Google GitGoogle Git
Sign in
llvm/llvm-project/mlir/HEAD
  1. 830c737 [mlir][xegpu] Block a convert_layout at a tile both layouts accept (#227892) by Jianhui Li · 3 hours ago main master
  2. 5f1333a [mlir][ROCDL] Add TargetInfo to replace Chipset, allow features queries (#223562) by Krzysztof Drewniak · 9 hours ago
  3. fcd77a8 [mlir][xegpu] Distribute extract_strided_slice over multiple dims (#227478) by Jianhui Li · 12 hours ago
  4. 4bb75ad [mlir][vector] Add an eliminate-vector-masks pass (#226517) by Dhairyashil R G · 13 hours ago
  5. fb379d5 [mlir][Vector] Reject scalable reduction in warp distribution (#225267) by Cheng-Chieh Liu · 14 hours ago
  6. 08ecbe1 [OpenMP] Fix missing implicit barriers in device worksharing loops (#227735) by Akash Banerjee · 14 hours ago
  7. 7143d5b [mlir][tosa] Add MXFP support for GATHER (#227710) by Maddy Dunn · 17 hours ago
  8. 60e425e [MLIR][VectorToGPU] Cache slice analysis in getOpToConvert (#221795) by Dmitriy Smirnov · 19 hours ago
  9. 28a7650 [mlir][SPIR-V] Verify memory semantics for AtomicLoad/Store/Exchange/CompareExchange ops (#212990) by Arseniy Obolenskiy · 19 hours ago
  10. c36f9a8 [mlir][SPIR-V] Share the memory operands mask verifier between both masks (#225520) by Arseniy Obolenskiy · 19 hours ago
  11. 29e51d6 [mlir][tosa] Lower AVG_POOL2D_ADAPTIVE to Linalg (#225637) by Jack Frankland · 21 hours ago
  12. dbc01f7 [mlir][SPIR-V] Fix CopyMemory handling of a lone memory operands mask (#226969) by Arseniy Obolenskiy · 23 hours ago
  13. b7c5491 [mlir][arith] Handle unsigned moduli in int-range optimizations (#224933) by 陈子昂 · 26 hours ago
  14. b7c0fde [mlir][sparse] Register bufferization dialect in stage pass (#227550) by Ziliang Zhang · 29 hours ago
  15. 1fe719d [mlir][bufferization] Make equivalent result removal order-independent (#227752) by Ziliang Zhang · 29 hours ago
  16. 1935109 [MLIR][Bufferization] Fix IdentityLayoutMap allocation at function boundaries (#227253) by Aaditya Agarwal · 30 hours ago
  17. be2c986 [mlir][ValueBounds] Skip analysis for identical slice components (#226894) by Ziliang Zhang · 30 hours ago
  18. b325568 [mlir][linalg] Document and diagnose pack/unpack memref limits (#225773) by Federico Bruzzone · 31 hours ago
  19. f192231 [mlir][vector] Fix VectorToSCF in-bounds check for negative indices (#224843) by Prashanth · 35 hours ago
  20. c52f8a3 [mlir][tosa] Lower MAX_POOL2D_ADAPTIVE to Linalg (#225675) by Jack Frankland · 2 days ago
  21. 4c9e722 [MLIR] Emit final-policy remarks in deterministic order (#224616) by Henrich Lauko · 2 days ago
  22. ef65412 [MLIR][LLVMIR] Restore constant folding for global initializer GEPs (#227651) by Henrich Lauko · 2 days ago
  23. d73e443 [mlir][x86] Add extra patterns for AMX nano-kernel lowering (acc with zero constant) (#222513) by Arun Thangamani · 2 days ago
  24. e1327ba [MLIR][Vector] Fix typo from #226524 (#227642) by Andrzej Warzyński · 2 days ago
  25. fd27c58 [mlir][vector] Use `ShapeCastOp` in `castAwayContractionLeadingOneDim` (#226524) by Andrzej Warzyński · 2 days ago
  26. b25c7b7 [mlir][affine] Handle generic memory ops in loop fusion dependence analysis (#224657) by purnima shrivastava · 2 days ago
  27. cce843d [mlir][bufferization] Skip parallel analysis without parallel regions (#227202) by Ziliang Zhang · 2 days ago
  28. c0305a6 [mlir] Test the final-policy remark on a failing pipeline without verification (#227276) by Henrich Lauko · 2 days ago
  29. f002738 [mlir][affine] Fix crash when rolling back vectorization of reduction loops (#226912) by Mattéo Rizza Murgier · 2 days ago
  30. d32fe67 [mlir][xegpu] Check uArch block shapes in VectorToXeGPU transfer lowering (#217179) by Igor Zamyatin · 2 days ago
  31. 4b2cf3b [MLIR][XeGPU][XeVM] Lower to XeVM: support skipping backend. (#227125) by Sang Ik Lee · 2 days ago
  32. 5054304 [OpenMP] Fix descriptor allocation for absent optional arrays (#227082) by Akash Banerjee · 2 days ago
  33. 9e0a1ea [MLIR][MathToXeVM] Add Algebraic simplification patterns in MathToXeVM. (#223442) by Md Abdullah Shahneous Bari · 2 days ago
  34. 6f1ca80 [mlir][OpenACC] Fix tile clause element bounds for descending loops (#227185) by Vijay Kandiah · 3 days ago
  35. bf52e31 [mlir][arith] Support equal-width float conversions (#225346) by Jack Frankland · 3 days ago
  36. f71b589 [mlir][OpenACC] Match reuse barriers to the reused private scope (#225570) by Delaram Talaashrafi · 3 days ago
  37. 3c48672 [mlir][ODS] Copy constant generated interface model prototypes (#226323) by Mehdi Amini · 3 days ago
  38. 5fe2db6 [mlir][tosa] Add allow-non-finites option for float min/max reduction (#222140) by Hariprasad Ravishankar · 3 days ago
  39. 73aa2f1 [mlir][tosa] Preserve non-TOSA ops in narrowing passes (#224594) by Jack Vickers · 3 days ago
  40. e796889 [clang][NVPTX] Add support for pzo in f32/f16x2/bf16x2 to FP4 conversions (#225318) by Dharuni R Acharya · 3 days ago
  41. 81f9a32 [mlir] Own the registrations of SourceMgrDiagnosticVerifierHandler (#226258) by Henrich Lauko · 3 days ago
  42. af19497 [LLVMIR] Directly lower global initializer GEP to constant expression (#226904) by Nikita Popov · 3 days ago
  43. efbf7a9 [mlir][cf] Fix cf.switch round-trip for case values wider than 64 bits (#221490) by Prajit Rahul · 3 days ago
  44. 949a906 [mlir][scf] Add unsignedCmp to scf.parallel and use it in the tiling in-bound check (#226130) by Samarth Narang · 3 days ago
  45. c6ceb26 [mlir][OpenACC] Record gang(static:) chunk size on lowered loops (#227037) by Delaram Talaashrafi · 3 days ago
  46. 8142240 Add registerToCppTranslation to CppEmmitter.h (#226337) by Jeremy Kun · 3 days ago
  47. 598e0de [MLIR] Fix mlir-reduce splitting smallest range instead of the largest one (#214738) by Daria Sukhonina · 3 days ago
  48. 57924d8 [mlir][OpenACC] Materialize routine bind targets before parallel call rewriting. (#227035) by nvptm · 3 days ago
  49. fb1dfcb [mlir][openacc] Update remark for privates (#227074) by Yian Su · 3 days ago
  50. 9695d11 [mlir] `remove-dead-values`: properly handle symbol users outside of a pass root. (#225355) by Ivan Butygin · 4 days ago
  51. 69071ef Give emitc.member_call_opaque operator precedence (#226349) by Jeremy Kun · 4 days ago
  52. ff57e23 [Flang][OpenMP] Support 'nowait' clause on taskwait (#219247) by Phoebe Linck · 4 days ago
  53. 17d7870 [mlir][transform] add ApplyEraseUnusedOperandsAndResultsPatternsOp transform op (#225864) by Tuomas Kärnä · 4 days ago
  54. c27d789 [MLIR][NVVM] Add SM version requirements to mbarrier Ops (#224105) by Dhairyashil R G · 4 days ago
  55. 451aa4f [mlir][tosa] Add assembly format for CONST (#226147) by Yuvaraj Venkatesh · 4 days ago
  56. ff5892c [mlir][memref] Enforce consistent reinterpret_cast metadata (#217338) by ioana ghiban · 4 days ago
  57. 46f33c3 [flang][OpenMP] Support allocate clauses on scope constructs (#221229) by Sairudra More · 4 days ago
  58. 20f5c3b [mlir][LLVM] Add smulh and umulh intrinsics. (#226776) by Letu Ren · 4 days ago
  59. bb58419 [MLIR][LLVM] Produce canonical const GEP in convertGEPOp (#226699) by Letu Ren · 5 days ago
  60. b261801 [mlir] Remove remaining strict property assembly opt-outs (#226702) by Mehdi Amini · 6 days ago
  61. bdee51a [mlir] Enable strict properties in assembly formats by default (#225742) by Mehdi Amini · 6 days ago
  62. d7f3e7b [MLIR][IRDL] Instantiate "." in IRDL-defined names as nested namespaces (#207035) by Ivan Ho · 6 days ago
  63. 055dd29 [MLIR][Python] Allow `Attribute` to denote unconstrained attributes in Python-defined ops (#224679) by Twice · 6 days ago
  64. 4ce5dbe [mlir][Interfaces] Share more operation interface bodies (NFC) (#226603) by Mehdi Amini · 6 days ago
  65. 6960a4f [mlir][ODS] Share operation interface methods with raw-op bodies (NFC) (#226317) by Mehdi Amini · 6 days ago
  66. 99c9b5a [MLIR] Enable strict assembly properties for the builtin dialect (#225750) by Mehdi Amini · 6 days ago
  67. f979110 [MLIR][XeGPU] Add MXFP fp8 WG GEMM tests and use shared input set (#225944) by Sang Ik Lee · 7 days ago
  68. 8a525d1 [mlir-c] Add mlirDialectMaterializeConstant (#206553) by Maksim Levental · 7 days ago
  69. 2d7533c [mlir][vector] Support fixed-size masks in `eliminateVectorMasks` (#221595) by Dhairyashil R G · 7 days ago
  70. f0b0e7a [mlir][XeVM] Stop using `getAttrs()`: explicitly preserve properties when cloning operations (NFC) (#226420) by Mehdi Amini · 7 days ago
  71. fe7d552 [mlir][LLVM] Stop using Operation::getAttrs in custom printers (NCF) (#226418) by Mehdi Amini · 7 days ago
  72. 2f2532a [mlir][Quant] Stop using Operation::getAttrs (NFC) (#226413) by Mehdi Amini · 7 days ago
  73. f14def0 [mlir][OpenACC] Stop using getAttrs() and copy function properties separately (NFC) (#226414) by Mehdi Amini · 7 days ago
  74. bd9c190 [mlir][Tensor] Stop using `getAttrs()` and only copy discardable call attributes explicitly (#226412) by Mehdi Amini · 7 days ago
  75. ac114f8 [mlir][nvgpu] Add negative tests for invalid FP8 warpgroup MMA types (#208047) by Vaisman · 7 days ago
  76. 351865c [mlir][bufferization] Support matching permutation maps in Linalg analysis (#226079) by Ziliang Zhang · 7 days ago
  77. 24fb667 [mlir][bufferization] Handle disjoint subsets in One-Shot Analysis (#224184) by Ziliang Zhang · 7 days ago
  78. 76545e1 [mlir][tosa] Use optnone for compliance initialization under HWAsan (#226310) by Walter Lee · 7 days ago
  79. d696bf1 [mlir] Constant-initialize registered operation hook tables (NFC) (#226320) by Mehdi Amini · 7 days ago
  80. 9e0c1fb [mlir][ODS] Share generated legacy property splitting (NFC) (#226085) by Mehdi Amini · 7 days ago
  81. 181ada3 [MLIR] Reduce generated assembly printer compile time (NFC) (#225740) by Mehdi Amini · 7 days ago
  82. e77c60e [mlir][bufferization] Relax happens-before analysis (#223777) by Colin De Vlieghere · 7 days ago
  83. 17f94fe [Flang][OpenMP][MLIR] Attach source location to target/target-data runtime c… (#222389) by Jason Van Beusekom · 8 days ago
  84. b82312e [NVPTX] Support 32-bit size operand for st.bulk (#217703) by robertvirany · 8 days ago
  85. 7563bed [mlir-c] Add mlirOperationIsAncestor and mlirOperationIsProperAncestor (#206556) by Maksim Levental · 8 days ago
  86. 358d215 [mlir][Vector] Fix scalable dim guard in broadcast lowering (#225021) by Cheng-Chieh Liu · 8 days ago
  87. 52d3d47 [mlir][openacc] Copy all host function attributes to the device routine (#226127) by Samarth Narang · 8 days ago
  88. 58ef6bf [mlir][xevm] Fold xevm.truncf of an xevm.extf round trip (#225875) by Sang Ik Lee · 8 days ago
  89. 276ee5d [mlir][xegpu] Distribute three more convert_layout cases to lanes (#222693) by Sang Ik Lee · 8 days ago
  90. 5041e47 [mlir][OpenACC] Preserve explicit device numbers in wait lowering (#222604) by leovance · 8 days ago
  91. 3ada089 [mlir][ODS] Share parser operand storage cleanup (NFC) (#226094) by Mehdi Amini · 8 days ago
  92. 4a656b0 [MLIR][XeGPU] Optimize create_mask sg-to-lane lowering (#221198) by Artem Kroviakov · 8 days ago
  93. 0fbb269 [mlir] Fold interface-map trait packs without recursive templates (NFC) (#226084) by Mehdi Amini · 8 days ago
  94. 48a1bc1 [mlir] Store OperationState property callbacks as function pointers (NFC) (#226083) by Mehdi Amini · 8 days ago
  95. 57f5033 [mlir] Fold operation trait lookup without a temporary array (NFC) (#226081) by Mehdi Amini · 8 days ago
  96. 8cbe060 [mlir][ODS] Share optional operand and type parser logic (NFC) (#226066) by Mehdi Amini · 8 days ago
  97. b5c0dc8 [mlir][ODS] Reuse collective builders for zero-result ops (NFC) (#226059) by Mehdi Amini · 8 days ago
  98. 77d7ae1 [mlir] Reduce Diagnostic storage across standard library debug modes (NFC) (#226070) by Mehdi Amini · 8 days ago
  99. 992baa7 [mlir][ODS] Share generated attribute property conversion (NFC) (#226057) by Mehdi Amini · 8 days ago
  100. aedd6ee [mlir][ODS] Reuse property storage in generated builders (NFC) (#226061) by Mehdi Amini · 8 days ago