Google Git Google Git
Sign in
llvm/llvm-project/mlir/HEAD
  1. 9f44ba7 [mlir][math] Add a set-llvm-linkage option to convert-math-to-funcs (#235961) by Alexander Viand · 11 minutes ago main master
  2. 84d0ec3 [mlir][emitc] Lower remaining C99 <math.h> functions in MathToEmitC (#235950) by Alexander Viand · 61 minutes ago
  3. 9e23c14 [CI] Bump deps to Python 3.15 (#235615) by Aiden Grossman · 3 hours ago
  4. 34c3aaa [TableGen] Store template arguments separately from fields (#234933) by Jay Foad · 3 hours ago
  5. ab87ada [mlir][xegpu] Skip scalable gather/scatter lowering (#234725) by Akimasa Watanuki · 3 hours ago
  6. fe906fd [mlir][tensor] Fix crash in ConvertToStaticExpandShape with negative constant output dims (#233804) by Wijkqwe · 4 hours ago
  7. a4963e6 [mlir][vector-to-gpu] Do not prepare masked contractions for MMA (#226732) by Vaisman · 4 hours ago
  8. 071828b [mlir][SPIRVToLLVM] Emit client API warning without attaching the module (#235750) by Arseniy Obolenskiy · 4 hours ago
  9. 4ac4cab [mlir][LLVM] Fix crash combining nested pointer data layouts (#222855) by Oscar Priego · 4 hours ago
  10. c3c1447 [mlir][vector] Do not flatten or scalarize region-masked transfers (#231799) by Vaisman · 5 hours ago
  11. 8564e74 [TBAA] Reject cyclic access type chains in the Verifier. (#235556) by Florian Hahn · 6 hours ago
  12. 6892dd9 [mlir][vector] Mask a write that fills its dims but starts at a non-zero index (#233243) by Dhairyashil R G · 6 hours ago
  13. d707a34 [mlir][acc] Decide reduction atomics by destination instead of by partitioning (#235099) by Vijay Kandiah · 8 hours ago
  14. 2b99820 [TableGen] Assert that RecordVal values are never null (#235077) by Jay Foad · 8 hours ago
  15. 24d9452 [AArch64][RuntimeDyld] Handle far external symbols in COFF JIT code (#229719) by YafetBeyene · 8 hours ago
  16. c9a266a [MLIR][XeGPU] Use all ones as the neutral value of an AND reduction (#232828) by Md Abdullah Shahneous Bari · 9 hours ago
  17. 5535440 [mlir][tensor] Fix element-count overflow assertion in reshape verifier (#222117) by Stanislav Bardyuk · 9 hours ago
  18. 2547817 [mlir][vector-to-gpu] Do not convert ops masked by vector.mask (#226548) by Vaisman · 10 hours ago
  19. 229e983 [MLIR][Index] Restrict subtraction comparison canonicalization (#216831) by at0m741 · 11 hours ago
  20. b0fccc8 [mlir][scf] support back peeling of signed integer loops (#235260) by Prashanth · 11 hours ago
  21. 553151a [mlir][tosa] Add tosa.argmin lowering to Linalg (#233754) by kmehanna · 12 hours ago
  22. ea79c03 [mlir][tosa] Support variadic batch dimensions in MATMUL operator (#232371) by kmehanna · 13 hours ago
  23. 82c1606 [mlir][NVVM] Split enums and attributes out of NVVMDialect.h (#235655) by Markus Böck · 14 hours ago
  24. ada9279 [mlir][linalg] Remap linalg.index when packing a structured op (#221430) by Vaisman · 16 hours ago
  25. 93b877a [mlir][vector] Fix transfer_write bufferization coverage checks (#234906) by Pecco · 20 hours ago
  26. 6e00d6d [mlir][scf] Propagate if conditions to captured select uses (#235433) by meinie · 32 hours ago
  27. 69a171b [mlir][linalg] Extend FoldReduceBroadcast to float maximumf/minimumf (#233417) by Wijkqwe · 36 hours ago
  28. 2eda527 [mlir] Skip uniquer locks when a context starts without threading (#235294) by Arseniy Obolenskiy · 2 days ago
  29. de05fde [mlir][linalg] Handle `DropPadUnitDims` when padding value is defined inside the pad body (#223712) by Federico Bruzzone · 2 days ago
  30. 918122e [mlir] Find the pattern dump root only when IR debugging is enabled (#233771) by Ivan Butygin · 2 days ago
  31. cc1e3d2 [mlir][SPIR-V] Support MaxByteOffset decoration in binary round trips (#235084) by Arseniy Obolenskiy · 3 days ago
  32. 32fc80e [MLIR][XeGPU] Rematerialize layout conversion sources after conflict resolution (#230669) by Nishant Patel · 3 days ago
  33. 21c3b3a [mlir][scf] add support for unsigned loop for back peeling (#234435) by Prashanth · 3 days ago
  34. 51cea5a [mlir][scf] Add scf.execute_region to the structural type conversions (#234405) by Jared Hoberock · 3 days ago
  35. ca202d3 [CIR] Add 'loop-id' to loop and branch types. (#235052) by Erich Keane · 3 days ago
  36. 398508c [SmallVector] Fixed usage in mlir/lib/TableGen/Operator.cpp. (#235067) by Slava Zakharin · 3 days ago
  37. 398fa42 Reland "[mlir] Fix false positive loops in RegionBranchOpInterface::hasLoop" (#234591) by Henrich Lauko · 3 days ago
  38. c3a6a82 [flang][OpenMP] Support for "omp assumes no_openmp". (#233252) by SunilKuravinakop · 3 days ago
  39. 633fbdd [mlir][acc] Flag the data region of a structured declare for the runtime (#234822) by Zhen Wang · 3 days ago
  40. c88bd8e [MLIR][CMake] Fix LLVM_DEFINITIONS handling in standalone example (#234653) by Christopher Bate · 3 days ago
  41. 704e90b [mlir] Avoid rewriting unreachable blocks in the greedy driver (#225814) by Mehdi Amini · 3 days ago
  42. 3f5c66d [mlir][gpu] Split target-specific passes out of MLIRGPUTransforms (#234903) by Markus Böck · 3 days ago
  43. f59ed1a [mlir][tensor] Verify that `tensor.pad` padding is non-negative (#231389) by Federico Bruzzone · 4 days ago
  44. ba07165 [mlir][Vector] Fold chains of `vector.extract` with dynamic positions (#228686) by Federico Bruzzone · 4 days ago
  45. 2942f1f [mlir][tosa] Move MUL shift value check out of verifier (#234063) by Akun · 4 days ago
  46. e9a2653 [mlir][cmake] NFC: fix typo (#234862) by Tobias Wölfel · 4 days ago
  47. 251a9fc [MLIR][NVVM] Support sparse.{de}compress MLIR Ops (#232731) by Kirill Vedernikov · 4 days ago
  48. 59054e7 [mlir][tosa] Emit a runtime assertion when lowering `tosa.pad` with negative padding (#232221) by Federico Bruzzone · 4 days ago
  49. bb45151 [mlir][linalg] Fix incorrect hoisting of transfers with mismatched masks (#232246) by Pecco · 4 days ago
  50. 5502042 [mlir][gpu] Fix address space casts in gpu.alloc/gpu.dealloc lowering (#234394) by Jared Hoberock · 4 days ago
  51. 7756da5 [Flang][OpenMP] Fix OpenMP data-mapping stride calculation (#225653) by Michael Klemm · 4 days ago
  52. de72c2f [LLVM][docs] Rename AMDGPU reST docs to Markdown (#233644) by Reid Kleckner · 4 days ago
  53. 00cae8e [MLIR][LLVMIR] Add 'align' to loop-annotations (#234263) by Erich Keane · 4 days ago
  54. aa8e19b [mlir][tosa] Don't broadcast non-constant mul shift and negate zero points (#233121) by Maher Ahmed Maher Shola · 4 days ago
  55. a089f6e [mlir][affine] Fix SuperVectorizer crash on uniforms from multi-result ops (#234531) by Mattéo Rizza Murgier · 5 days ago
  56. 5bbe2e2 [IRBuilder] Remove insertion block (#234245) by Nikita Popov · 5 days ago
  57. 39a59f1 Revert "[mlir] Fix false positive loops in RegionBranchOpInterface::hasLoop" (#234573) by Nikita Popov · 5 days ago
  58. b83695e [mlir][ABI] Add indirect address space to ArgClassification (#229991) by Chaitanya · 5 days ago
  59. 50a37c9 [mlir] Fix false positive loops in RegionBranchOpInterface::hasLoop (#233784) by Henrich Lauko · 5 days ago
  60. 3ed9df7 [mlir][tosa] Add `tosa.avg_pool2d_adaptive` purity note (#233473) by Luke Hutton · 5 days ago
  61. 89323bd [OpenMP][flang] Fix location of reducing worksharing constructs. (#233934) by Abid Qadeer · 5 days ago
  62. c468239 [mlir][tosa] Clarify signless integer type semantics (#234173) by Peng Sun · 5 days ago
  63. d05a33e [mlir][complex] Fix exp special values for infinite real part (#232791) by Chang Yong Lik · 5 days ago
  64. 50b6ec0 [mlir][arith] Honor finite min/max reduction identities (#232257) by Anutosh Bhat · 5 days ago
  65. 904b9c9 [mlir] Notify rewriter listeners when hoisting constants (#233776) by Ivan Butygin · 5 days ago
  66. b46ff03 PassBuilder: Take LLVMContext for LibraryOptionsContext (#233150) by Fangrui Song · 5 days ago
  67. 360e262 [mlir][cf] Canonicalize cf.switch cases targeting ub.unreachable (#234387) by Alexander Shaposhnikov · 5 days ago
  68. c8d8618 [mlir][LLVM] Add a negative test for inttoptr(ptrtoint(x)) (#234397) by Alexander Shaposhnikov · 5 days ago
  69. 89619f7 [OpenACC] Handle device_type(*) properly for OpenACC routine bind (#234373) by Moazin K. · 5 days ago
  70. 9b9b280 [mlir][acc] Reduce a complex accumulator componentwise (#234276) by Vijay Kandiah · 5 days ago
  71. 2b1cade [openmp][mlir] Expand use of atomicrmw for atomic update (#215654) by Ville-Markus Yli-Suutala · 5 days ago
  72. f5a4fdf [mlir][LLVM] Add LLVMStructType::getElementOffset() (#234171) by Ivan Kosarev · 5 days ago
  73. 3d73271 [mlir] Reduce contention in parallel pass execution and timing (#232948) by Mehdi Amini · 5 days ago
  74. 36310ab [mlir][tosa] Fix GCC 7 build failure in TosaProfileCompliance (#234239) by DeanSturtevant1 · 5 days ago
  75. e08e082 [mlir] Reduce template work in operation registration (NFC) (#233051) by Mehdi Amini · 5 days ago
  76. 187aec2 [MLIR][LLVMIR] Add 'distinct' ID to the loop-annotate attribute (#233890) by Erich Keane · 5 days ago
  77. 5960957 [mlir][tosa][NFC] Speed up compilation of TosaProfileCompliance (#233949) by DeanSturtevant1 · 5 days ago
  78. 34c27cc [mlir][SymbolTable] Handle unknown symbol users in SymbolUserMap (#227918) by Vinicius Silva · 6 days ago
  79. 6407a45 [mlir][tosa] Lower concat to tensor.concat (#231726) by Akun · 6 days ago
  80. 43064b0 [mlir][SPIR-V] Add Volatile function parameter round-trip tests (#232195) by Alexander Shaposhnikov · 6 days ago
  81. 63fc9aa [mlir][LLVM] Verify LLVMStructType element types in get() (#234091) by Henrich Lauko · 6 days ago
  82. 1ba2ae0 [mlir][tblgen] Define enum `FieldParser` specializations out-of-line (#233730) by Markus Böck · 6 days ago
  83. 24979c3 [MLIR][LLVM] Remove support for synthetic profile entry counts (#233357) by Aiden Grossman · 6 days ago
  84. fdbe695 [mlir][SPIR-V] Serialize decorations on FunctionCall results (#233917) by Arseniy Obolenskiy · 6 days ago
  85. 7d980cc [mlir][scf] support front peeling for unsigned loop (#233238) by Prashanth · 6 days ago
  86. fed9cc0 [mlir] Respect unknown memory effects in LICM and dead alloc erasure (#233939) by Sajid Zubair · 6 days ago
  87. 83a508a [mlir][OpenACC] Decouple frontend support from GPU operations (#233103) by Mehdi Amini · 6 days ago
  88. 10c9d21 [mlir][CIR] Separate OpenMP LLVM conversion helpers from the pass (NFC) (#232766) by Mehdi Amini · 6 days ago
  89. e5e2fe4 [mlir] Place MathToFuncs helpers in the nearest symbol table (#232582) by frokaikan · 6 days ago
  90. 663b8bc [MLIR] Fix SPIRV shared libs build after #232793 (#234024) by Jan Patrick Lehr · 6 days ago
  91. 38c079b [mlir][Canonicalizer] Preserve analyses when there is no change (#232159) by Hideto Ueno · 6 days ago
  92. e32ee1b [mlir][tosa] Fix assertion when folding mul with out of range shift (#233486) by Luke Hutton · 6 days ago
  93. 8f10509 [mlir][tosa] Fix slice fold when result type does not match input (#233515) by Luke Hutton · 6 days ago
  94. 0676374 [mlir][ArmSVE][NFC] Remove redundant scalability checks in contract lowering (#233868) by Andrzej Warzyński · 6 days ago
  95. 95e672d [mlir][flang][OpenMP] Privatize LINEAR list items with linear privatizers; support ALLOCATABLE (#228827) by Aditya Trivedi · 7 days ago
  96. 40bca52 [mlir][vector][nfc] Remove unused mask from tests (#233748) by Andrzej Warzyński · 7 days ago
  97. f0ca77b [mlir][bytecode] Allow selecting dialect versions in mlir-opt (#233149) by Mehdi Amini · 7 days ago
  98. 4d14764 [mlir][vector][NFC] Rename getShapeForUnroll to getIterationShapeToUnroll (#232648) by Andrzej Warzyński · 7 days ago
  99. 7715997 [mlir] Replace PointerUnion::dyn_cast with llvm::dyn_cast (NFC) (#233681) by Kazu Hirata · 7 days ago
  100. 0168562 [mlir][tosa] Fix tosa-to-linalg assertion on rescale with an output wider than 32 bits (#233508) by Stanislav Bardyuk · 7 days ago