Google Git
Sign in
opensecura / 3p / openxla / iree / 0e16a89f7dbb89cc550254b0336abbea8b8c8f4b
  1. 0e16a89 [Codegen][GPU] Disable consumer fusion for multi use cases (#18723) by Quinn Dawkins · 6 months ago
  2. 0f28d44 Use upstream dataflow tooling to build an arithmetic opt pass. (#18702) by Stella Laurenzo · 6 months ago
  3. 0889d13 Add the support to yield multiple results (#18717) by Prashant Kumar · 6 months ago
  4. 7fb28e0 [Codegen][GPU] Fix delinearized index order in forall resolution (#18724) by Quinn Dawkins · 6 months ago
  5. 4636257 [Encoding][NFC] Moving Encoding attr/enum to Encoding[Types|Attrs].* (#18711) by Han-Chung Wang · 6 months ago
  6. e8ff07e [Codegen][GPU] Stop using redundant transfer hoisting pattern on memrefs (#18721) by Quinn Dawkins · 6 months ago
  7. 6c095ed Revert "Revert "[CPU] Enable tileDispatchUsingForall for mmt4d and co… (#18718) by Prashant Kumar · 6 months ago
  8. 8f3f1e2 [docs] Remove call to `t()` in external param example. (#18706) by Vinayak Dev · 6 months ago
  9. e8ab5f8 Integrate LLVM at 634c57d7 by Alan Li · 6 months ago
  10. f6a9b6b [Codegen][GPU] Enable destination fusion for unit trip loops (#18674) by Quinn Dawkins · 6 months ago
  11. ad68964 [LLVMGPU] Pad to intrinsic shape in LLVMGPUPadAndVectorDistribute pipeline (#18632) by Kunwar Grover · 6 months ago
  12. 6001f9c Fix distribution logic when number of parallel loops is greater than 3 (#18714) by MaheshRavishankar · 6 months ago
  13. 5b0680d [Codegen] Add option to disable copy vectorization (#18673) by Quinn Dawkins · 6 months ago
  14. cc3b28f [Codegen][GPU] Improve loop fusion pattern verification (#18671) by Quinn Dawkins · 6 months ago
  15. 88cb0ab Add @bjacob and myself to Encoding dialect owners. (#18712) by Han-Chung Wang · 6 months ago
  16. 62f8d7e Revert "[CPU] Enable tileDispatchUsingForall for mmt4d and convolution pipelines. " (#18707) by Han-Chung Wang · 6 months ago
  17. 8c9f2cb Integrate with LLVM 20241007 by Alan Li · 6 months ago
  18. 691aa4f Bump llvm/torch-mlir@e9ed4af9ced23c201 (#18699) by Rob Suderman · 6 months ago
  19. 23b63cd [GPU][DT] Add e2e matmul tests for GPU data tiling (#18627) by Max191 · 6 months ago
  20. 65158ac Rework util.assume.* ops to util.assume.int and base on attributes. (#18703) by Stella Laurenzo · 6 months ago
  21. caacf6c Honor narrow dims in GPUMaterializeEncoding (#18622) by Benoit Jacob · 6 months ago
  22. bb5f2f5 [CPU] Enable tileDispatchUsingForall for mmt4d and convolution pipelines. (#18618) by Prashant Kumar · 7 months ago
  23. 126e334 [CPU][NFC] Collapsing methods that query a config is enabled. (#18686) by Han-Chung Wang · 7 months ago
  24. 4710c98 Integrate LLVM at 208f42fd (#18696) by Benoit Jacob · 7 months ago
  25. b89ba05 [CPU] Switching to linalg::LinalgOp for MaterializeContractionOp pattern (#18690) by Han-Chung Wang · 7 months ago
  26. 3801a5d [GPU][DT] Add support for materializing gemm with batch dimensions. (#18693) by Han-Chung Wang · 7 months ago
  27. 58dac26 [Encoding] Introduce getElementTypesArray helper in EncodingAttr. (#18692) by Han-Chung Wang · 7 months ago
  28. f7a02a0 [DT] Use createOrFold to simplify the logic of creating tensor.cast op. (#18691) by Han-Chung Wang · 7 months ago
  29. 067ba0e [GPU][NFC] Updates comments/style/TODO/debug_message for GPU data-tiling (#18688) by Han-Chung Wang · 7 months ago
  30. 79e979f Legalize newly added compiler hints ops. (#18689) by Stella Laurenzo · 7 months ago
  31. a9f5628 Limit transposition of narrow-N to only CPUMaterializeEncoding (#18684) by Benoit Jacob · 7 months ago
  32. c7a9af7 Integrate Stablehlo at d40285e (#18685) by Benoit Jacob · 7 months ago
  33. f39884d Cherry-pick stablehlo build fix for MSVC. (#18683) by Scott Todd · 7 months ago
  34. 747081a [Codegen][GPU] Force linalg ops to always use the same vector size (#18654) by Quinn Dawkins · 7 months ago
  35. 0e8a573 Adding vm.cast.f32.si64 and vm.cast.f32.ui64 ops (#18642) by Nirvedh Meshram · 7 months ago
  36. a6043e2 Adding a null HAL driver. (#18675) by Ben Vanik · 7 months ago
  37. 0bbc432 [VectorDistribution]Add distribution pattern and test mlir file for vector.gather (#18660) by Bangtian Liu · 7 months ago
  38. 88153eb [Codegen][GPU] Fuse into destinations for parallel tiling (#18666) by Quinn Dawkins · 7 months ago
  39. 24ee841 [Codegen][GPU] Fix alloc creation for dynamic outputs in loop fusion (#18665) by Quinn Dawkins · 7 months ago
  40. 42ca044 Integrate LLVM at e8137503 (#18678) by Benoit Jacob · 7 months ago
  41. 718b4fd [docs][pytorch] Add examples for compiling with external weights. (#18658) by Vinayak Dev · 7 months ago
  42. 206c1f2 [Codegen] Allow vectorizing linalg.copy ops on memrefs (#18672) by Quinn Dawkins · 7 months ago
  43. 903ab0a Integrate LLVM at 9fa55ec3 (#18670) by Benoit Jacob · 7 months ago
  44. cd48b10 [NFC] Delete dead ops after cloning (#18669) by Ian Wood · 7 months ago
  45. 7a2705d Bump stablehlo to `f7f8e4e35` and drop LLVM local reverts (#18668) by Benoit Jacob · 7 months ago
  46. d341128 [ExternalInterfaces] Make fill non-hoistableLeafOp, hoist linalg init operands (#18634) by Max191 · 7 months ago
  47. 66c3397 [docs] Update Python API docs (#18662) by Marius Brehler · 7 months ago
  48. 916bb88 Stopped threads from holding a reference to themselves. (#18636) by Andrew Woloszyn · 7 months ago
  49. 84ac47b [LLVMGPU] Switch LLVMGPUVectorDistribute to use iree_gpu.lowering_config (#18651) by Kunwar Grover · 7 months ago
  50. 462ecb6 [torch] Materialize all derivable bounds and divisor information in the IR. (#18646) by Stella Laurenzo · 7 months ago
  51. 8de9856 [LinalgExt] Add Interfaces for implementing fusion support for `iree_linalg_ext.custom_op`. (#18647) by MaheshRavishankar · 7 months ago
  52. 451ef71 [Codegen] Add pass for unrolling annotated for loops (#18641) by Quinn Dawkins · 7 months ago
  53. 9c39a29 [Codegen][GPU] Fix forall hositing arg use in single trip loops (#18657) by Nirvedh Meshram · 7 months ago
  54. c86b621 Switch build_package to arm-hosted runner. (#18656) by Scott Todd · 7 months ago
  55. 0a71ea5 [Codegen][GPU] Add iree_gpu.multi_mma op to PartitionableLoopsInterface (#18653) by Max191 · 7 months ago
  56. e45c570 Switch linux_arm64_clang workflow to arm-hosted runner. (#18643) by Scott Todd · 7 months ago
  57. 839f7f6 [GPU] Use shared memory for data tiled multi_mma ops (#18625) by Max191 · 7 months ago
  58. 4d31d89 [LinalgExt] Avoid rank reduction in Im2Col lowering pattern (#18637) by Quinn Dawkins · 7 months ago
  59. 0d65b6e Integrate LLVM at `a86e966a` (#18644) by Benoit Jacob · 7 months ago
  60. a7d84f9 [ROCm] Fix known target info for MI300A (#18648) by Jakub Kuderski · 7 months ago
  61. 20a7638 [ROCm] Always require `--iree-hip-target` (#18645) by Jakub Kuderski · 7 months ago
  62. 0b17c72 Add testing for punet model variations. (#18639) by saienduri · 7 months ago
  63. f87ae4e IREE Custom tilable op (`iree_linalg_ext.custom_op`). (#18555) by MaheshRavishankar · 7 months ago
  64. b0ede80 [LLVMGPU] Add KernelConfig for data tiled multi_mma ops (#18623) by Max191 · 7 months ago
  65. 6c47f63 Update references to nod-ai/SHARK-* repository names. (#18592) by Scott Todd · 7 months ago
  66. 5502ca4 [Codegen][GPU] Fix index delinearized index order (#18640) by Quinn Dawkins · 7 months ago
  67. 35dafee [LLVMGPU] Remove more dead code from prefetching pass (#18638) by Jakub Kuderski · 7 months ago
  68. 12c653b Integrate LLVM at `bfde1783` (#18635) by Benoit Jacob · 7 months ago
  69. f5dc573 [DispatchCreation] CollapseDimensions patch (#18424) by Ian Wood · 7 months ago
  70. a9c7ec1 [Util][GPU] Add TiedOpInterface implementation for iree_gpu.multi_mma (#18626) by Max191 · 7 months ago
  71. b7ac442 [GPU][DT] Fix indexing bug in populateOperandOffsetsSizesStrides (#18624) by Max191 · 7 months ago
  72. 9e09115 Simplifications around narrow dimensions in encodings. (#18607) by Benoit Jacob · 7 months ago
  73. 34641dd Integrate LLVM at llvm/llvm-project@68ddd6c80e917b (#18619) by Han-Chung Wang · 7 months ago
  74. ff1b8b0 [Codegen][GPU] Make operand promotion controlled by lowering config (#18576) by Quinn Dawkins · 7 months ago
  75. 66bf9de [VectorExt] Fix to_layout op (#18621) by Ian Wood · 7 months ago
  76. 2e382a7 [docs] Update examples in the PyTorch+IREE guide (#18620) by Vinayak Dev · 7 months ago
  77. b5b4ab7 Bump cpubuilder dockerfile image to newer multi-arch version. (#18558) by Scott Todd · 7 months ago
  78. 8872710 Revert "Removed the iree_thread_join in the cleanup of deferred_work_queue.c" (#18616) by Andrew Woloszyn · 7 months ago
  79. 14728a7 Bump torch-mlir to 9938abf25e1e7526ca7f43a8c49e9078c14fc55c (#18615) by Vivek Khandelwal · 7 months ago
  80. 76c3e61 [CodeGen] Fix the argument replacements in scf.forall op lowering. (#18613) by Han-Chung Wang · 7 months ago
  81. 66d0c31 [DispatchCreation] Disable batch mmt4d fusion as its not supported by backends (#18611) by Nirvedh Meshram · 7 months ago
  82. 32a44bd [DispatchCreation][NFC] Simplify the logic of dumping CollapseInfo. (#18610) by Han-Chung Wang · 7 months ago
  83. 7db91ce [Codegen][GPU] Change the location of barriers in forall fusion (#18542) by Quinn Dawkins · 7 months ago
  84. c3fa4d0 Fix `task_executor_initialize` in resource exhausted scenario. (#18609) by Stella Laurenzo · 7 months ago
  85. 97896ce Integrate LLVM at llvm/llvm-project@24d707e215a1e2 (#18606) by Han-Chung Wang · 7 months ago
  86. d18064f [COMMON] Select the last compute op that has workgroup tilin… (#18604) by Prashant Kumar · 7 months ago
  87. 5a2dd56 Removed the iree_thread_join in the cleanup of deferred_work_queue.c (#18605) by Andrew Woloszyn · 7 months ago
  88. b13d38b [DT] Collapse matmul_narrow_M/N field into round_dims_to attribute. (#18599) by Han-Chung Wang · 7 months ago
  89. d583958 simplify `DataTiledMMAAttr::buildMmaOperation` (#18597) by Benoit Jacob · 7 months ago
  90. 672ae82 Attach Fusion interface to `linalg.softmax` (#18550) by Ian Wood · 7 months ago
  91. 6634f0f Integrate LLVM at llvm/llvm-project@cebb7c010854e3 (#18596) by Han-Chung Wang · 7 months ago
  92. 0b29f7b [GPU][DT] Add support for GPU data-tiling E2E tests. (#18591) by Han-Chung Wang · 7 months ago
  93. 7290283 Add F16 support for benchmark. (#18580) by erman-gurses · 7 months ago
  94. 3773a48 Lower data-tiled multi_mma to intrinsics. (#18547) by Benoit Jacob · 7 months ago
  95. 129ad45 Fixing cconv printing of function signatures with multiple tuples. (#18595) by Ben Vanik · 7 months ago
  96. 9158a90 GPU data tiling: Refine tile dimensions, more preparation for thread distribution. (#18556) by Benoit Jacob · 7 months ago
  97. b2dd6db [Encoding] Retire original_type field. (#18586) by Han-Chung Wang · 7 months ago
  98. 863ca01 Integrate LLVM at llvm/llvm-project@3fbf6f8bb183ad (#18590) by Han-Chung Wang · 7 months ago
  99. e6cf5bb [GPU][DT] Add support for materializing encoding ops with dynamic shape. (#18585) by Han-Chung Wang · 7 months ago
  100. e19950c Integrate LLVM at llvm/llvm-project@40d6497a97a61e (#18581) by Han-Chung Wang · 7 months ago