Google Git
Sign in
opensecura / 3p / openxla / iree / HEAD
  1. 818e59f Bump to llvm/torch-mlir@3cebce2 (#22902) by zjgarvey · 5 hours ago main
  2. 45017a7 [Codegen] Add PCF bufferization interfaces (#22805) by Quinn Dawkins · 7 hours ago
  3. d8b504f [ROCM][DT] Add architecture matching to ukernel_info attribute (#22899) by Zhewen Yu · 8 hours ago
  4. b361bf7 Bump torch-mlir (#22894) by Rahul Kayaith · 10 hours ago
  5. c54764e [Codegen] Add PCF dialect (#22804) by Quinn Dawkins · 11 hours ago
  6. 5ed9041 Update shark/SHARK to amd-shark/AMD-SHARK in documentation and URLs in IREE (#22883) by Bangtian Liu · 11 hours ago
  7. aba450e Integrates/llvm 20251212 (#22897) by Bangtian Liu · 13 hours ago
  8. 1e45c84 [Stream] Handle AsyncCloneOp in UnifyEncodingForGlobals tracing. (#22895) by Han-Chung Wang · 20 hours ago
  9. bc6c3fa Integrates/llvm 20251211 (#22885) by Bangtian Liu · 2 days ago latest-snapshot
  10. a33b55a [LDS] Improve multiple transfers per lane (#22879) by Alan Li · 2 days ago
  11. d0dd889 Integrates/llvm 20251210 (#22876) by Bangtian Liu · 2 days ago
  12. 248f274 [Codegen] Do not swap extract_slice and collapse_shape for a special case (#22870) by Vivian Zhang · 3 days ago
  13. 1eb6407 [Encoding] Add resolver swizzle verification (#22867) by Jorn Tuyls · 3 days ago
  14. f2156d7 [DT][SVE] adjust tile sizes for mmt4d & disable transposition of narrow-N matmuls (#21701) by Ege Beysel · 3 days ago
  15. 0f64f41 [bindings] Add `iree_tensor_ext` to python bindings (#22872) by Rahul Kayaith · 3 days ago
  16. d2e92fa [DT][GPU] Redefine intrinsics M/N interleaving (#22812) by Zhewen Yu · 3 days ago
  17. 4581198 [Pkgci] Update golden dispatch counts (#22869) by Ian Wood · 3 days ago
  18. 0711973 [Codegen][GPU]Skip prologue pipeline barriers only for non-nested pipelined loops (#22868) by Zhuoran Yin · 3 days ago
  19. 031445e Bump the github-actions group across 1 directory with 3 updates (#22858) by dependabot[bot] · 4 days ago
  20. dd5f28a Integrates/llvm 20251209 (#22864) by Bangtian Liu · 4 days ago
  21. 6ccb336 [libcall] Update musl Makefile to include missing files. (#22859) by Alan Li · 4 days ago
  22. fea540f [Encoding] Add verifier for gpu/cpu/vmvx_encoding_resolver (#22838) by Jorn Tuyls · 4 days ago
  23. 3585436 [Stream] Add UnifyEncodingForGlobals pass. 1/n (#22767) by Han-Chung Wang · 4 days ago
  24. 0c1753c [Codegen] Use workgroup_count_hint for most code paths (#22549) by Quinn Dawkins · 4 days ago
  25. 621a5e9 Integrates/llvm 20251208 (#22856) by Bangtian Liu · 4 days ago
  26. ac28c58 Revert "[Util] Implement InferIntDivisibilityOpInterface for affine o… (#22860) by Ian Wood · 4 days ago
  27. 21684f2 [LDS] Add AMDGPULowerCoalescedDMAToGatherLDS pass for direct global to LDS loads (#22356) by Alan Li · 4 days ago
  28. fd4ff2b [Dispatch Creation] Create more multi-use dispatches (#22011) by Ian Wood · 4 days ago
  29. b44836e [Torch Models] Fix SDXL golden dispatch counts (#22855) by Ian Wood · 4 days ago
  30. 69fc446 Add CDNA3 test filtering to CI (#22848) by Alan Li · 4 days ago
  31. fa24a3a [Util] Implement InferIntDivisibilityOpInterface for affine ops (#22723) by Max191 · 4 days ago
  32. e1694aa [tests][e2e] Add more llama related shapes (#22831) by Muzammiluddin Syed · 5 days ago
  33. 21b6cbb Unify RISC-V toolchain environment variables and remove default path (#22710) by Han-Kuan Chen · 5 days ago
  34. 8f7ab2c [Codegen] Add WorkgroupCountHintOp to defer populating the workgroup count (#22533) by Quinn Dawkins · 5 days ago
  35. e1eba96 [Encoding] Add verifier for iree_encoding.layouts (#22850) by Jorn Tuyls · 5 days ago
  36. c6a044b [Stream] Encode packed_storage device and host tensors (#22722) by Lukas Sommer · 5 days ago
  37. 70b2b45 [Encoding] Improve specialized encoding usage in lit test (#22851) by Jorn Tuyls · 5 days ago
  38. d49d410 [SPIRV][Codegen] Use single subgroup when reduction consumer has non-distributable broadcast (#22832) by Eric Feng · 5 days ago
  39. 8f6b259 Fix deadlock in `ROCMDialect::getMlirUKernels` (#22843) by Benoit Jacob · 5 days ago
  40. 6a28284 [Codegen] Add vector.to/from_elements to bf16 -> i16 conversion (#22846) by Quinn Dawkins · 7 days ago
  41. 09f5095 [Codegen][GPU] Allow channel first layouts to lower through direct convolution path (#22840) by Vivian Zhang · 7 days ago
  42. 70b44fa [e2e][ukernel] Remove dead/duplicate tests (#22834) by Zhewen Yu · 7 days ago
  43. 554753b [Runtime][HIP] Correct O(log n) bound search logic and eliminate O(n) loop(#22733) (#22734) by NohHyeon Kwon · 7 days ago
  44. 3120a77 ElideAsyncCopiesPass refactoring for SCF/transfer support. (#22739) by Ben Vanik · 7 days ago
  45. 7f5aca2 Fix tests: `noubsan` was not being honored, and MXFP4 matmul tests are static-shape-only (#22836) by Benoit Jacob · 8 days ago
  46. 883d466 [Encoding] Use struct directive for TestingAttr assembly format (#22826) by Jorn Tuyls · 8 days ago
  47. 1ccd5d7 Add jtuyls and Yu-Zhewen to CODEOWNERS for ROCM plugin and Encoding (#22810) by Jorn Tuyls · 8 days ago
  48. b1e3812 [Codegen][GPU] Preserve loop domain when collapsing dims in Conv to Matmul conversion (#22821) by Vivian Zhang · 8 days ago
  49. 196b716 Reland "[LLVMGPU] Unroll elementwise operations #21665" (#22828) by Alan Li · 8 days ago
  50. 82fc1ac [Dispatch Creation] Don't fuse if there are no common parallel loops (#22819) by Ian Wood · 8 days ago
  51. e2dc7a5 [LLVMGPU] Update seeds for scaled gemm (#22798) by Muzammiluddin Syed · 8 days ago
  52. 6d742a1 [GlobalOpt] Fix rank-reduced permutation in SinkTransposeThroughExtractSlice (#22754) by Ziliang Zhang · 8 days ago
  53. f7e0280 [Codegen][GPU] Replace prefetch_shared_memory with prefetch_num_stages in IREEGPUAttrs (#22818) by Zhuoran Yin · 8 days ago
  54. cdc5eee [GPU] Fix alignment check for scaled matmul (#22737) by Zhewen Yu · 9 days ago
  55. 68a9309 Add SCF support and fence coverage to ElideTimepointsPass. (#22611) by Ben Vanik · 9 days ago
  56. 4eff28d [Encoding] Remove unneeded command line option (#22816) by Muzammiluddin Syed · 9 days ago
  57. 3e65f15 [GPU] Add M dimension constraints for pingpong ukernel (#22801) by Ian Wood · 9 days ago
  58. 60058ec [LLVMGPU] Fix lowering strategy for direct convolution (#22802) by Vivian Zhang · 9 days ago
  59. 91bf741 Add iree_status_t stack trace support on Linux. (#22796) by Ben Vanik · 9 days ago
  60. a6f8dfe [Codegen][LLVMGPU] Replace TransposeSharedMem pipeline (#21661) by Quinn Dawkins · 10 days ago
  61. 789b515 [HAL] fix IREE_HAL_MAX_QUEUES to be number of bits in queue affinity type (#22702) by Stefan Schuermans · 10 days ago
  62. 4928091 [Codegen] Support dynamic offsets in collapse_shape fusion to interface stores (#22800) by Quinn Dawkins · 10 days ago
  63. 97c9020 Bump llvm-project to @a7c1f467339abd1942c89f2ef8b79083e89e7dad (#22787) by Max191 · 10 days ago
  64. 069c079 [LLVMGPU][Codegen] Reland "Emit packed chain FMA from select multi_reductions and contracts" (#22789) by Eric Feng · 10 days ago
  65. 5160310 [Codegen][GPU] Enable 3-stage pipelining with hipblaslt compute->write->read ordering (#22788) by Zhuoran Yin · 11 days ago
  66. d344073 [CI] Update iree-org/iree-test-suites@132f91e4 (#22784) by Eric Feng · 11 days ago
  67. d2117d7 [Codegen][GPU] Add fusion barrier after result promotion (#21709) by Quinn Dawkins · 11 days ago
  68. 08b6af6 build_tools: fix: ensure that iree-flatcc-cli and iree-c-embed-data are build for the target during cross-compilation (#22755) by Florian Walbroel · 11 days ago
  69. caf2352 [Flow] Annotate scaled matmul dispatches (#22773) by Zhewen Yu · 12 days ago
  70. cdcbfd3 ScheduleExecution enhancements for timeline-aware scheduling and SCF. (#22483) by Ben Vanik · 12 days ago
  71. 4bb0c12 [Bazel] Migrate to bzlmod for LLVM compatibility (#22771) by maxbartel · 2 weeks ago
  72. 6a73711 [tests][e2e] Add custom mxfp4 gemm test to verify shape of interest. (#22775) by Muzammiluddin Syed · 2 weeks ago
  73. 46fbe05 [Codegen][Tuner] Expose the python bindings for LinalgExt::inferScaledContractionDims and LinalgExt::isaScaledContractionOpInterface (#22763) by Muzammiluddin Syed · 2 weeks ago
  74. af241f9 Integrate LLVM @ 356479191ca0 (#22772) by Alan Li · 2 weeks ago
  75. fb8d0cc [Input] Register IREETensorExtDialect for Torch plugin (#22719) by Ian Wood · 2 weeks ago
  76. 39a15a7 [Encoding] Implement compatibility check for packed_storage (#22757) by Lukas Sommer · 2 weeks ago
  77. 74ee8f2 Integrate llvm/llvm-project@ebf5d9ef (#22761) by Vivian Zhang · 2 weeks ago
  78. 34b8187 Bump version to 3.10 after 3.9 release. (#22759) by Sahil Faizal · 2 weeks ago
  79. 77873f7 Update gfx1250 LDS size (#22760) by Ivan Butygin · 2 weeks ago
  80. b346a98 [DispatchCreation] Add FoldExtractSliceOfBroadcast Pattern (#22694) by Bangtian Liu · 2 weeks ago
  81. a9cae0b [Codegen] Test Cleanup 3/8: Common tests (#22746) by Quinn Dawkins · 2 weeks ago
  82. edff002 Integrate llvm/llvm-project@c582688b (#22758) by Vivian Zhang · 2 weeks ago
  83. 645b446 Use `scf::tileAndFuseConsumer` in `GPUFuseAndHoistParallelLoops` (#22617) by MaheshRavishankar · 2 weeks ago
  84. 1f322ce [Codegen] Test Cleanup 2/8: Common GPU tests (#22745) by Quinn Dawkins · 3 weeks ago
  85. acefc23 [Codegen] Test Cleanup 5/8: LLVMCPU tests (#22748) by Quinn Dawkins · 3 weeks ago
  86. 2e40437 [Codegen] Test Cleanup 6/8: LLVMGPU tests (#22749) by Quinn Dawkins · 3 weeks ago
  87. 222940b [Codegen] Test Cleanup 7/8: SPIRV tests (#22750) by Quinn Dawkins · 3 weeks ago
  88. 1a66819 [Codegen] Test Cleanup 4/8: Dialect tests (#22747) by Quinn Dawkins · 3 weeks ago
  89. 3b7ff2d [Codegen] Test Cleanup 8/8: VMVX tests (#22751) by Quinn Dawkins · 3 weeks ago
  90. abc8095 [CI] Bump golden value to 165*1.1=181.5 for prefill benchmark on mi325 (#22752) by Han-Chung Wang · 3 weeks ago
  91. b9afdb9 [Codegen] Test Cleanup 1/8: Common CPU tests (#22744) by Quinn Dawkins · 3 weeks ago
  92. 8c9e329 Integrate llvm/llvm-project@778e104d (#22741) by Vivian Zhang · 3 weeks ago
  93. a7b0d0b Fix incompatible pointer types for macOS build. (#22738) by Han-Chung Wang · 3 weeks ago
  94. 8ae91eb Bump actions/checkout from 5.0.1 to 6.0.0 in the github-actions group (#22742) by dependabot[bot] · 3 weeks ago
  95. 5f1ddc3 [TensorExt] Add Operations/Attributes/Interfaces for specifying ragged tensors. (#22267) by MaheshRavishankar · 3 weeks ago
  96. 843f9d1 [CI][TorchModels] Update flags for CLIP test. (#22413) by MaheshRavishankar · 3 weeks ago
  97. a18c213 Update CODEOWNERS to add more reviewers for GPU codegen pieces (#22721) by MaheshRavishankar · 3 weeks ago
  98. 3483097 [Dispatch Creation] Add aggressive reshape movement flag (#22707) by Ian Wood · 3 weeks ago
  99. 9269e03 [Codegen][GPU]Fixing barrier placement for 3+ stages pipelining (#22725) by Zhuoran Yin · 3 weeks ago
  100. a8f4791 Revert "[LLVMGPU][Codegen] Emit packed chain FMA from select multi_reductions and contracts" (#22736) by Han-Chung Wang · 3 weeks ago