Google Git
Sign in
opensecura / 3p / openxla / iree / 5eebb9168cfd43e57691dde8cf13a037e0df349d
  1. 5eebb91 Removing unused hal.descriptor_set_layout.lookup op. (#16494) by Ben Vanik · 1 year, 2 months ago
  2. 218a5e6 Added support for i4 Const-eval for Tensors (#16321) by Balaji V. Iyer · 1 year, 2 months ago
  3. 23b317d Splitting HAL dialect attrs into HALAttrs.td. (#16490) by Ben Vanik · 1 year, 2 months ago
  4. a7c2ba9 Removing hal.device.targets attr from tests that don't need it. (#16489) by Ben Vanik · 1 year, 2 months ago
  5. 548204b Revert LLVM Patch 3f0404aae7ed2f7138526e1bcd100a60dfe08227. (#16491) by Stella Laurenzo · 1 year, 2 months ago
  6. b42e627 [rocdl] Deduce and plumb MMA schedule in vector distribution (#16482) by Lei Zhang · 1 year, 2 months ago
  7. e4ae2b7 [Codegen][GPU] Fail vector distribution if any live conversion ops remain (#16487) by Quinn Dawkins · 1 year, 2 months ago
  8. cd18fdf Integrate llvm 20240219 (#16483) by Nirvedh Meshram · 1 year, 2 months ago
  9. ee44e3d NFC: Move ContractOpInfo to a new file in Codegen/Utils/ (#16478) by Lei Zhang · 1 year, 2 months ago
  10. 56725c5 [gpu] NFC: Move MMA schedule deduction to Common/GPU/ (#16480) by Lei Zhang · 1 year, 2 months ago
  11. 39108c4 Bump torch-mlir to 135c81a4165f9e4c9070d72c485efece887d64f8. (#16481) by Stella Laurenzo · 1 year, 2 months ago
  12. da98215 [gpu] NFC: Improve MMA layout comments (#16479) by Lei Zhang · 1 year, 2 months ago
  13. d9b1fdc [CPU] remove architecture check for llvm-cpu ordinal passes (#16474) by maxbartel · 1 year, 2 months ago
  14. a3876e3 Bump LLVM to llvm/llvm-project@886294a2fe (#16470) by Quinn Dawkins · 1 year, 2 months ago
  15. 2f41487 [NestedLayout] Add subgroup_basis and thread_basis to layout (#16467) by Kunwar Grover · 1 year, 2 months ago
  16. b5b1dd2 [gpu] NFC: Improve doc for MMA attribute interface (#16468) by Lei Zhang · 1 year, 2 months ago
  17. ab4df60 [hip] Fix CMakeLists duplication and improve variable name (#16465) by Lei Zhang · 1 year, 2 months ago
  18. 0895f11 [Codegen] Add op for setting contraction layouts based on mfma attribute (#16457) by Quinn Dawkins · 1 year, 2 months ago
  19. fea6031 [LLVMGPU] Add flag for maximum shared memory limit (#16463) by Quinn Dawkins · 1 year, 2 months ago
  20. 2d07ad0 [Codegen] Rework global read vector distribution to use new layout (#16420) by Quinn Dawkins · 1 year, 2 months ago
  21. 798f206 [gpu] Drop max vector size limit in warp reduction pipeline (#16462) by Lei Zhang · 1 year, 2 months ago
  22. 4efb908 [rocdl] Add (m,k)x(n,k) variant to contract distribution (#16461) by Lei Zhang · 1 year, 2 months ago
  23. 1a010d8 [rocm][hip] Make shared object init error understandable (#16459) by Lei Zhang · 1 year, 2 months ago
  24. 5b3a0ab [rocm][hip] Name the function for excessive shared memory in error (#16460) by Lei Zhang · 1 year, 2 months ago
  25. f063c5d [rocdl] NFC: Move mfma details to the MFMAAttr impl (#16458) by Lei Zhang · 1 year, 2 months ago
  26. d33bf20 [rocdl] Distribute vector.contract with nested layout (#16445) by Lei Zhang · 1 year, 2 months ago
  27. 2892d81 [LLVMGPU] Add test case for attention lowering to mfma using vector distribution (#16455) by Kunwar Grover · 1 year, 2 months ago
  28. 26d041f [VectorDistributon] Make elementwise distribution match on OpTrait::Elementwise (#16451) by Kunwar Grover · 1 year, 2 months ago
  29. 16b1f2d [HIP] List all current error codes from HIP (#16430) by Nithin Meganathan · 1 year, 2 months ago
  30. 21bfe6d Bump LLVM to llvm/llvm-project@f01ed3bc8884223bf3edbaad8d3685622444cbf5 (#16444) by Max191 · 1 year, 2 months ago
  31. 885d348 [VectorDistribution] Fix layout iteration when VECTORX is frozen (#16447) by Kunwar Grover · 1 year, 2 months ago
  32. 8fc4cd4 [HIP] Replace hipLaunchKernel API with module call (#16448) by Nithin Meganathan · 1 year, 2 months ago
  33. 6560f86 [Codegen][LLVMGPU] Fixes for chained matmul pass (#16442) by Kunwar Grover · 1 year, 2 months ago
  34. 567a449 Only run benchmark workflows when requested. (#16439) by Scott Todd · 1 year, 2 months ago
  35. 0c540db Revert "Turn on SLPVectorizer for ROCM backend (#16412)" (#16417) by harsh-nod · 1 year, 2 months ago
  36. 7ba952c Register LinalgExt dialect in the torch pipeline (#16437) by Lei Zhang · 1 year, 2 months ago
  37. 6d293af Retrying try-lock in synchronization_test to avoid arm64 flakes. (#16436) by Ben Vanik · 1 year, 2 months ago
  38. 5b477a9 Enable several excluded tests in test_riscv.sh (#16434) by Bruce Lai · 1 year, 2 months ago
  39. 1ae8e95 Disable attention decomposition. (#16433) by MaheshRavishankar · 1 year, 2 months ago
  40. a519d21 Fix A100 transform dialect tests (#16432) by Quinn Dawkins · 1 year, 2 months ago
  41. b9fdcce [Codegen] Re-Enable transform dialect configuration strategy round 2 (#16427) by Quinn Dawkins · 1 year, 2 months ago
  42. 045bca1 Convert func->util as part of input conversion. (#16411) by Ben Vanik · 1 year, 2 months ago
  43. 1ee6007 Adding util transform dialect ops that support util.func. (#16426) by Ben Vanik · 1 year, 2 months ago
  44. a86304a Fixing bug in IPO argument uniformity check. (#16425) by Ben Vanik · 1 year, 2 months ago
  45. 4463f8d [python] Enable building of 3.12 wheels on Linux. (#16424) by Stella Laurenzo · 1 year, 2 months ago
  46. bcfe942 Bump torch-mlir to llvm/torch-mlir@e7a0944 (#16416) by Ean Garvey · 1 year, 2 months ago
  47. 0be6423 Quality of life improvements for experimental/regression_suite. (#16415) by Scott Todd · 1 year, 2 months ago
  48. a2ea8b9 [VectorDistribution] Infer operand transpose for vector.contract distribution (#16414) by Kunwar Grover · 1 year, 2 months ago
  49. 0c61f77 [Codegen] Add transfer_write distribution pattern for nested layouts (#16402) by Quinn Dawkins · 1 year, 2 months ago
  50. 1f3e907 ukernels: update README.md (#16358) by Benoit Jacob · 1 year, 2 months ago
  51. d1e1d05 [python] Add a couple more async APIs. (#16419) by Stella Laurenzo · 1 year, 2 months ago
  52. 00aa173 [hip] Add missing source locations and fix parsing (#16418) by Lei Zhang · 1 year, 2 months ago
  53. d32609e Add s8s4s32 ukernel for ARM (#16259) by mariecwhite · 1 year, 2 months ago
  54. 67eec4f [VectorDistribution] Add pattern to distribute layout resolutions (#16379) by harsh-nod · 1 year, 2 months ago
  55. c1d608f Add host cpu tests for regression_suite/.../ukernel. (#16413) by Scott Todd · 1 year, 2 months ago
  56. c066ceb Turn on SLPVectorizer for ROCM backend (#16412) by harsh-nod · 1 year, 2 months ago
  57. 21566f6 [CPU][ArmSME] Add convert-arith-to-arm-sme to the SME pipeline (#16409) by Benjamin Maxwell · 1 year, 2 months ago
  58. 3206e20 Add AMDGPU pattern for chained matmuls (#16398) by harsh-nod · 1 year, 2 months ago
  59. e83ce9e [Codegen] Add transfer read distribution pattern for nested layout (#16393) by Quinn Dawkins · 1 year, 2 months ago
  60. c02b89e [cuda][hip] Guard against NULL cleanup callbacks (#16403) by Lei Zhang · 1 year, 2 months ago
  61. 7c2ec73 Fix a bug in the fastpath of iree_hal_task_semaphore_multi_wait which was doing a spurious wait. (#16404) by Stella Laurenzo · 1 year, 2 months ago
  62. 1acfbf3 [CodeGen] Drop ad-hoc patterns for pack/unapck decomposition. (#16213) by Han-Chung Wang · 1 year, 2 months ago
  63. 60ac333 [python] Add a HalDeviceLoop class for routing runtime events to futures. (#16385) by Stella Laurenzo · 1 year, 2 months ago
  64. c8b6dc1 [hip] Initialize the executable resource after allocation (#16397) by Lei Zhang · 1 year, 2 months ago
  65. d36e8f3 [hip] Mark graph update/copy buffer as unimplmented (#16395) by Lei Zhang · 1 year, 2 months ago
  66. 7b12493 Enable MLP plugin only for x86_64 builds. (#16392) by MaheshRavishankar · 1 year, 2 months ago
  67. 98b30f9 [VectorDistribution] Add distribution for broadcast (1D->2D only) (#16332) by Kunwar Grover · 1 year, 2 months ago
  68. 91ee20f [rocdl] Create basic code structure for ROCDL CodeGen (#16342) by Lei Zhang · 1 year, 2 months ago
  69. c70bf22 [HAL] Remove pool assert during allocator creation (#16388) by Nithin Meganathan · 1 year, 2 months ago
  70. 297560c [CPU] Propagate scalable flags for compute Ops (#16350) by Andrzej Warzyński · 1 year, 2 months ago
  71. 2f20165 [ROCM] Create hasco image as string as expected by the schema (#16384) by Nithin Meganathan · 1 year, 2 months ago
  72. 583cd6f Add sample to match subgraph and call implementation in system plugin. (#16356) by MaheshRavishankar · 1 year, 2 months ago
  73. 7fdb581 [HIP] Enable HAL CTS (#16380) by Nithin Meganathan · 1 year, 2 months ago
  74. ebcd016 [HIP] Enable semaphores in HIP device (#16349) by Nithin Meganathan · 1 year, 2 months ago
  75. c121b86 Add documentation guide for parameters. (#16382) by Scott Todd · 1 year, 2 months ago
  76. 246edee Fix stream sink op folder with users captured in nested regions (#16363) by Jerry Wu · 1 year, 2 months ago
  77. 14927d1 Replacing the ancient vm_util with function_io/function_util. (#16351) by Ben Vanik · 1 year, 2 months ago
  78. 9722440 [Codegen] Implement getDistributedShape for NestedLayout (#16377) by Kunwar Grover · 1 year, 2 months ago
  79. 9aabcb3 Add conversions for FP8 types (F8E5M2 and F8E4M3) (#16374) by Benoit Jacob · 1 year, 2 months ago
  80. 4a49e37 [VectorExt] Add LayoutV2 supporting warp distribution and rank > 2 (#16368) by Kunwar Grover · 1 year, 2 months ago
  81. 6a5ddad Add a pass for generating splat archives during compilation (#16353) by Quinn Dawkins · 1 year, 2 months ago
  82. 30901f5 Replacing the ancient vm_util with function_io/function_util. by Ben Vanik · 1 year, 2 months ago
  83. 49f8a61 Adding iree_io_vec_stream_t. by Ben Vanik · 1 year, 2 months ago
  84. 29a7462 Adding iree_io_stdio_stream_t. by Ben Vanik · 1 year, 2 months ago
  85. 0a2483a Splitting iree_io_memory_stream_t from iree/io/stream.h. by Ben Vanik · 1 year, 2 months ago
  86. 621c186 Add support for scalarizing Exp2Op (#16352) by harsh-nod · 1 year, 2 months ago
  87. 9234f42 Add a number of runtime python bindings and refine the HalFence.wait() behavior. (#16371) by Stella Laurenzo · 1 year, 2 months ago
  88. d19a9d1 Bump LLVM to llvm/llvm-project@351f94d981f363909ae6e76ed57cd0a75c3f5688 (#16367) by Rob Suderman · 1 year, 2 months ago
  89. fc6612f [spirv] Add explicit layout to the top-level buffer (#16370) by Lei Zhang · 1 year, 2 months ago
  90. 87bf971 Fixing implicit casting that caused 4GB fill/copy limits in local-task. (#16364) by Ben Vanik · 1 year, 2 months ago
  91. 5620afd [compiler] Fix a bug in DenseMapInfo specialization for SmallVector (#16360) by Boian Petkantchin · 1 year, 2 months ago
  92. 2a46995 ignore .orig and .rej files (#16359) by Benoit Jacob · 1 year, 2 months ago
  93. 831d240 [Codegen][ROCM] Add a codegen pipeline for supported MFMA variants (#16258) by Quinn Dawkins · 1 year, 2 months ago
  94. 9517472 Switch CI to install TF instead of using 'frontends' Docker images. (#16346) by Scott Todd · 1 year, 2 months ago
  95. 259fe7e [CPU][SME] Add an experimental flag to disable SME tiling (#16211) by Andrzej Warzyński · 1 year, 2 months ago
  96. 3e29cc4 [VectorDistribution] Add distribution for vector.transpose (#16347) by Kunwar Grover · 1 year, 2 months ago
  97. 8c2a3a9 [Util] Add HoistableOpInterface to prevent hoisting metadata ops (#15714) by Quinn Dawkins · 1 year, 2 months ago
  98. 8c4c3e0 [Util] Disable consteval for globals without serializable initial values (#16269) by Quinn Dawkins · 1 year, 2 months ago
  99. 5a0ea36 Drop build-dir outputs from build_all CI job. (#16333) by Scott Todd · 1 year, 2 months ago
  100. 4ef579f [CPU] Move pipeline tests for SSVE (#16312) by Andrzej Warzyński · 1 year, 2 months ago