttr from enum to structured. (#14336) by bjacob · 1 year, 9 months ago
  7. 4086bd6 Integrate llvm-project at llvm/llvm-project@dbaa5838c13e (#14351) by Jakub Kuderski · 1 year, 9 months ago
  8. 0634080 Remove myself from CODEOWNERS (#14366) by Geoffrey Martin-Noble · 1 year, 9 months ago
  9. c890923 Update scripting and README to enable canarying with single-instance a100 groups (#14361) by Geoffrey Martin-Noble · 1 year, 9 months ago
  10. 8ae0f52 Reland "Implement CI job optionality (#14312)" (#14362) by Geoffrey Martin-Noble · 1 year, 9 months ago
  11. 3df82af Add ctypes based Python API for compiler embedding C API. (#14360) by Stella Laurenzo · 1 year, 9 months ago
  12. 8d631dd Makes --iree-input-type an open namespace and adds a plugin extension for it. (#14358) by Stella Laurenzo · 1 year, 9 months ago
  13. 05cec80 Fix concurrency control conflicts with workflow name (#14355) by Jerry Wu · 1 year, 9 months ago
  14. faa0f69 Make the MLIRInterop.h APIs more ergonomic. (#14359) by Stella Laurenzo · 1 year, 9 months ago
  15. 36a8d57 Update contributor tips (#14331) by Geoffrey Martin-Noble · 1 year, 9 months ago
  16. aae14f2 Use `complex.cast` instead of manual bitshifting manipulations. (#14328) by Rob Suderman · 1 year, 9 months ago
  17. 2f4d5ac Update GitHub Actions Runner to 2.306.0 (#14352) by Geoffrey Martin-Noble · 1 year, 9 months ago
  18. 04beef2 [cuda] Port over existing semaphore impl (#14325) by Lei Zhang · 1 year, 9 months ago
  19. d01a83c Make ukernel code inlinable down to arch-specific function pointer selection. (#14283) by bjacob · 1 year, 9 months ago
  20. 80b694f Add support for uint-type input for chlo.topk->linalg_ext lowering (#14329) by NatashaKnk · 1 year, 9 months ago
  21. 2888d40 Add explicit homepage to website extra section. (#14350) by Scott Todd · 1 year, 9 months ago
  22. fc521f9 Improve buffer handling in WebGPU sample. (#14163) by Scott Todd · 1 year, 9 months ago
  23. 0994923 [Stream] Add tests for optimization barrier legality (#14315) by Eugene Zhulenev · 1 year, 9 months ago
  24. 6867577 Add a "IREE developer tips and tricks" guide. (#14254) by Scott Todd · 1 year, 9 months ago
  25. 69eb9ca Remove the ukernels standalone plugin (#14339) by bjacob · 1 year, 9 months ago
  26. ac34d7b [NFC] IREEInput/Util: Simplify loops with llvm range helpers (#14334) by Eugene Zhulenev · 1 year, 9 months ago
  27. 095643b Integrate llvm-project at 7a749fe94bb7 (#14341) by Han-Chung Wang · 1 year, 9 months ago
  28. 5d96935 Fix warnings that `${arch}-unknown-unknown-eabi-elf` was not a correct triple (#14340) by bjacob · 1 year, 9 months ago
  29. 68350cb Revert "Implement CI job optionality" (#14344) by Scott Todd · 1 year, 9 months ago
  30. 82cfc9d Remove `configure_ci.py` from `post_benchmark_comment.yaml` (#14343) by Jerry Wu · 1 year, 9 months ago
  31. 1ca7e79 Use name instead of ID for benchmark artifacts and targets (#14219) by Jerry Wu · 1 year, 9 months ago
  32. 55b4d17 Integrate llvm-project at d6e9efab8 (#14304) by Han-Chung Wang · 1 year, 9 months ago
  33. 3a8e511 Add missing concurrency control in workflows (#14335) by Jerry Wu · 1 year, 9 months ago
  34. edf18a5 Implement a timeout for benchmarking through python bindings. (#14261) by Kojo Acquah · 1 year, 9 months ago
  35. 09f54d8 Implement CI job optionality (#14312) by Geoffrey Martin-Noble · 1 year, 9 months ago
  36. 89919da Reserve extra scratch registers for >4byte remappings. (#14332) by Stella Laurenzo · 1 year, 9 months ago
  37. 7c9bb50 Start work on a new incremental LLVM integrate script. (#14318) by Stella Laurenzo · 1 year, 9 months ago
  38. 08f969a LinalgExt: remove EncodingAttr, redundant with TensorEncodingAttr (#14323) by bjacob · 1 year, 9 months ago
  39. 88c67f4 Incrementally integrate LLVM to 9dc88651d591f62ddd7f54b98e3c9a8cb81d8bd5 (24 of 88 patches). (#14317) by Stella Laurenzo · 1 year, 9 months ago
  40. 0be5971 [Flow] NFC: Remove redundant tied_operands attribte from tensor.update op (#14322) by Eugene Zhulenev · 1 year, 9 months ago
  41. 3cee690 [IREEInput] Add executable source and dispatch operations (#14290) by Eugene Zhulenev · 1 year, 9 months ago
  42. 0b1cacd [IREEInput] Add TiedOpInterface and optimization barrier op (#14289) by Eugene Zhulenev · 1 year, 9 months ago
  43. c1ec61d [IREEInput] Add support for buffers and constructing buffer views (#14278) by Eugene Zhulenev · 1 year, 9 months ago
  44. 4939b9a [tf] Switch off of pywrap entry point (#14303) by Jacques Pienaar · 1 year, 9 months ago
  45. ccf886b [HAL] Allow iree_hal_buffer_view_shape to accept NULL out_shape (#14298) by Boian Petkantchin · 1 year, 9 months ago
  46. aa7284b [Stream] Add missing dynamic legality for util.optimization_barrier (#14296) by Eugene Zhulenev · 1 year, 10 months ago
  47. 46d94c3 [Flow] Add a pass to fold away values of tensor type with zero extents (#14308) by Rob Suderman · 1 year, 10 months ago
  48. c1e14b6 Fix CUDA bitcode builds on Windows. (#14306) by Scott Todd · 1 year, 10 months ago
  49. 23748f6 Add `iree-dump-module` to the python iree-runtime wheel. (#14243) by Scott Todd · 1 year, 10 months ago
  50. be3a6c9 Bump TF nightly to 2023-07-05 (#14300) by Jacques Pienaar · 1 year, 10 months ago
  51. 3a64294 Extend TD strategy to support batched matmul (#14292) by Oleksandr "Alex" Zinenko · 1 year, 10 months ago
  52. 6de4a73 Make barrier elimination more aggressive (#14293) by Oleksandr "Alex" Zinenko · 1 year, 10 months ago
  53. 566ed4d Fix mmperf and sharktank to use A100 runner (#14286) by Jerry Wu · 1 year, 10 months ago
  54. d9674d8 Tag `e2e_matmul_direct_f16_gpu_large_unaligned` as requiring sm80 (#14266) by Geoffrey Martin-Noble · 1 year, 10 months ago
  55. fe87604 [metal] NFC: Simplify file names by dropping `metal_` prefix (#14270) by Lei Zhang · 1 year, 10 months ago
  56. 88d6b69 Proper error-handling in ukernel bitcode loading. (#13917) by bjacob · 1 year, 10 months ago
  57. a37c817 ARM: detect more CPU features (#14253) by bjacob · 1 year, 10 months ago
  58. dd3d69a Generate build targets for benchmark presets (#14204) by Jerry Wu · 1 year, 10 months ago
  59. 9ee339f Integrate llvm/llvm-project@989879f8fded (#14271) by Lei Zhang · 1 year, 10 months ago
  60. 635245c Make HoistRedundantVectorTransfers be an individual pass. (#14244) by Han-Chung Wang · 1 year, 10 months ago
  61. 542db78 No need to return module generation configs in benchmark generators (#14205) by Jerry Wu · 1 year, 10 months ago
  62. a58d86e Integrate llvm/llvm-project@0e9384a6c6ca (#14231) by Lei Zhang · 1 year, 10 months ago
  63. 465492e Separate GPU test jobs into general and Ampere-specific (#14251) by Geoffrey Martin-Noble · 1 year, 10 months ago
  64. 7b28a41 Add missing cmake dependency for iree-tblgen (#14235) by Oleksandr "Alex" Zinenko · 1 year, 10 months ago
  65. 0b21a6c Add validators for module generation and run configs (#14234) by Jerry Wu · 1 year, 10 months ago
  66. 7991dc5 Do not rematerialize scalar-like ops. (#14259) by MaheshRavishankar · 1 year, 10 months ago
  67. e414c0a Add `OpDocGroup`s to MLIR tablegen files. (#14194) by Scott Todd · 1 year, 10 months ago
  68. 2f2d28c NFC: Rename `LoweringConfig.cpp/.td/.h` -> `IREECodegenAtts.cpp/.td/.h` (#14256) by MaheshRavishankar · 1 year, 10 months ago
  69. ee53836 Fix clone producers for use in count region (#14250) by Rob Suderman · 1 year, 10 months ago
  70. 19bd0c4 Plumb i64-to-i32 flag down AutoInputConversionPipeline (#14236) by Rob Suderman · 1 year, 10 months ago
  71. 1f6dba0 Add type propagation for illegal types for linalgExt sort (#14225) by NatashaKnk · 1 year, 10 months ago
  72. 4566e65 Update GPU VM image to one built using a T4 (#14176) by Geoffrey Martin-Noble · 1 year, 10 months ago
  73. 444eb7c Add missing BUILD.bazel file for Cuda target test (#14247) by Geoffrey Martin-Noble · 1 year, 10 months ago
  74. af95696 Add folding arith extension patterns to vectorization post processing. (#14229) by Han-Chung Wang · 1 year, 10 months ago
  75. c647794 [TransformStrategies] NFC: Harden matmul strategy defaults (#14222) by Quinn Dawkins · 1 year, 10 months ago
  76. 99b81bf [NFC] Simplify BufferViewBufferOp folder (#14242) by Eugene Zhulenev · 1 year, 10 months ago
  77. b96be3e [NFC] Move LLVMCPUVectorization pass to common GenericVectorization pass (#14228) by Han-Chung Wang · 1 year, 10 months ago
  78. 5d97d86 Lower float16 and bfloat16 matmuls to ukernels. (#14241) by bjacob · 1 year, 10 months ago
  79. fbbd1ee Ukernels: basic support for float16 and bfloat16. (#14239) by bjacob · 1 year, 10 months ago
  80. a67b550 [HAL] Fix a bug in buffer_view.buffer folder (#14232) by Eugene Zhulenev · 1 year, 10 months ago
  81. 2c608e2 Add bfloat16 conversion helpers (#14238) by bjacob · 1 year, 10 months ago
  82. 37c79f0 Add support for lowering ops that implement the `UKernelOpInterface` on the CUDA path. (#14101) by MaheshRavishankar · 1 year, 10 months ago
  83. fc0dd6b NFC: Split `Passes.td` in `Codegen` into several `Passes.td` in individual codegen folders (#14230) by MaheshRavishankar · 1 year, 10 months ago
  84. 52b967c data-tiling for `f16` and `bf16` matmuls (#14207) by bjacob · 1 year, 10 months ago
  85. 2ed97ab Activate python venv properly on mac/arm. by Stella Laurenzo · 1 year, 10 months ago
  86. acf0b27 Fix the MacOS FindPython build issue. (#14233) by Stella Laurenzo · 1 year, 10 months ago
  87. abe91fa Port iree.runtime to nanobind. (#14214) by Stella Laurenzo · 1 year, 10 months ago
  88. 6eb7ce5 List target backends registered by plugins in C API. (#14030) by Scott Todd · 1 year, 10 months ago
  89. 59d0988 Add `vector.fma` to the list of bf16 arith operations (#14226) by Rob Suderman · 1 year, 10 months ago
  90. 154648c Remove INTERFACE copts/linkopts from external_cc_library header libraries. (#14216) by Stella Laurenzo · 1 year, 10 months ago
  91. 798bc7a Add support for mixed precision fma and peel epilogue to matmul strategy (#14218) by Nicolas Vasilache · 1 year, 10 months ago
  92. 8bd48d9 Add nanobind to build requirements. (#14217) by Stella Laurenzo · 1 year, 10 months ago
  93. 2b7d51e Integrate llvm-project at d179421099314431a91b85c01977ba0086ffd6db (#14188) by Kojo Acquah · 1 year, 10 months ago
  94. 3898dc6 Ignore deleted files in python format checks (#14210) by Jerry Wu · 1 year, 10 months ago
  95. 5c86921 Add compiler code reformatting to `.git-blame-ignore-revs` (#14212) by Jakub Kuderski · 1 year, 10 months ago
  96. 3b652d4 Switch compiler to LLVM/MLIR formatting style (#14181) by Jakub Kuderski · 1 year, 10 months ago
  97. 1799e24 Add iree-cpuinfo to the python iree-runtime wheel. (#14209) by Stella Laurenzo · 1 year, 10 months ago
  98. c2e602d Add support for tm_tensor.attention (#13777) by gpetters94 · 1 year, 10 months ago
  99. 6200ade NFC - Refactor Matmul and GemmLike strategies in preparation for gene… (#14201) by Nicolas Vasilache · 1 year, 10 months ago
  100. 1dbd0ba Relax the Matmul transform strategy to allow using fmas for smaller cases. (#14138) by Nicolas Vasilache · 1 year, 10 months ago