August 2023 Archives by subject

• Messages sorted by: [ thread ] [ author ] [ date ]
• More info on this list...

Starting: Tue Aug 1 00:56:45 PDT 2023
Ending: Thu Aug 31 23:53:19 PDT 2023
Messages: 409

• [Mlir-commits] [mlir] 00aa1a8 - Revert "[mlir][irdl] Support variadicity check in operations"   Mathieu Fehr
• [Mlir-commits] [mlir] 00d27fb - [mlir][sparse] Disable sparse_reshape_dot.mlir test with XFAIL   Christian Sigg
• [Mlir-commits] [mlir] 012b148 - [mlir] Fix crash when adding nested dialect extensions   Matthias Springer
• [Mlir-commits] [mlir] 01f4390 - [MLIR] Fold memref.reinterpret_cast(x) -> x when the type is fully static and   Andrey Turetskiy
• [Mlir-commits] [mlir] 024f562 - [mlir] Use a type for representing branch points in `RegionBranchOpInterface`   Markus Böck
• [Mlir-commits] [mlir] 0259669 - [mlir] Add a postprocessing parameter in Pattern   Jian Cai
• [Mlir-commits] [mlir] 02afc69 - [mlir][NFC] clang-format file   Markus Böck
• [Mlir-commits] [mlir] 030e315 - [mlir][linalg][transform][python] Verify modules in mix-in tests.   Ingo Müller
• [Mlir-commits] [mlir] 03b43d3 - Fix scf-to-cfg conversion for IndexSwitchOp   Eugene Zhulenev
• [Mlir-commits] [mlir] 0495912 - [mlir][sparse] Adding `LvlVar` forward-declarations to `DimLvlMap::print`   wren romano
• [Mlir-commits] [mlir] 0575ab2 - [mlir][tensor][transform][python] Add mix-in class.   Ingo Müller
• [Mlir-commits] [mlir] 059da56 - [MLIR][Lianlg] Add memory effects for softmax   Lorenzo Chelini
• [Mlir-commits] [mlir] 061aa2e - [mlir][bufferization] Better error checking for ops with unstructured control flow   Matthias Springer
• [Mlir-commits] [mlir] 0620f99 - Fix minor typos in comments in MLIR Pass.cpp (NFC)   Mehdi Amini
• [Mlir-commits] [mlir] 0664db5 - [mlir][sparse][gpu] fix spgemm runtime compile error   Kun Wu
• [Mlir-commits] [mlir] 067bd7d - [mlir][vector] Use optional for outerproduct accumulator instead of variadic   Cullen Rhodes
• [Mlir-commits] [mlir] 067ecad - [Flang][OpenMP] Convert elementTypeAttr for AtomicRead Op   Kiran Chandramohan
• [Mlir-commits] [mlir] 0682131 - [mlir][ROCDL] Adds the ROCDL target attribute.   Fabian Mora
• [Mlir-commits] [mlir] 06dacf5 - [mlir][func][bufferization][NFC] Simplify implementation   Matthias Springer
• [Mlir-commits] [mlir] 07bd5f2 - [mlir][sparse] Support strided convolution on compressed level.   Peiming Liu
• [Mlir-commits] [mlir] 07d135e - [mlir][ArmSME][test] Cleanup printing scalable vectors in vector-load-store.mlir (NFC)   Benjamin Maxwell
• [Mlir-commits] [mlir] 08d7377 - [mlir] Enable DRR variadic operand matching   Logan Chien
• [Mlir-commits] [mlir] 08ed557 - [mlir] mlir-opt: Fix linking after 7c4e8c6a273f2 .   Will Dietz
• [Mlir-commits] [mlir] 097efdd - [mlir] Add missing #include after 7c4e8c6   Christian Sigg
• [Mlir-commits] [mlir] 0a0aff2 - fix unused variable warnings in conditionals   Mikhail Goncharov
• [Mlir-commits] [mlir] 0ac21e6 - [mlir][IR] SingleBlockImplicitTerminator: Declare "inherited" trait in ODS instead of C++   Matthias Springer
• [Mlir-commits] [mlir] 0bb4d4d - [mlir][transform] Add ApplyToLLVMConversionPatternsOp   Matthias Springer
• [Mlir-commits] [mlir] 0bc1430 - [mlir][linalg][transform][python] Fix type hints   Rahul Kayaith
• [Mlir-commits] [mlir] 0bcae5e - [mlir][bufferization] Add pattern to BufferDeallocationSimplification pass   Martin Erhart
• [Mlir-commits] [mlir] 0c46a91 - [MLIR] Infer locations for block argument conversion   Nandor Licker
• [Mlir-commits] [mlir] 0c4aad0 - Revert "[mlir][linalg][transform][python] Add mix-in for BufferizeToAllocOp."   Mehdi Amini
• [Mlir-commits] [mlir] 0cd5e02 - [mlir][transform] Improve assembly format of apply_conversion_patterns   Matthias Springer
• [Mlir-commits] [mlir] 0d18c2d - [mlir][ods] Allow custom directives to anchor optional groups in op assembly formats   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 0d3abdc - [mlir][Linalg] Fix formatting of generated docs markdown   Benjamin Maxwell
• [Mlir-commits] [mlir] 0db1ae3 - [mlir][CFGToSCF] Visit subregions in CFGToSCF pass   Ivan Butygin
• [Mlir-commits] [mlir] 0e98fb9 - [MLIR][transforms] Add an optimization pass to remove dead values   Srishti Srivastava
• [Mlir-commits] [mlir] 0f8bab8 - [mlir] Revamp implementation of sub-byte load/store emulation.   Mahesh Ravishankar
• [Mlir-commits] [mlir] 10ae8ae - [mlir][NFC] Make `ReturnLike` trait imply `RegionBranchTerminatorOpInterface`   Markus Böck
• [Mlir-commits] [mlir] 1102489 - [mlir][transform] Fix typo in ApplyConversionPatternsOp   Matthias Springer
• [Mlir-commits] [mlir] 1295a35 - [mlir][irdl] Support variadicity check in operations   Mathieu Fehr
• [Mlir-commits] [mlir] 12b4951 - [mlir][vector] Add missing support for scalable vectors   Andrzej Warzynski
• [Mlir-commits] [mlir] 12ce9fd - [mlir][spirv] Add client-api option to -convert-spirv-to-llvm   Victor Perez
• [Mlir-commits] [mlir] 12e1a9b - [mlir][ArmSME] Extend vector.transfer_write lowering   Andrzej Warzynski
• [Mlir-commits] [mlir] 138df29 - [mlir] Revamp `RegionBranchOpInterface` successor mechanism   Markus Böck
• [Mlir-commits] [mlir] 14de5a2 - [mlir][complex] Initial support for FastMath flag when converting to LLVM   Kai Sasaki
• [Mlir-commits] [mlir] 15a08cf - [mlir][Vector] Fold selects of single-element i1 vectors   Diego Caballero
• [Mlir-commits] [mlir] 15ea230 - [mlir][NVGPU] Support N-D masks in transform.nvgpu.create_async_groups   Matthias Springer
• [Mlir-commits] [mlir] 185bf56 - [mlir][linalg] NFC: Rename SVE integration tests directory from Scalable to ArmSVE   Cullen Rhodes
• [Mlir-commits] [mlir] 1896096 - [mlir][ROCM] Add Wave/Warp shuffle lowering and op for ROCM.   Anush Elangovan
• [Mlir-commits] [mlir] 189f4ac - [mlir][Presburger] Remove slow applyDomainAndRange test   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 18e161f - [MLIR][NVVM] Introduction of the `wgmma.mma_async` Op   Guray Ozen
• [Mlir-commits] [mlir] 199442e - [mlir][vector] Fix uniform transfer_read distribution   Lei Zhang
• [Mlir-commits] [mlir] 19b1107 - [mlir][gpu] Add debug print with environment value   Guray Ozen
• [Mlir-commits] [mlir] 1b1cfe4 - [mlir] Set intial value for integer FieldParser function   Mahesh Ravishankar
• [Mlir-commits] [mlir] 1b272d2 - Revert "[mlir][VectorOps] Use SCF for vector.print and allow scalable vectors"   Mehdi Amini
• [Mlir-commits] [mlir] 1c5fd15 - [mlir][Tosa] Allow non-fp32 tosa.cast to integers   Krzysztof Drewniak
• [Mlir-commits] [mlir] 1d9dcca - [mlir][vector] Add canonicalzation pattern for shape_cast(create_mask)   Andrzej Warzynski
• [Mlir-commits] [mlir] 1e15d79 - [mlir][sparse] minor cleanup of merger unit test   Aart Bik
• [Mlir-commits] [mlir] 1e491c4 - [mlir][sparse][gpu] add 2:4 spmm prune_and_check flag   Kun Wu
• [Mlir-commits] [mlir] 1e4e891 - [mlir][sme][nfc] Split tests into a separate file   Andrzej Warzynski
• [Mlir-commits] [mlir] 1e77536 - Revert "[mlir][ROCDL] Adds the ROCDL target attribute."   Fabian Mora
• [Mlir-commits] [mlir] 1e92e25 - [MLIR][OpenMP] Added MLIR translation support for use_device clauses   Akash Banerjee
• [Mlir-commits] [mlir] 20966fc - [mlir][linalg][transform][python] Add mix-in for BufferizeToAllocOp.   Ingo Müller
• [Mlir-commits] [mlir] 211c975 - [mlir][NVVM] Adds the NVVM target attribute.   Fabian Mora
• [Mlir-commits] [mlir] 2257ebd - [mlir][arith][bufferize] Fix crash when bufferizing elementwise arith.select   Matthias Springer
• [Mlir-commits] [mlir] 22a28d8 - [mlir][spirv] NFC: split bitwidth emulation tests out   Lei Zhang
• [Mlir-commits] [mlir] 22e8d5b - [mlir][sparse] Support strided convolution on dense level.   Peiming Liu
• [Mlir-commits] [mlir] 232f8ea - [MLIR][analysis] Fix call op handling in sparse backward dataflow   Srishti Srivastava
• [Mlir-commits] [mlir] 23e5130 - [mlir][test] Reland: Refactor SparseTensor CPU integration tests   Andrzej Warzynski
• [Mlir-commits] [mlir] 25396e1 - [mlir][test] Fix typo in a test   Andrzej Warzynski
• [Mlir-commits] [mlir] 254d139 - [mlir][bufferization] CloneOp: implement memory side-effects in ODS   Martin Erhart
• [Mlir-commits] [mlir] 25bc999 - Intrinsics: Add type overload to stacksave and stackstore   Matt Arsenault
• [Mlir-commits] [mlir] 2660fef - [mlir] Fix DRR either local variable redefinition   Logan Chien
• [Mlir-commits] [mlir] 289f723 - [mlir][sparse][gpu] minor code cleanup for sparse gpu ops   Aart Bik
• [Mlir-commits] [mlir] 28d8c0d - [mlir][nvgpu] Fix -Wunused-variable in NVGPUTransformOps.cpp (NFC)   Jie Fu
• [Mlir-commits] [mlir] 28fef90 - [mlir][VectorOps] Fix folding of vector.extract from stretch vector.broadcast   Benjamin Maxwell
• [Mlir-commits] [mlir] 296d5cb - [mlir][BuiltinTypes] Return VectorType from VectorType::Builder conversion operator   Benjamin Maxwell
• [Mlir-commits] [mlir] 2a5d497 - [mlir][python] Add __{bool, float, int, str}__ to bindings of attributes.   Ingo Müller
• [Mlir-commits] [mlir] 2ad297d - [mlir][spirv] Handle zero-element tensors in spirv type conversion   Jakub Kuderski
• [Mlir-commits] [mlir] 2b06650 - [mlir][spirv] Fix integer type emulation with extension/truncation   Lei Zhang
• [Mlir-commits] [mlir] 2b1bdc9 - fix build error.   Peiming Liu
• [Mlir-commits] [mlir] 2b2889b - Add index::CmpOp canonicalization.   Weiwei Chen
• [Mlir-commits] [mlir] 2b5b2bf - [mlir][gpu] Add DecomposeMemrefsPass   Ivan Butygin
• [Mlir-commits] [mlir] 2b664d6 - [mlir][python bindings] turn on openmp   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 2cc5f5d - [mlir][Linalg] Implement tileReductionUsingScf for multiple reductions   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 2d3dcd4 - [mlir][linalg][transform][python] Add mix-in for BufferizeToAllocOp.   Ingo Müller
• [Mlir-commits] [mlir] 2d8f793 - Revert "[mlir] Add a postprocessing parameter in Pattern"   Mehdi Amini
• [Mlir-commits] [mlir] 2dd3f42 - [mlir][ArmSME] Lower vector.broadcast to ArmSME   Cullen Rhodes
• [Mlir-commits] [mlir] 2e53e15 - [mlir][complex] Convert complex.abs to arith with fastmath flag   Kai Sasaki
• [Mlir-commits] [mlir] 2ef44aa - [MLIR][Bytecode] Add missing field initializer in constructor initializer list   Mehdi Amini
• [Mlir-commits] [mlir] 2ef7e20 - [MLIR] Enable converting dialect attributes on external functions   Sergio Afonso
• [Mlir-commits] [mlir] 2f0047a - [MLIR][OpenMP] Allow map operands to be not specified   Kiran Chandramohan
• [Mlir-commits] [mlir] 2f8d8c7 - Generalize finding the rocm_agent_enumberator program   Krzysztof Drewniak
• [Mlir-commits] [mlir] 30c1866 - [mlir][sparse][gpu] enable SpGEMM on GPU for libgen path   Aart Bik
• [Mlir-commits] [mlir] 3185031 - [mlir][ArmSME] Remove "pure" side-effect from 'get_tile_id' op to prevent CSE   Cullen Rhodes
• [Mlir-commits] [mlir] 32b7c1f - [mlir][TOSA] Set default TOSA validation level to 'None' for TOSA -> linalg   Benjamin Maxwell
• [Mlir-commits] [mlir] 345acac - [mlir] Fix shared libs build after 138df298208a095dc9bb9e5d1e3c67231b0abd77   Markus Böck
• [Mlir-commits] [mlir] 359ba0b - [mlir][CFGToSCF] Add interface changes for downstream projects   Markus Böck
• [Mlir-commits] [mlir] 3610c82 - [mlir][bufferization] Enable BufferizationToMemRef to run on functions   Martin Erhart
• [Mlir-commits] [mlir] 363b655 - Finish renaming getOperandSegmentSizeAttr() from `operand_segment_sizes` to `operandSegmentSizes`   Mehdi Amini
• [Mlir-commits] [mlir] 36c9afc - [mlir][emitc][nfc] List supported comparisons   Marius Brehler
• [Mlir-commits] [mlir] 370a6f0 - [MLIR] Make the `ConversionTarget` const ref in the DialectConversion (NFC)   Mehdi Amini
• [Mlir-commits] [mlir] 370a7ea - [mlir][spirv] Handle zero-sized memrefs   Jakub Kuderski
• [Mlir-commits] [mlir] 372d88b - [mlir][sparse] code cleanup.   Peiming Liu
• [Mlir-commits] [mlir] 37ce660 - [mlir] Fix resource printing in the presence of multiple dialects   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 3875804 - [mlir][VectorOps] Use SCF for vector.print and allow scalable vectors   Benjamin Maxwell
• [Mlir-commits] [mlir] 39d8876 - [mlir][NVGPU] Support 2D masks in transform.nvgpu.create_async_groups   Matthias Springer
• [Mlir-commits] [mlir] 3a8db0f - [mlir] Reduce warnings for bad assertion in generated code   Valentin Clement
• [Mlir-commits] [mlir] 3b45fe2 - [mlir][cf] Add ControlFlow to SCF lifting pass   Markus Böck
• [Mlir-commits] [mlir] 3b4b6cb - [mlir][ArmSME] Add move vector to tile slice op and lowerings   Cullen Rhodes
• [Mlir-commits] [mlir] 3bcc63e - [mlir][lsp] Add LSP support for attribute and type aliases   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 3c5b4da - [mlir][docs] Fix typos.   Jian Cai
• [Mlir-commits] [mlir] 3c9aa10 - Foo   Nicolas Vasilache
• [Mlir-commits] [mlir] 3cb0128 - [mlir][tensor] Do not fold rank-reduced extract_slice into unpack op.   Hanhan Wang
• [Mlir-commits] [mlir] 3dd5833 - [mlir][Transforms] TypeConverter: Mark conversion/materialization functions as "const"   Matthias Springer
• [Mlir-commits] [mlir] 3e2e10b - Clarify the invariant of the MLIR pass pipeline around `Pass::initialize()`   Mehdi Amini
• [Mlir-commits] [mlir] 3f7f1bc - [mlir] Update AArch64 integration tests to use mlir-cpu-runner   Andrzej Warzynski
• [Mlir-commits] [mlir] 3fe8ec7 - Revert "[mlir][Arith] Add arith.is_nan and arith.is_inf predicates"   Krzysztof Drewniak
• [Mlir-commits] [mlir] 40bf363 - [MLIR][Math] Add support for f16 in the expansion of math.roundeven   Alexander Shaposhnikov
• [Mlir-commits] [mlir] 41cb3c4 - Fix-forward broken test case from 2a5d497494c24425e99655b85e2277dd3f15a400.   Ingo Müller
• [Mlir-commits] [mlir] 43752a2 - [mlir][gpu] Add the `gpu-module-to-binary` pass.   Fabian Mora
• [Mlir-commits] [mlir] 4434bc5 - [tests] Fix gpu-to-cubin.mlir (NFC)   Benjamin Maxwell
• [Mlir-commits] [mlir] 4529797 - Add a generic "convert-to-llvm" pass delegating to an interface   Mehdi Amini
• [Mlir-commits] [mlir] 45d2033 - [MLIR][Printing] ASMPrinter prints escape characters in Resources   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 475938d - [flang][openacc] Update the global ctor for descriptor   Valentin Clement
• [Mlir-commits] [mlir] 4760ea0 - [mlir][gpu] Add the GPU offloading handler attribute interface.   Fabian Mora
• [Mlir-commits] [mlir] 490dae2 - [mlir][VectorOps] Use SCF for vector.print and allow scalable vectors   Benjamin Maxwell
• [Mlir-commits] [mlir] 4bac6ed - [mlir][openacc] Add set operation   Valentin Clement
• [Mlir-commits] [mlir] 4bdc905 - [openacc] Add implicit flag to declare attribute   Razvan Lupusoru
• [Mlir-commits] [mlir] 4bde084 - [mlir][bufferization] Change semantics of DeallocOp result values   Martin Erhart
• [Mlir-commits] [mlir] 4dd744a - Reland "[mlir] Use a type for representing branch points in `RegionBranchOpInterface`"   Markus Böck
• [Mlir-commits] [mlir] 4e9eaa2 - [mlir][vector] Allow out-of-bounds starting positition for vector transfer ops   Matthias Springer
• [Mlir-commits] [mlir] 4fdc019 - [mlir][SCF] Add `SingleBlock` op trait to "scf.while"   Matthias Springer
• [Mlir-commits] [mlir] 4ffc63a - [mlir][spirv] Fix 64-bit index for MemRef bitwidth emulation   Lei Zhang
• [Mlir-commits] [mlir] 5033ec0 - Revert "[tests] Fix gpu-to-cubin.mlir (NFC)"   Mehdi Amini
• [Mlir-commits] [mlir] 5066551 - [mlir] Apply ClangTidy fixes (NFC)   Adrian Kuegel
• [Mlir-commits] [mlir] 50a76a7 - [MLIR][NVGPU] Handling Offset in `nvgpu.tma.async.load`   Guray Ozen
• [Mlir-commits] [mlir] 50ab427 - [MLIR][NVGPU] Introduce Warpgroup Matrix Descriptor Type   Guray Ozen
• [Mlir-commits] [mlir] 51a5707 - [mlir][vector] Add missing canonicalisation for vector.multi_reduction   Andrzej Warzynski
• [Mlir-commits] [mlir] 51b65d0 - [mlir][AMDGPU] Improve BF16 handling through AMDGPU compilation   Krzysztof Drewniak
• [Mlir-commits] [mlir] 51c9f12 - [mlir] Use StringMap::lookup (NFC)   Kazu Hirata
• [Mlir-commits] [mlir] 51eaee3 - [mlir][SparseTensor] Fix test regression   Andrzej Warzynski
• [Mlir-commits] [mlir] 51ebecf - [mlir][sparse] Changed sparsity properties to use _ instead of -   Yinying Li
• [Mlir-commits] [mlir] 52aa6bd - [mlir][Conversion] Implement ConvertToLLVMPatternInterface (1)   Matthias Springer
• [Mlir-commits] [mlir] 52b93d2 - [mlir][nvgpu] remove duplicated pattern (nfc)   Guray Ozen
• [Mlir-commits] [mlir] 5388149 - [mlir][cuda runtime] Set Max Dynamic Shared Memory Attribute   Guray Ozen
• [Mlir-commits] [mlir] 53cae21 - [mlir] Remove unused declaration populateExtractOpVectorizationPatterns   Kazu Hirata
• [Mlir-commits] [mlir] 5468340 - [mlir][bufferization] Improve analysis for element-wise operations   Matthias Springer
• [Mlir-commits] [mlir] 550b6f1 - [mlir][openacc] Add acc.declare_action attribute   Valentin Clement
• [Mlir-commits] [mlir] 553943d - [mlir][spirv] Fix description formatting in BitOps. NFC.   Jakub Kuderski
• [Mlir-commits] [mlir] 5577493 - [mlir] Update mlir/docs/Tutorials/UnderstandingTheIRStructure.md (NFC)   Jie Fu
• [Mlir-commits] [mlir] 55e3857 - Make buffer hoisting/promotion passes use AllocationOpInterface   Mehdi Amini
• [Mlir-commits] [mlir] 5703519 - [mlir] Fix typo in comments   Aart Bik
• [Mlir-commits] [mlir] 574e759 - [mlir][ods] Support using custom directives as first optional group element   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 576b184 - [mlir][vector] Add support for scalable vectors in `trimLeadingOneDims`   Andrzej Warzynski
• [Mlir-commits] [mlir] 57c090b - [mlir][linalg][transform][python] Improve mix-in for PadOp.   Ingo Müller
• [Mlir-commits] [mlir] 57f03ba - Revert "[MLIR] Switch the default for usePropertiesForAttributes (NFC)"   Mehdi Amini
• [Mlir-commits] [mlir] 583e78b - [mlir] Apply ClangTidy fixes (NFC)   Adrian Kuegel
• [Mlir-commits] [mlir] 5a1f87f - Revert "[mlir][test] Refactor SparseTensor CPU integration tests"   Aart Bik
• [Mlir-commits] [mlir] 5b29f86 - [mlir] Fix verifier of `RegionBranchOpInterface`   Markus Böck
• [Mlir-commits] [mlir] 5c3150e - [MLIR][NVVM] Introduce WGMMA Types   Guray Ozen
• [Mlir-commits] [mlir] 5c58172 - [mlir][Vector] Add support for scalable vectors in multi_reduction   Andrzej Warzynski
• [Mlir-commits] [mlir] 5c7d97b - [mlir][bufferization] Canonicalizer to skip extract_strided_metadata when operand is already a base memref.   Martin Erhart
• [Mlir-commits] [mlir] 5e57752 - Fix minor typos in MLIR doc (NFC)   Mehdi Amini
• [Mlir-commits] [mlir] 5f230ed - [mlir][llvm] Translate alias scopes lazily   Tobias Gysi
• [Mlir-commits] [mlir] 5f6c036 - [mlir][linalg] Extend scalable vectorisation support   Andrzej Warzynski
• [Mlir-commits] [mlir] 604aba0 - [mlir] Fix -Wunused-variable warning in AsmParserState.cpp (NFC)   Jie Fu
• [Mlir-commits] [mlir] 6081f56 - [mlir][ArmSME] Use vector.reduction add in zero test   Cullen Rhodes
• [Mlir-commits] [mlir] 616eb0b - [mlir][gpu] Fix error message on unknown CUDA error code.   Ingo Müller
• [Mlir-commits] [mlir] 620e2bb - [mlir][LLVM] NFC - Remove createIndexConstant method   Nicolas Vasilache
• [Mlir-commits] [mlir] 62b2b39 - [mlir][irdl] Support variadicity check in operations   Mathieu Fehr
• [Mlir-commits] [mlir] 64e86d8 - [mlir] Update mlir/examples/standalone/README.md (NFC)   Jie Fu
• [Mlir-commits] [mlir] 653f776 - [mlir][complex] Convert complex.abs to arith with fastmath flag   Kai Sasaki
• [Mlir-commits] [mlir] 65a6be5 - [mlir][ArmSME] Use memref indices for load and store   Cullen Rhodes
• [Mlir-commits] [mlir] 660fded - [mlir][bufferization] Add specialized lowering for deallocs with one memref but arbitrary retains   Martin Erhart
• [Mlir-commits] [mlir] 667a195 - [mlir][LLVM] Fix dbg intrinsic import of killed locations   Christian Ulmann
• [Mlir-commits] [mlir] 667a9f7 - [MLIR][OpenMP] Fix compiler crash when translating omp.target to LLVM IR   Sergio Afonso
• [Mlir-commits] [mlir] 66ff408 - [mlir] Fix a warning   Kazu Hirata
• [Mlir-commits] [mlir] 67c092c - [mlir][transform][python] Add test for AnyValueType binding.   Ingo Müller
• [Mlir-commits] [mlir] 691a2fa - [mlir][linalg][transform][python] Add mix-in for MapCopyToThreadsOp.   Ingo Müller
• [Mlir-commits] [mlir] 69a3c9c - [mlir][spirv] Support sub-byte element vector extension/truncation   Lei Zhang
• [Mlir-commits] [mlir] 69cd6ae - [mlir][linalg][nfc] Clarify the description of linalg.matmul   Andrzej Warzynski
• [Mlir-commits] [mlir] 69ffd49 - [mlir] Use {DenseSet, DenseMap, SemallDenseSet}::contains (NFC)   Kazu Hirata
• [Mlir-commits] [mlir] 6a0e536 - [mlir] Fully qualify typenames in SymbolInterfaces.td   Markus Böck
• [Mlir-commits] [mlir] 6a0feb1 - [mlir][ROCDL] Adds the ROCDL target attribute.   Fabian Mora
• [Mlir-commits] [mlir] 6b5ce2c - [mlir][transform] Expose vector patterns useful for cleaning up masked vectorization and add test to showcase composition   Nicolas Vasilache
• [Mlir-commits] [mlir] 6c4cd7a - [mlir][sparse][gpu] refine sparse gpu round-trip and lowering test   Aart Bik
• [Mlir-commits] [mlir] 6ca0b27 - [mlir][sparse] more complicated test for dual sparse convolution kernel.   Peiming Liu
• [Mlir-commits] [mlir] 6cde64a - [mlir] Apply ClangTidy fix (NFC)   Adrian Kuegel
• [Mlir-commits] [mlir] 6e4ea4e - add `owner` to OpResultsList. this is useful for when the list is empty and an element can't be used to fetch the owner.   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 6e8db66 - Fix MLIR doc build   Mehdi Amini
• [Mlir-commits] [mlir] 6eb0332 - [mlir][sparse] test pack copy behavior   Aart Bik
• [Mlir-commits] [mlir] 6ebeecf - [mlir][transform] ApplyConversionPatternsOp: Make conversion target optional   Matthias Springer
• [Mlir-commits] [mlir] 6ecebb4 - [mlir][bufferization] Support unstructured control flow   Matthias Springer
• [Mlir-commits] [mlir] 733edde - [mlir][sparse] reorganized method order in sparse support lib header   Aart Bik
• [Mlir-commits] [mlir] 73ddc44 - [mlir][vector] Enable distribution over multiple dimensions   Lei Zhang
• [Mlir-commits] [mlir] 765e82e - [mlir][bufferization] Generalize dealloc simplification pattern   Martin Erhart
• [Mlir-commits] [mlir] 76a80a0 - [mlir][sparse][gpu] sparsifier GPU libgen for SpGEMM in cuSparse   Aart Bik
• [Mlir-commits] [mlir] 778494a - [mlir][bufferization] Add bufferization.dealloc canonicalizer to remove unused alloc-dealloc pairs   Martin Erhart
• [Mlir-commits] [mlir] 781883e - [mlir][ArmSME] Split lowering of arith.constant from vector.transfer_write   Cullen Rhodes
• [Mlir-commits] [mlir] 78921a6 - [mlir][sparse] Add more helper methods for converting DimLvlExpr to Var   Aart Bik
• [Mlir-commits] [mlir] 7897a94 - [mlir][vector] Fold extract(shape_cast) for same element count   Lei Zhang
• [Mlir-commits] [mlir] 793ee2b - [mlir][gpu] Add DecomposeMemrefsPass   Ivan Butygin
• [Mlir-commits] [mlir] 79ff70f - [mlir][sparse] Better error handling when bufferizing sparse_tensor ops   Matthias Springer
• [Mlir-commits] [mlir] 7a8dcf2 - [mlir][sparse][gpu] add CHECK test to spGEMM libgen   Aart Bik
• [Mlir-commits] [mlir] 7c349c3 - [mlir][Arith] Add arith.is_nan and arith.is_inf predicates   Krzysztof Drewniak
• [Mlir-commits] [mlir] 7c4e8c6 - [mlir] Disentangle dialect and extension registrations.   Fabian Mora
• [Mlir-commits] [mlir] 7c74a25 - [mlir][SCF][NFC] Add helper functions to get body of scf.while   Matthias Springer
• [Mlir-commits] [mlir] 7c800a4 - [mlir] Relax requirement on memory buffer creation.   Jacques Pienaar
• [Mlir-commits] [mlir] 7d6fb14 - [mlir] Apply ClangTidy fix (NFC)   Adrian Kuegel
• [Mlir-commits] [mlir] 7db1853 - [mlir][MemRefToLLVM] Add fmin, fmax to AtomicRMW lowering   Krzysztof Drewniak
• [Mlir-commits] [mlir] 7e9d7db - [mlir][LLVM] Add support for DIModule metadata   Christian Ulmann
• [Mlir-commits] [mlir] 7ec88f0 - [mlir][memref][transform] Add vector_to_llvm conversion patterns   Matthias Springer
• [Mlir-commits] [mlir] 7f4026e - [mlir] Add linalg.batch_mmt4d named op   Jerry Wu
• [Mlir-commits] [mlir] 7f4dbd8 - [mlir][GPU][NFC] Remove type converter hack   Matthias Springer
• [Mlir-commits] [mlir] 804b997 - [mlir][openacc] Introduce acc.declare operation   Valentin Clement
• [Mlir-commits] [mlir] 809b440 - Fix MLIR pass manager initialization: hash the pass pipeline to detect when initialization is needed   Mehdi Amini
• [Mlir-commits] [mlir] 8154494 - [mlir][sparse] refactor sparsification and bufferization pass into proper TD pass   Aart Bik
• [Mlir-commits] [mlir] 8184737 - [mlir][Linalg] Clarify error message in YieldOp verification NFC   Mehdi Amini
• [Mlir-commits] [mlir] 81c326c - [mlir][spirv] NFC: Merge ArithToSPIRV pattern decl and definition   Lei Zhang
• [Mlir-commits] [mlir] 834cdc8 - [mlir][ArmSME] Fix get_tile_id type in zero lowering   Cullen Rhodes
• [Mlir-commits] [mlir] 8399f37 - [mlir][doc] fix document link in Builtin Dialect document   Aart Bik
• [Mlir-commits] [mlir] 83af56e - [mlir][tblgen] Fully qualify more names.   Christian Sigg
• [Mlir-commits] [mlir] 863c346 - [MLIR] Switch the default for usePropertiesForAttributes (NFC)   Mehdi Amini
• [Mlir-commits] [mlir] 8663915 - [MLIR][Presburger] Implement getDomainSet and getRangeSet for PresburgerRelation   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 86c4dfa - [mlir][gpu] Add GPU target attribute interface.   Fabian Mora
• [Mlir-commits] [mlir] 876a480 - [mlir][Conversion] Add type converter parameter to ConvertToLLVMPatternInterface   Matthias Springer
• [Mlir-commits] [mlir] 878950b - [mlir][bufferization] Simplify `getBufferType`   Matthias Springer
• [Mlir-commits] [mlir] 87a1421 - Fix MLIR build failure: error: no member named 'getValue' in 'mlir::OptionalParseResult'   Mehdi Amini
• [Mlir-commits] [mlir] 87f2dee - [mlir][bufferization] Add DeallocationSimplification pass   Martin Erhart
• [Mlir-commits] [mlir] 888717e - [mlir][transform] Enable gpu-to-nvvm via conversion patterns driven by TD   Nicolas Vasilache
• [Mlir-commits] [mlir] 88fbccd - Revert "Fix canonicalizer to copy the entire GreedyRewriteConfig instead of selected fields"   Mehdi Amini
• [Mlir-commits] [mlir] 895c4ac - [mlir][Target][LLVM] Adds an utility class for serializing operations to binary strings.   Fabian Mora
• [Mlir-commits] [mlir] 8a77917 - [Printing] Add flag to not print resources.   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 8ae074b - [mlir][gpu] Add the Select Object compilation attribute.   Fabian Mora
• [Mlir-commits] [mlir] 8b134d0 - [mlir][transform][python] Add AnyValueType to bindings.   Ingo Müller
• [Mlir-commits] [mlir] 8b68cec - [mlir][tensor] Add producer fusion for tensor.pack op.   Hanhan Wang
• [Mlir-commits] [mlir] 8c8aecd - [mlir][sparse] Supporting (non)uniqueness in SparseTensorStorage::lexDiff.   Peiming Liu
• [Mlir-commits] [mlir] 8cacabe - [mlir] Add an integration test for masked vectorisation for linalg.matmul   Andrzej Warzynski
• [Mlir-commits] [mlir] 8ce23b8 - [mlir][ArmSME] Add vector to tile intrinsics   Cullen Rhodes
• [Mlir-commits] [mlir] 8cf814e - [openacc] Add declare op to data construct operations list   Razvan Lupusoru
• [Mlir-commits] [mlir] 8dcb672 - [mlir][python] Make DenseBoolArrayAttr.get work with list of bools.   Ingo Müller
• [Mlir-commits] [mlir] 8dd6c7a - [mlir][llvm] Improve intrinsic import/export tests   Tobias Gysi
• [Mlir-commits] [mlir] 8dd8c4a - [mlir][Transforms] Inliner: Extra checks for unstructured control flow   Matthias Springer
• [Mlir-commits] [mlir] 8e946fe - Revert "[mlir][complex] Convert complex.abs to arith with fastmath flag"   Muhammad Omair Javaid
• [Mlir-commits] [mlir] 90b2556 - [mlir][NFC] Expose the `CFGToSCFInterface` for the `ControlFlowToSCF` pass   Markus Böck
• [Mlir-commits] [mlir] 920c461 - [mlir][Transform] Add support to drive conversions of func to LLVM with TD   Nicolas Vasilache
• [Mlir-commits] [mlir] 9223306 - [mlir][python bindings] generate all the enums   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 93228cf - [mlir] Apply ClangTidy fix (NFC)   Adrian Kuegel
• [Mlir-commits] [mlir] 935ba83 - add empty line in the end of the td files   Yijia Gu
• [Mlir-commits] [mlir] 950f094 - [mlir][bufferization] Factor out bufferization.dealloc lowering into separate pass   Martin Erhart
• [Mlir-commits] [mlir] 95a6c50 - [mlir][sparse][gpu] add set csr pointers, remove estimate op, fix bugs   Aart Bik
• [Mlir-commits] [mlir] 96e1914 - [mlir][sparse] fix crash when generating convolution kernel with sparse input in DCCD format.   Peiming Liu
• [Mlir-commits] [mlir] 977cb4f - [mlir][linalg][transform] PadOp: Add option to generate linalg.copy copy_back op   Matthias Springer
• [Mlir-commits] [mlir] 97da414 - [mlir][ArmSME] Lower loads/stores of (.Q) 128-bit tiles to intrinsics   Benjamin Maxwell
• [Mlir-commits] [mlir] 9aaf007 - [SCF][Transform] Add transform.loop.fuse_sibling   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 9bd19bb - [mlir][tensor] Fix bug in utility `tensor::isCastLikeExtractSliceOp`   Christopher Bate
• [Mlir-commits] [mlir] 9cb7250 - [mlir][sparse][gpu] fixed some whitespace   Aart Bik
• [Mlir-commits] [mlir] 9cf4280 - Fix typos in TargetLLVMIR.md   Mehdi Amini
• [Mlir-commits] [mlir] 9d927d0 - [mlir][Linalg] Add an end-to-end test for scalable vectorisation   Andrzej Warzynski
• [Mlir-commits] [mlir] 9dfd3c3 - [mlir][sparse][gpu] reduce boilerplate class declarations   Aart Bik
• [Mlir-commits] [mlir] 9e1b825 - [mlir][ArmSME] Add conversion from ArmSME to SCF to materialize loops   Cullen Rhodes
• [Mlir-commits] [mlir] 9ef6cff - [tests] Fix gpu-to-cubin.mlir (NFC)   Anlun Xu
• [Mlir-commits] [mlir] 9f37c21 - [mlir][vector] Fold shape_cast of broadcast with same element count   Lei Zhang
• [Mlir-commits] [mlir] 9fa7b9e - [mlir][gpu] Add target attribute to GPU modules.   Fabian Mora
• [Mlir-commits] [mlir] a011943 - [mlir][gpu] Support arith.extf in subgroup MMA elementwise ops   Lei Zhang
• [Mlir-commits] [mlir] a02ad6c - [mlir][bufferization] Generalize getAliasingOpResults to getAliasingValues   Matthias Springer
• [Mlir-commits] [mlir] a03ea35 - [mlir][LLVM] Introduce verfier for call debug locations   Christian Ulmann
• [Mlir-commits] [mlir] a173137 - [mlir][linalg][transform] Return copy_back op from PadOp.   Ingo Müller
• [Mlir-commits] [mlir] a1f04b7 - [mlir][Interfaces][NFC] Use camel case for offset/size/stride accessors   Matthias Springer
• [Mlir-commits] [mlir] a3cd2ee - [mlir][nvgpu] Add a nvgpu.rewrite_copy_as_tma transform operation.   Nicolas Vasilache
• [Mlir-commits] [mlir] a470df3 - [mlir][linalg][transform][python] Extend mix-in for Vectorize   Ingo Müller
• [Mlir-commits] [mlir] a4d87e3 - [mlir][ArmSME] Calculate correct tile mask when lowering arm_sme.zero   Benjamin Maxwell
• [Mlir-commits] [mlir] a5925ee - [MLIR][NVVM] Fix register mapping in `wgmma.mma_async`   Guray Ozen
• [Mlir-commits] [mlir] a5b584d - [mlir][lsp] Add parser support for tracking alias definitions and uses   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] a623689 - [mlir][bufferization] Check for invalid pass flags instead of failed assertions   Matthias Springer
• [Mlir-commits] [mlir] a63db3f - [mlir][gpu] Modifies `gpu.launch_func` to allow lowering it after gpu-to-llvm.   Fabian Mora
• [Mlir-commits] [mlir] a67072e - [MLIR][Presburger] Fix incorrect doc comment and add const   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] a7cdea7 - [mlir][gpu] Add documentation for the new GPU compilation mechanism   Fabian Mora
• [Mlir-commits] [mlir] a7d80c5 - [MLIR][python bindings] add vendor gpu dialects   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] a7fdb90 - [mlir][linalg][transform][python] Add mix-in for MapCopyToThreadsOp.   Mehdi Amini
• [Mlir-commits] [mlir] a8599ac - [mlir][UBToLLVM] Do not arbitrarily restrict input types   Markus Böck
• [Mlir-commits] [mlir] a88732d - [mlir][bufferization][NFC] Extract block signature bufferization into separate function   Matthias Springer
• [Mlir-commits] [mlir] a8daefe - Lock the MLIR TypeConverter caches management to make it thread-safe (NFC)   Mehdi Amini
• [Mlir-commits] [mlir] aa33561 - Fix ODS verifier emission for DerivedAttr when Properties are enabled   Mehdi Amini
• [Mlir-commits] [mlir] acc572f - [mlir][nfc] Avoid implicit casting VectorType -> Type   Andrzej Warzynski
• [Mlir-commits] [mlir] ad83164 - Revert "Fix MLIR build failure: error: no member named 'getValue' in 'mlir::OptionalParseResult'"   Mehdi Amini
• [Mlir-commits] [mlir] ada6256 - [mlir][sparse] cleanup of CMake files   Aart Bik
• [Mlir-commits] [mlir] adea7e7 - [mlir][emitc] Add comparison operation   Marius Brehler
• [Mlir-commits] [mlir] b13248f - Revert "[mlir][gpu] Add DecomposeMemrefsPass"   Ivan Butygin
• [Mlir-commits] [mlir] b160442 - Revert "[mlir][VectorOps] Use SCF for vector.print and allow scalable vectors"   Benjamin Maxwell
• [Mlir-commits] [mlir] b26bb30 - Revert "[mlir] Use a type for representing branch points in `RegionBranchOpInterface`"   Markus Böck
• [Mlir-commits] [mlir] b2d1de2 - [mlir][Interfaces][NFC] Delete dead code from OffsetSizeAndStrideOpInterface   Matthias Springer
• [Mlir-commits] [mlir] b328396 - [mlir][openacc][NFC] Remove duplicated test   Valentin Clement
• [Mlir-commits] [mlir] b43068e - [mlir][gpu] Update GPU translation to accept binaries.   Fabian Mora
• [Mlir-commits] [mlir] b448fe0 - [mlir][NFC] Split OpBase.td into multiple smaller units   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] b454ecc - [mlir] Apply ClangTidy fix (NFC)   Adrian Kuegel
• [Mlir-commits] [mlir] b49bb7b - [MLIR][PDL] Add support for representing and lowering negated constraints   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] b6bab6d - [MLIR][transforms] Fix `cloneInto()` error in `RemoveDeadValues` pass   Srishti Srivastava
• [Mlir-commits] [mlir] b7fcf51 - [OpenMP][OpenMPIRBuilder] Add kernel launch codegen to emitTargetCall   Jan Sjodin
• [Mlir-commits] [mlir] b808648 - [mlir][LLVM] Delay debug intrinsic import to ensure dominance   Christian Ulmann
• [Mlir-commits] [mlir] b86d3cb - [mlir][sparse] complete various FIXMEs in sparse support lib   Aart Bik
• [Mlir-commits] [mlir] b90d6b2 - [mlir][openacc] Switch deviceType to optional single operand   Valentin Clement
• [Mlir-commits] [mlir] b96f6cf - [MLIR][Math] Add support for f16 in the expansion of math.roundeven   Alexander Shaposhnikov
• [Mlir-commits] [mlir] b9982b2 - [mlir][bufferization] Add rename function to BufferViewFlowAnalysis   Martin Erhart
• [Mlir-commits] [mlir] bb44a6b - [mlir][sparse] migrate more to new surface syntax   Aart Bik
• [Mlir-commits] [mlir] bbce1fc - [mlir] Fix verifier for call debug locations   Valentin Clement
• [Mlir-commits] [mlir] bbf0733 - [mlir][arith] Fold `select` with poison   Markus Böck
• [Mlir-commits] [mlir] bc5a023 - [mlir][sparse] cleanup of pass code   Aart Bik
• [Mlir-commits] [mlir] bc9a375 - Revert "[mlir][Target][LLVM] Adds an utility class for serializing operations to binary strings."   Fabian Mora
• [Mlir-commits] [mlir] bcabaa5 - Add LLVM_MARK_AS_BITMASK_ENUM to HoistingKind enum   Mehdi Amini
• [Mlir-commits] [mlir] bcfdb3e - [mlir][transform] Add apply_conversion_patterns op   Matthias Springer
• [Mlir-commits] [mlir] bd077e9 - Released restriction that prevented implicit dynamic-to-static dimension type cast in TOSA ops.   Jacques Pienaar
• [Mlir-commits] [mlir] be556ee - [mlir][sparse] Fix typos in comments   Yinying Li
• [Mlir-commits] [mlir] beb7ea5 - [mlir][sparse] cleanup of merger header file   Aart Bik
• [Mlir-commits] [mlir] bf24fb8 - [mlir][gpu] Add `gpu.binary` op and `#gpu.object` attribute.   Fabian Mora
• [Mlir-commits] [mlir] bf57c1f - Revert "[tests] Fix gpu-to-cubin.mlir (NFC)"   Mehdi Amini
• [Mlir-commits] [mlir] bf92a76 - [mlir] Apply ClangTidy fixes (NFC)   Adrian Kuegel
• [Mlir-commits] [mlir] bfdc472 - [mlir][Conversion] Implement ConvertToLLVMPatternInterface (2)   Matthias Springer
• [Mlir-commits] [mlir] c171ed4 - [OpenMP] Fix the linkage for kernel environment global variable   Shilei Tian
• [Mlir-commits] [mlir] c4769ef - [mlir][Conversion] Re-submit: Implement ConvertToLLVMPatternInterface (1)   Matthias Springer
• [Mlir-commits] [mlir] c555308 - [mlir][linalg] Add an end-to-end test for linalg.fill to ArmSME   Cullen Rhodes
• [Mlir-commits] [mlir] c5e8fbb - [mlir][bufferization] Add pattern to BufferDeallocationSimplification pass that removes unnecessary retain values   Martin Erhart
• [Mlir-commits] [mlir] c65442b - Fix some missing fully qualified namespaces in MLIR TableGen generator   Mehdi Amini
• [Mlir-commits] [mlir] c730c62 - [mlir] Fix -Wctad-maybe-unsupported in MemRefUtils.cpp (NFC)   Jie Fu
• [Mlir-commits] [mlir] c8aab9b - Add missing libraries dependencies to ConvertToLLVMPass to fix the shared library build (NFC)   Mehdi Amini
• [Mlir-commits] [mlir] c8e0364 - [mlir][Target][LLVM] Adds an utility class for serializing operations to binary strings.   Fabian Mora
• [Mlir-commits] [mlir] ca21398 - [MLIR][Presburger] Implement findSymbolicIntegerLexMin/Max for PresburgerRelation   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] cad2678 - [mlir] Prefer to use empty to check for emptiness (NFC)   Jacques Pienaar
• [Mlir-commits] [mlir] cad4646 - [mlir][sparse] Improve handling of NEW_SYNTAX   wren romano
• [Mlir-commits] [mlir] cb5c0a7 - [OpenMP] Fix MLIR test after updating visibility   Joseph Huber
• [Mlir-commits] [mlir] cc6b8d8 - [mlir][conversion] NFC - Relax convert-cf-to-llvm and finalize-memref-to-llvm to also work on non-builtin module ops   Nicolas Vasilache
• [Mlir-commits] [mlir] ccd7f0f - [mlir][memref][transform][python] Create mix-in for MemRefMultiBufferOp.   Ingo Müller
• [Mlir-commits] [mlir] cce3e8e - [MLIR][NVGPU] Introduction of wgmma.generate.descriptor Op   Guray Ozen
• [Mlir-commits] [mlir] cd7af14 - Fix canonicalizer to copy the entire GreedyRewriteConfig instead of selected fields   Mehdi Amini
• [Mlir-commits] [mlir] ce25459 - [mlir][Conversion] Store const type converter in ConversionPattern   Matthias Springer
• [Mlir-commits] [mlir] cfa82f7 - [mlir][sparse][gpu] introduce flag that controls host to device copy strategies (regular dma default)   Kun Wu
• [Mlir-commits] [mlir] d151aa4 - Fix MLIR build failure: error: no member named 'getValue' in 'mlir::OptionalParseResult'   Mehdi Amini
• [Mlir-commits] [mlir] d22883e - Revert "[MLIR][Math] Add support for f16 in the expansion of math.roundeven"   Alexander Shaposhnikov
• [Mlir-commits] [mlir] d22965f - Reland "[mlir] Add a postprocessing parameter in Pattern"   Jian Cai
• [Mlir-commits] [mlir] d243378 - [mlir][vector] Use dyn_cast in if conditions   Lei Zhang
• [Mlir-commits] [mlir] d26eb82 - [mlir][bufferization] DeallocOp canonicalizer removing memrefs that are never deallocated   Martin Erhart
• [Mlir-commits] [mlir] d2f2ef8 - [MLIR][Linalg] Respect DPS in `lower_unpack`   Lorenzo Chelini
• [Mlir-commits] [mlir] d4bde69 - [mlir][irdl] Introduce a way to define regions   Daniil Dudkin
• [Mlir-commits] [mlir] d4f47f2 - [mlir] Apply ClangTidy fix (NFC)   Adrian Kuegel
• [Mlir-commits] [mlir] d582338 - [mlir][ArmSME] Add -canonicalize to vector to ArmSME test   Cullen Rhodes
• [Mlir-commits] [mlir] d5c2204 - [TableGen] OpInterface inheritance duplicates bases   Andrew Lenharth
• [Mlir-commits] [mlir] d5e6931 - [MLIR][NVVM] Make links for PTX ISA documents   Guray Ozen
• [Mlir-commits] [mlir] d774622 - [mlir][lsp] Register all extensions and TestDynDialect in main.   Ingo Müller
• [Mlir-commits] [mlir] d790a21 - [mlir] Add getArgOperandsMutable method to CallOpInterface   Martin Erhart
• [Mlir-commits] [mlir] d7e26b5 - [mlir][linalg][transform][python] Fix mix-in for MaskedVectorize.   Ingo Müller
• [Mlir-commits] [mlir] d84450b - [mlir][linalg] Canonicalize tensor.extract(linalg.fill)   Lei Zhang
• [Mlir-commits] [mlir] d8ae3a9 - [mlir][sparse] Fix strict weak ordering in sorting   Aart Bik
• [Mlir-commits] [mlir] d923f4c - [mlir][NVVM|ROCDL] Explicitly construct the return type in loadBitcodeFiles in (NVVM|ROCDL)Target   Fabian Mora
• [Mlir-commits] [mlir] da4d191 - [mlir][tosa] operation printing syntax prettification   Eric Kunze
• [Mlir-commits] [mlir] dac19b4 - [mlir][linalg][transform][python] Add mix-in for MaskedVectorize.   Ingo Müller
• [Mlir-commits] [mlir] dad9de0 - [mlir][vector] Improve lowering to LLVM for `minf`, `maxf` reductions   Daniil Dudkin
• [Mlir-commits] [mlir] db11fd8 - [MLIR][NVVM] Change WgmmaMmaSyncOp to WgmmaMmaAsyncOp (NFC)   Guray Ozen
• [Mlir-commits] [mlir] dbf798f - [mlir] Fix generating checks for multiple funcs in generate-test-checks   Benjamin Maxwell
• [Mlir-commits] [mlir] dc3dc97 - Remove the `conversionCallStack` from the MLIR TypeConverter   Mehdi Amini
• [Mlir-commits] [mlir] de3f7e2 - [mlir] Fix infinite recursion in alias initializer   Markus Böck
• [Mlir-commits] [mlir] de72243 - [openmp][mlir] Parallel reduction LLVM IR generation   Ethan Luis McDonough
• [Mlir-commits] [mlir] dea33c8 - [mlir][Transforms] teach CSE about recursive memory effects   Tom Eccles
• [Mlir-commits] [mlir] dfa10ec - [mlir][ArmSME] Extend arm_sme.zero for all types   Andrzej Warzynski
• [Mlir-commits] [mlir] dfa96cf - [mlir][tensor] Fix ReifyRankedShapedTypeOpInterface impl. of reshape ops   Matthias Springer
• [Mlir-commits] [mlir] dfe2942 - [mlir][sparse][gpu] add spgemm operator   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] e015d38 - [mlir][sparse] Pass down constant coefficients of affine index expressions to LoopEmitter.   Peiming Liu
• [Mlir-commits] [mlir] e18672a - [flang][openacc] Add routine info attribute to the function   Valentin Clement
• [Mlir-commits] [mlir] e3373c6 - [mlir][memref] Fix crash in SubViewReturnTypeCanonicalizer   Matthias Springer
• [Mlir-commits] [mlir] e468c60 - Fix canonicalizer to copy the entire GreedyRewriteConfig instead of selected fields   Mehdi Amini
• [Mlir-commits] [mlir] e77e891 - [mlir][test] Refactor SparseTensor CPU integration tests   Andrzej Warzynski
• [Mlir-commits] [mlir] e7aed22 - [mlir] Fix -Wunused-private-field. NFC   Fangrui Song
• [Mlir-commits] [mlir] e7e4ed0 - [mlir][sparse][gpu] only support default algorithm for SpGEMM   Aart Bik
• [Mlir-commits] [mlir] e98e599 - Revert "Foo"   Alex Zinenko
• [Mlir-commits] [mlir] ec5e947 - Fix MSAN error: use of unitialized value when hashing the MLIR pass manager (NFC)   Mehdi Amini
• [Mlir-commits] [mlir] ecc4ef9 - Revert "[mlir][linalg][transform][python] Add mix-in for MapCopyToThreadsOp."   Mehdi Amini
• [Mlir-commits] [mlir] ecfd547 - [mlir] Apply ClangTidy fix (NFC)   Adrian Kuegel
• [Mlir-commits] [mlir] edea31e - [MLIR] fix some copy/paste issues in the doc for Interface examples (NFC)   Mehdi Amini
• [Mlir-commits] [mlir] ef3ab3d - [MLIR] Switch the default for usePropertiesForAttributes (NFC)   Mehdi Amini
• [Mlir-commits] [mlir] f054901 - [mlir][bufferization][transform][python] Add enums to bindings & mixins.   Ingo Müller
• [Mlir-commits] [mlir] f0ceba8 - Revert "[mlir][Conversion] Implement ConvertToLLVMPatternInterface (1)"   Matthias Springer
• [Mlir-commits] [mlir] f20b67a - [Flang][MLIR][OpenMP] Improve device-only function filtering   Sergio Afonso
• [Mlir-commits] [mlir] f36e193 - [mlir][bufferization] Improve `bufferizesToElementwiseAccess`   Matthias Springer
• [Mlir-commits] [mlir] f36e909 - [mlir][VectorOps] Use SCF for vector.print and allow scalable vectors   Benjamin Maxwell
• [Mlir-commits] [mlir] f3b1361 - [mlir] Generate constructor in generic adaptors allowing construction from an op instance   Markus Böck
• [Mlir-commits] [mlir] f40af3b - [MLIR][Presburger] Optimize for union & subtract   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] f4bef78 - Add narrow type emulation pattern for vector.transfer_read   Hanhan Wang
• [Mlir-commits] [mlir] f559e73 - [mlir] Support fast-math friendly constants for identity value   Quentin Colombet
• [Mlir-commits] [mlir] f5b974b - [mlir][sparse] Adding `{Var, DimLvlExpr, DimSpec, LvlSpec, DimLvlMap}::str` methods   Aart Bik
• [Mlir-commits] [mlir] f66e4bd - [mlir][math] Modify math.powf to handle negative bases.   Rob Suderman
• [Mlir-commits] [mlir] f6897c3 - [mlir][MemRef] Bail out for unsupported cases in FoldMemRefAliasOps pass   Hanhan Wang
• [Mlir-commits] [mlir] f745c91 - Revert "[MLIR][Math] Add support for f16 in the expansion of math.roundeven"   Alexander Shaposhnikov
• [Mlir-commits] [mlir] f9070b2 - [mlir][vector] Enable CastAwayElementwiseLeadingOneDim for scalable vec   Andrzej Warzynski
• [Mlir-commits] [mlir] f9d5053 - [mlir][sparse] updating methods to get MLIRContext   wren romano
• [Mlir-commits] [mlir] f9da447 - [mlir][sparse] clean up a few TODOs and layout   Aart Bik
• [Mlir-commits] [mlir] fa6726e - [mlir][sparse] supports sparse_tensor.pack on libgen path   Peiming Liu
• [Mlir-commits] [mlir] fa9c93e - [mlir][sparse] Remove view-based sparse tensor collapse_shape implementation.   Peiming Liu
• [Mlir-commits] [mlir] fbbb8ad - [mlir][gpu] Add passes to attach (NVVM|ROCDL) target attributes to GPU Modules   Fabian Mora
• [Mlir-commits] [mlir] fc0d4d5 - [mlir][tosa] Change axis to I32Attr   Robert Suderman
• [Mlir-commits] [mlir] fcb0294 - Revert "[mlir][conversion] NFC - Relax convert-cf-to-llvm and finalize-memref-to-llvm to also work on non-builtin module ops"   Alex Zinenko
• [Mlir-commits] [mlir] fcfeb1e - [mlir][gpu] Add GPU target support to `gpu-to-llvm`.   Fabian Mora
• [Mlir-commits] [mlir] fdaf2f9 - [mlir][LLVM] Fix export call mapping for calls with a result   Christian Ulmann
• [Mlir-commits] [mlir] fdbe931 - [mlir][sparse] Adding getters/setters to `DimLvlMap`   wren romano
• [Mlir-commits] [mlir] fe355a4 - [MLIR][Math] Add support for f64 in the expansion of math.roundeven   Alexander Shaposhnikov
• [Mlir-commits] [mlir] fe5370d - [mlir] Store segment sizes in std::array   Tobias Gysi
• [Mlir-commits] [mlir] fe8e7e3 - [mlir-linalg-ods-yaml-gen] Fix a bug in getDpsInitsPositionRange   Andrey Turetskiy
• [Mlir-commits] [mlir] fea185d - [mlir][bufferization] Add pattern to BufferDeallocationSimplification pass   Martin Erhart
• [Mlir-commits] [mlir] ff5696c - Document CMake Changes Needed to Generate Attribute Code from TableGen   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] fff1830 - [mlir][bufferization] Run the simple dealloc canonicalization patterns as part of BufferDeallocationSimplification   Martin Erhart

Last message date: Thu Aug 31 23:53:19 PDT 2023
Archived on: Thu Aug 31 23:53:22 PDT 2023

• Messages sorted by: [ thread ] [ author ] [ date ]
• More info on this list...