July 2021 Archives by author

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

Starting: Thu Jul 1 00:22:32 PDT 2021
Ending: Sat Jul 31 13:42:13 PDT 2021
Messages: 259

• [Mlir-commits] [mlir] 6bbbd7b - Update MLIRContext to allow injecting an external ThreadPool (NFC)   Mehdi Amini
• [Mlir-commits] [mlir] 4525d52 - Revert "[mlir][Vector] NFC - Compress vector to outerproduct lowering."   Mehdi Amini
• [Mlir-commits] [mlir] 38451fa - Revert "[mlir][sparse] Add Merger unit tests"   Mehdi Amini
• [Mlir-commits] [mlir] f4f11ee - [mlir][NFC] Switched `interfaces` to a private member of SSANameState.   Mehdi Amini
• [Mlir-commits] [mlir] 2c0f179 - [mlir] Added OpPrintingFlags to AsmState and SSANameState.   Mehdi Amini
• [Mlir-commits] [mlir] ebbe149 - [mlir] Gated calls to getAsm{Result, BlockArgument}Names on whether printing ops in generic form.   Mehdi Amini
• [Mlir-commits] [mlir] 5801885 - Defend early against operation created without a registered dialect   Mehdi Amini
• [Mlir-commits] [mlir] 3e25ea7 - Revert "Defend early against operation created without a registered dialect"   Mehdi Amini
• [Mlir-commits] [mlir] 0f9e645 - Defend early against operation created without a registered dialect   Mehdi Amini
• [Mlir-commits] [mlir] 20113d6 - Fix mismatch between the provisioning of asyncExecutors and the actual thread count currently in the context (NFC)   Mehdi Amini
• [Mlir-commits] [mlir] 68ec4aa - Add `lli` as dependency of MLIR integration tests   Mehdi Amini
• [Mlir-commits] [mlir] a664c14 - [mlir][LLVM] Revert bareptr calling convention handling as an argument materialization.   Mehdi Amini
• [Mlir-commits] [mlir] 5a8a159 - Add verifier for insert/extract element/value on type match between container and inserted/extracted value, and fix vector.shuffle lowering   Mehdi Amini
• [Mlir-commits] [mlir] ebe817f - Define the namespace for the Affine dialect in ODS (NFC)   Mehdi Amini
• [Mlir-commits] [mlir] aaacd8c - Add llvm::equal convenient wrapper for ranges around std::equal   Mehdi Amini
• [Mlir-commits] [mlir] b349d4c - Emit strong definition for TypeID storage in Op/Type/Attributes definition   Mehdi Amini
• [Mlir-commits] [mlir] 1cc29f0 - Revert "Emit strong definition for TypeID storage in Op/Type/Attributes definition"   Mehdi Amini
• [Mlir-commits] [mlir] 6cba963 - Add some missing CMake dependencies between MLIR dialects (NFC)   Mehdi Amini
• [Mlir-commits] [mlir] 660a569 - Emit strong definition for TypeID storage in Op/Type/Attributes definition   Mehdi Amini
• [Mlir-commits] [mlir] 6e9e4b5 - Revert "Emit strong definition for TypeID storage in Op/Type/Attributes definition"   Mehdi Amini
• [Mlir-commits] [mlir] 4bb0ad2 - Emit strong definition for TypeID storage in Op/Type/Attributes definition   Mehdi Amini
• [Mlir-commits] [mlir] 0be5d1a - Implement recursive support into OperationEquivalence::isEquivalentTo()   Mehdi Amini
• [Mlir-commits] [mlir] 0082764 - Revert "Add workaround for false positive in -Wfree-nonheap-object"   Christopher Di Bella
• [Mlir-commits] [mlir] 6412a13 - [mlir] Move common reshapeops-related code to ReshapeOpsUtils.h.   Alexander Belyaev
• [Mlir-commits] [mlir] d659527 - [mlir] Use indices instead of affine maps when composing 2 reshape ops.   Alexander Belyaev
• [Mlir-commits] [mlir] 46ef86b - [mlir] Move linalg::Expand/CollapseShapeOp to memref dialect.   Alexander Belyaev
• [Mlir-commits] [mlir] 2994ad3 - [mlir] Remove unused functions in LinalgOps.cpp   Alexander Belyaev
• [Mlir-commits] [mlir] 3b03d9b - [mlir] Introduce `linalg.tiled_yield` terminator for `linalg.tiled_loop`.   Alexander Belyaev
• [Mlir-commits] [mlir] 58ddeba - Revert "[mlir] Introduce `linalg.tiled_yield` terminator for `linalg.tiled_loop`."   Alexander Belyaev
• [Mlir-commits] [mlir] 266a741 - [mlir][sparse] move tensor expression builder into Merger utility   Aart Bik
• [Mlir-commits] [mlir] b8a021d - [mlir][sparse] support for negation and subtractions   Aart Bik
• [Mlir-commits] [mlir] 8cf60e6 - [mlir][sparse] updated setter/getter comments   Aart Bik
• [Mlir-commits] [mlir] 622eb16 - [mlir][sparse] add restrictive versions of division support   Aart Bik
• [Mlir-commits] [mlir] 45b3cfe - [mlir][sparse] add support for AND and OR operations   Aart Bik
• [Mlir-commits] [mlir] 7039dfc - [mlir][memref] adjust integration tests to new lowering passes   Aart Bik
• [Mlir-commits] [mlir] 123e8df - [mlir][sparse] add support for std unary operations   Aart Bik
• [Mlir-commits] [mlir] 04bddb6 - [mlir][crunner] fix bug in memref copy for rank 0   Aart Bik
• [Mlir-commits] [mlir] 68ac2e5 - [mlir][sparse] replace linalg.copy with memref.copy   Aart Bik
• [Mlir-commits] [mlir] e6e79b3 - [mlir][sparse] remove linalg-to-loops from integration tests   Aart Bik
• [Mlir-commits] [mlir] 2b6e433 - [mlir][sparse] add shift ops support   Aart Bik
• [Mlir-commits] [mlir] afc760e - [mlir][sparse] add int64 storage type to sparse tensor runtime support library   Aart Bik
• [Mlir-commits] [mlir] 8fe6597 - [mlir][sparse] minor cleanup of Merger   Aart Bik
• [Mlir-commits] [mlir] c2415d6 - [mlir][sparse] fixed bug in verification   Aart Bik
• [Mlir-commits] [mlir] 2b013a6 - [mlir][sparse] use proper type alias for filename ptr   Aart Bik
• [Mlir-commits] [mlir] 1d77bb9 - [mlir][sparse] template the memory resident coordinate scheme storage   Aart Bik
• [Mlir-commits] [mlir] 160399c - [mlir][sparse] move comments from cpp files into dialect doc   Aart Bik
• [Mlir-commits] [mlir] 697ea09 - [mlir][sparse] add sparse tensor type conversion operation   Aart Bik
• [Mlir-commits] [mlir] 1def257 - PR51018: Remove explicit conversions from SmallString to StringRef to future-proof against C++23   David Blaikie
• [Mlir-commits] [mlir] 715137d - [MLIR] Fix memref get constant bound size and shape method   Uday Bondhugula
• [Mlir-commits] [mlir] 0c29f45 - [MLIR] Fix dialect conversion cancelRootUpdate   Uday Bondhugula
• [Mlir-commits] [mlir] 11d88c4 - [MLIR][NFC] Move normalizeAffine methods to Affine utils   Uday Bondhugula
• [Mlir-commits] [mlir] 4acf380 - [MLIR] Split out GPU ops library from Transforms   Uday Bondhugula
• [Mlir-commits] [mlir] 0c1a773 - [MLIR] Simplify affine.if having yield values and trivial conditions   Uday Bondhugula
• [Mlir-commits] [mlir] fc01faf - [MLIR][GPU][NFC] Fix documentation for wmma matrix load/store ops   Uday Bondhugula
• [Mlir-commits] [mlir] edfcfa6 - [MLIR][NFC] Improve doc comment and delete stale comment   Uday Bondhugula
• [Mlir-commits] [mlir] 7932d21 - [MLIR] Introduce a new rewrite driver to simplify supplied list of ops   Uday Bondhugula
• [Mlir-commits] [mlir] 104fad9 - [MLIR] Add folder for zero trip count affine.for   Uday Bondhugula
• [Mlir-commits] [mlir] 795e726 - [MLIR] Fix affine.for empty loop body folder   Uday Bondhugula
• [Mlir-commits] [mlir] a218627 - [mlir][affine-loop-fusion] Fix a bug that AffineIfOp prevents fusion of the other loops   Uday Bondhugula
• [Mlir-commits] [mlir] bf6c46d - [MLIR] NFC Clean up doc comments on memref replacement utility   Uday Bondhugula
• [Mlir-commits] [mlir] 4ff440b - [mlir] Change custom syntax of emitc.include op to resemble C   Marius Brehler
• [Mlir-commits] [mlir] 96e3fb2 - [mlir] Unbreak building mlir-reduce   Marius Brehler
• [Mlir-commits] [mlir] 49d840c - [mlir] Improve description of interface options   Marius Brehler
• [Mlir-commits] [mlir] 14078ae - [mlir][OpAsmParser] Add parseString method   Markus Böck
• [Mlir-commits] [mlir] a96911c - [mlir] Escape strings of opaque attributes   Markus Böck
• [Mlir-commits] [mlir] 3e6d2cb - [mlir] Fully qualify types and expressions in Interfaces   Markus Böck
• [Mlir-commits] [mlir] 8a7b0da - [mlir] Fully qualify MemoryEffects   Markus Böck
• [Mlir-commits] [mlir] a006af5 - [llvm] Add enum iteration to Sequence   Guillaume Chatelet
• [Mlir-commits] [mlir] 2c47b88 - Revert "[llvm] Add enum iteration to Sequence"   Guillaume Chatelet
• [Mlir-commits] [mlir] d6da02d - [llvm] Add enum iteration to Sequence   Guillaume Chatelet
• [Mlir-commits] [mlir] 0c164ea - [MLIR][CAPI] On MINGW don't link against libMLIR   Valentin Churavy
• [Mlir-commits] [mlir] 5664c5e - [MLIR] [Python] Add `owner` to PyValue and fix its parent reference   John Demme
• [Mlir-commits] [mlir] b4c93ec - [MLIR] [Python ODS] Use @builtins.property for cases where 'property' is already defined   John Demme
• [Mlir-commits] [mlir] db9df43 - [mlir-tblgen] Avoid ODS verifier duplication   Chia-hung Duan
• [Mlir-commits] [mlir] 1a001de - [mlir-reduce] Improve diagnostic message and clean build dependency   Chia-hung Duan
• [Mlir-commits] [mlir] ba913b8 - [mlir-reduce] Fix the memory leak and recycle unused modules.   Chia-hung Duan
• [Mlir-commits] [mlir] 70eb3bf - [mlir-reduce] Fix the grammer in the doc   Chia-hung Duan
• [Mlir-commits] [mlir] 9bdf1ab - [mlir-tblgen] Slightly improve the diagnostic message in pattern match   Chia-hung Duan
• [Mlir-commits] [mlir] b4001ae - [mlir-tblgen] Fix failed matching when binds same operand of an op in different depth   Chia-hung Duan
• [Mlir-commits] [mlir] d7314b3 - [mlir-tblgen] Support binding multi-results of NativeCodeCall   Chia-hung Duan
• [Mlir-commits] [mlir] 6eb2ffb - Fix a couple regression tests I missed updating in 2a284782   Eli Friedman
• [Mlir-commits] [mlir] ed1f149 - [MLIR][StandardToLLVM] Move `copyUnrankedDescriptors` to pattern   Frederik Gossen
• [Mlir-commits] [mlir] 9c90725 - [MLIR] Fix documentation of the `ExecutionEngine` in the toy tutorial example   Frederik Gossen
• [Mlir-commits] [mlir] 226f925 - [mlir][linalg][python] Update integration of OpDSL doc (NFC).   Tobias Gysi
• [Mlir-commits] [mlir] 8eb4b3e - [CMake][MLIR][Linalg] Adding variable to specify tablegen file dependencies.   Tobias Gysi
• [Mlir-commits] [mlir] 3b95400 - [mlir][linalg][python] Add max operation in OpDSL   Tobias Gysi
• [Mlir-commits] [mlir] 6944f7d - [mlir][linalg][python] Introduce python integration test folder.   Tobias Gysi
• [Mlir-commits] [mlir] f239026 - [mlir][linalg][python] Add min operation in OpDSL.   Tobias Gysi
• [Mlir-commits] [mlir] 511af1b - [mlir][linalg] Tighter StructuredOp Verification.   Tobias Gysi
• [Mlir-commits] [mlir] 84354b2 - [mlir][linalg] Remove GenericOpBase.   Tobias Gysi
• [Mlir-commits] [mlir] abfa950 - [mlir][linalg][python] Add exp and log to the OpDSL.   Tobias Gysi
• [Mlir-commits] [mlir] b4e843b - [mlir][linalg][python] Add auto-generated file warning (NFC).   Tobias Gysi
• [Mlir-commits] [mlir] 3f8f292 - [mlir][linalg] Set explicit insertion point in pad_tensor patterns.   Tobias Gysi
• [Mlir-commits] [mlir] 87656a3 - [mlir][linalg] Fold TensorCast into PadTensorOp.   Tobias Gysi
• [Mlir-commits] [mlir] 3396377 - [linalg] Add TensorDimOp to list of ops known by bufferization.   Tobias Gysi
• [Mlir-commits] [mlir] 06d2fb5 - [mlir][Linalg] Fix a missing copy when source of insert_slice is not inplace.   Tobias Gysi
• [Mlir-commits] [mlir] deebf18 - [mlir][linalg] Add pooling_nchw_max, conv_2d_nchw as yaml ops.   Tobias Gysi
• [Mlir-commits] [mlir] ca0d244 - [mlir][linalg] Introduce a separate EraseIdentityCopyOp Pattern.   Tobias Gysi
• [Mlir-commits] [mlir] 09635dc - [mlir][linalg] Specialize LinalgOp canonicalization patterns (NFC).   Tobias Gysi
• [Mlir-commits] [mlir] 2a342c7 - [mlir][linalg] Format bufferization debug print outs (NFC).   Tobias Gysi
• [Mlir-commits] [mlir] eda4640 - [mlir][memref] Clarify the documentation for memref.clone [NFC]   Stephan Herhut
• [Mlir-commits] [mlir] 53e5a60 - [NFC] Fix some comments and only look at terminators when looking for ReturnLike ops   Rahul Joshi
• [Mlir-commits] [mlir] 0cc2346 - [MLIR][NFC] Minor cleanup for BufferDeallocation pass.   Rahul Joshi
• [Mlir-commits] [mlir] f8d3755 - [MLIR][memref] Fix findDealloc() to handle > 1 dealloc for the given alloc.   Rahul Joshi
• [Mlir-commits] [mlir] 17de7ed - [MLIR][NFC] Minor cleanup in liveness.   Rahul Joshi
• [Mlir-commits] [mlir] 58aa388 - [MLIR][SCF][NFC] Fix typo in documentation of scf.while   Rahul Joshi
• [Mlir-commits] [mlir] 86778e8 - [MLIR][NFC] Rework some comments.   Rahul Joshi
• [Mlir-commits] [mlir] 0425332 - [mlir] Added new RegionBranchTerminatorOpInterface and adapted uses of hasTrait<ReturnLike>.   Marcel Koester
• [Mlir-commits] [mlir] ce857d3 - [mlir][async] Remove unused variable. NFC.   Benjamin Kramer
• [Mlir-commits] [mlir] e27c700 - [mlir] Restore markUnknownOpDynamicallyLegal to call isDynamicallyLegal by default   Benjamin Kramer
• [Mlir-commits] [mlir] 8c63c24 - [mlir] Fix typo s/applyPermuationMap/applyPermutationMap/   Benjamin Kramer
• [Mlir-commits] [mlir] 1c9c2c9 - [mlir] Remove the default isDynamicallyLegal hook   Benjamin Kramer
• [Mlir-commits] [mlir] d81a843 - [mlir] Put back virtual ~ConversionTarget(), some users started relying on it   Benjamin Kramer
• [Mlir-commits] [mlir] 791ddb7 - Add LogOp to Complex dialect.   Adrian Kuegel
• [Mlir-commits] [mlir] 380fa71 - [mlir] Add LogOp lowering from Complex dialect to Standard/Math dialect.   Adrian Kuegel
• [Mlir-commits] [mlir] bf17ee1 - Add MulOp lowering from Complex dialect to Standard/Math dialect.   Adrian Kuegel
• [Mlir-commits] [mlir] 6e80e3b - Add Log1pOp to complex dialect.   Adrian Kuegel
• [Mlir-commits] [mlir] ffe6a58 - [mlir][nvvm]: Add math::Exp2Op lowering to NVVM.   Adrian Kuegel
• [Mlir-commits] [mlir] 74b8880 - [mlir][rocdl] Add math::Exp2Op lowering to ROCDL   Adrian Kuegel
• [Mlir-commits] [mlir] fb978f0 - [mlir][Complex]: Add lowerings for AddOp and SubOp from Complex dialect to   Adrian Kuegel
• [Mlir-commits] [mlir] 3d25fa2 - Exclude pybind11 2.7.0 from MLIR python requirements.   Stella Laurenzo
• [Mlir-commits] [mlir] 2607209 - Remove libMLIRPublicAPI DSO.   Stella Laurenzo
• [Mlir-commits] [mlir] 310c949 - Re-engineer MLIR python build support.   Stella Laurenzo
• [Mlir-commits] [mlir] dad10a9 - NFC: Adapt operation.py to builtin operation print format changes.   Stella Laurenzo
• [Mlir-commits] [mlir] 0cdf491 - Break apart the MLIR ExecutionEngine from core python module.   Stella Laurenzo
• [Mlir-commits] [mlir] 7e2174c - NFC: Add missing import to integration test.   Stella Laurenzo
• [Mlir-commits] [mlir] 5b2e7f5 - [MLIR][python] Export CAPI headers.   Stella Laurenzo
• [Mlir-commits] [mlir] cf36ab1 - [MLIR][Python] Use DEST_PREFIX when installing.   Stella Laurenzo
• [Mlir-commits] [mlir] 1de7a17 - [MLIR][python] Disable SONAME on extensions.   Stella Laurenzo
• [Mlir-commits] [mlir] 108a320 - [mlir][spirv] Add support for GLSL FMix   Weiwei Li
• [Mlir-commits] [mlir] 9955c65 - [NFC][MLIR][std] Clean up ArithmeticCastOps   Geoffrey Martin-Noble
• [Mlir-commits] [mlir] e86fe36 - [MLIR] Allow Affine scalar replacement to handle inner operations   William S. Moses
• [Mlir-commits] [mlir] eaf22ba - [MLIR] Provide lowering of std switch to llvm switch   William S. Moses
• [Mlir-commits] [mlir] 9a11c70 - [SCF] Handle lowering of Execute region to Standard CFG   William S. Moses
• [Mlir-commits] [mlir] c605dfc - [MLIR] FlatAffineConstraints: Use Matrix objects to store the constraints   Arjun P
• [Mlir-commits] [mlir] eacbd7d - [MLIR] AffineStructures: resolve clang-tidy warnings [NFC]   Arjun P
• [Mlir-commits] [mlir] 35d4593 - Add C API files for the LLVM dialect   Jacques Pienaar
• [Mlir-commits] [mlir] 51cbe4e - [mlir] Fix broadcasting check with 1 values   Jacques Pienaar
• [Mlir-commits] [mlir] 8a2720d - Add more types to the LLVM dialect C API   Jacques Pienaar
• [Mlir-commits] [mlir] 4b897de - [mlir][ods] Add nested OpTrait   Jacques Pienaar
• [Mlir-commits] [mlir] ec9767e - [mlir] Use OpTraitList to define InferTensorType. NFC   Jacques Pienaar
• [Mlir-commits] [mlir] c030ba2 - [mlir] Add alias for input to shaped type op interface   Jacques Pienaar
• [Mlir-commits] [mlir] ee7242c - [mlir] Update to use ValueShapeRange (NFC)   Jacques Pienaar
• [Mlir-commits] [mlir] a5b889d - [mlir] Also update inferReturnTensorTypes (NFC)   Jacques Pienaar
• [Mlir-commits] [mlir] edffb97 - [mlir] Fix comment typos   Jacques Pienaar
• [Mlir-commits] [mlir] d425f58 - [mlir] Make ValueShapeRange a new class   Jacques Pienaar
• [Mlir-commits] [mlir] fabc171 - [IRBuilder] Add type argument to CreateMaskedLoad/Gather   Nikita Popov
• [Mlir-commits] [mlir] 6ac3287 - [Attributes] Replace doesAttrKindHaveArgument() (NFC)   Nikita Popov
• [Mlir-commits] [mlir] ffe9473 - [ExecutionEngine] Fix GEP type   Nikita Popov
• [Mlir-commits] [mlir] 32627f4 - [mlir] Handle unused variable when assertions are disabled.   Tres Popp
• [Mlir-commits] [mlir] 539437e - [mlir] split type conversion to two lines for GCC's sake   Tres Popp
• [Mlir-commits] [mlir] ddd8482 - [PDL] Remove RewriteEndOp and mark RewriteOp as NoTerminator   River Riddle
• [Mlir-commits] [mlir] e90a0d6 - [mlir] Add a FailureOr copy constructor from a FailureOr of a convertible type.   River Riddle
• [Mlir-commits] [mlir] 6b4ce5f - [PDL] Fix the builders for OperationOp and PatternOp   River Riddle
• [Mlir-commits] [mlir] 2f7511c - [PDL] Mark PatternOp as SingleBlock   River Riddle
• [Mlir-commits] [mlir] f8479d9 - [mlir] Set the namespace of the BuiltinDialect to 'builtin'   River Riddle
• [Mlir-commits] [mlir] 3e59064 - [vscode-mlir] Update package.json in preparation for publishing   River Riddle
• [Mlir-commits] [mlir] 03b2d1a - [mlir-vscode] Create a proper output channel for the MLIRContext   River Riddle
• [Mlir-commits] [mlir] 634b086 - [vscode-mlir] Fix the package repo url.   River Riddle
• [Mlir-commits] [mlir] 8066f22 - [MLIR] Add argument insertion helpers for FunctionLike   Fabian Schuiki
• [Mlir-commits] [mlir] da289a1 - [mlir] Allow conversion to LLVM for ElementsAttr's with size 0   Sean Silva
• [Mlir-commits] [mlir] 7c35aae - Mark TensorDialect legal and PadTensor op illegal   Sean Silva
• [Mlir-commits] [mlir] 4569c14 - Refactor TensorExp parameters into a union   Gus Smith
• [Mlir-commits] [mlir] 0d0cff3 - [mlir][sparse] Add Merger unit tests   Gus Smith
• [Mlir-commits] [mlir] 4084334 - [mlir][sparse] Add Merger unit tests (with gcc5 build fix)   Gus Smith
• [Mlir-commits] [mlir] bcf6f64 - [mlir] Add workaround for false positive in -Wfree-nonheap-object   Fangrui Song
• [Mlir-commits] [mlir] f2026f5 - [mlir] Replace LLVM_ATTRIBUTE_NORETURN with C++11 [[noreturn]]   Fangrui Song
• [Mlir-commits] [mlir] e895a67 - [mlir] Move BufferizeDimOp to Tensor/Transforms/Bufferize.cpp   Matthias Springer
• [Mlir-commits] [mlir] 2c115ec - [mlir][NFC] MemRef cleanup: Remove helper functions   Matthias Springer
• [Mlir-commits] [mlir] b70dde5 - [mlir][linalg] Fix typo in ExtractSliceOfPadTensorSwapPattern   Matthias Springer
• [Mlir-commits] [mlir] 3469a8e - [mlir][linalg][NFC] Factor out tile generation in makeTiledShapes   Matthias Springer
• [Mlir-commits] [mlir] 5da010a - [mlir][linalg] Add optional output operand to PadTensorOp   Matthias Springer
• [Mlir-commits] [mlir] d624c1b - [mlir][NFC] Move asOpFoldResult helper functions to StaticValueUtils   Matthias Springer
• [Mlir-commits] [mlir] 4064b6a - [mlir][linalg] Tile PadTensorOp   Matthias Springer
• [Mlir-commits] [mlir] ffb1392 - [mlir][linalg] Fix Windows build   Matthias Springer
• [Mlir-commits] [mlir] 318ce4a - [mlir][linalg] Improve codegen of ExtractSliceOfPadTensorSwapPattern   Matthias Springer
• [Mlir-commits] [mlir] a0e0201 - [mlir][linalg] Improve codegen when tiling PadTensor evenly   Matthias Springer
• [Mlir-commits] [mlir] 4a3defa - [mlir][vector] Refactor TransferReadToVectorLoadLowering   Matthias Springer
• [Mlir-commits] [mlir] d1a9e9a - [mlir][vector] Remove vector.transfer_read/write to LLVM lowering   Matthias Springer
• [Mlir-commits] [mlir] 8dea784 - [mlir][tosa] Add tosa shape inference with InferReturnTypeComponent   Rob Suderman
• [Mlir-commits] [mlir] 65eb402 - [mlir][tosa] Added missing includes on PassDetails.h   Rob Suderman
• [Mlir-commits] [mlir] 6aaaeac - [mlir][tosa] Include TosaDialect as include in tosa PassDetail.h   Rob Suderman
• [Mlir-commits] [mlir] 5a4e776 - [mlir][tosa] Added more shape inference for tosa ops   Rob Suderman
• [Mlir-commits] [mlir] f2832c2 - [mlir][tosa] Added shape propagation for TOSA pool operations.   Rob Suderman
• [Mlir-commits] [mlir] 11dda1a - [mlir][tosa] Added shape inference for tosa convolution operations   Rob Suderman
• [Mlir-commits] [mlir] 6bf0f6a - [mlir][tosa] Add quantized lowering for matmul and fully_connected   Rob Suderman
• [Mlir-commits] [mlir] 40a02fa - [mlir][tosa] Added tosa to linalg lowering to unstrided transposed conv   Rob Suderman
• [Mlir-commits] [mlir] cf8a1f6 - [mlir][tosa] Quantized Conv2DOp lowering to linalg added.   Rob Suderman
• [Mlir-commits] [mlir] 286e7bd - [mlir][tosa] Make tosa MakeBroadcastable pass handle unreanked tensors.   Rob Suderman
• [Mlir-commits] [mlir] 055fa44 - [mlir][tosa] Disable tosa shape verification between operands/results   Rob Suderman
• [Mlir-commits] [mlir] 2d0ba5e - [mlir][tosa] Fix tosa.reshape failures due to implicit broadcasting   Rob Suderman
• [Mlir-commits] [mlir] 0516f49 - Add linalg.mmt4d named op   Ahmed Taei
• [Mlir-commits] [mlir] 8a0d6e8 - Rorder mmt4d iteration domain   Ahmed S. Taei
• [Mlir-commits] [mlir] ada5808 - [mlir] Enable cleanup of single iteration reduction loops being sibling-fused maximally   Sumesh Udayakumaran
• [Mlir-commits] [mlir] 73bea97 - [mlir][Linalg] Add support for CallOp bufferization (10/n)   Nicolas Vasilache
• [Mlir-commits] [mlir] 231b9dd - [mlir][Linalg] Add comprehensive bufferization support for linalg::InitTensor and tensor::CastOp (11/n)   Nicolas Vasilache
• [Mlir-commits] [mlir] 55c274d - [mlir][Linalg] Drop comprehensive-func-bufferize (12/n)   Nicolas Vasilache
• [Mlir-commits] [mlir] ed1681e - [mlir][Linalg] Add comprehensive bufferization support for ConstantOp (13/n)   Nicolas Vasilache
• [Mlir-commits] [mlir] ad0050c - [mlir][Linalg] Add comprehensive bufferization support for TiledLoopOp (14/n)   Nicolas Vasilache
• [Mlir-commits] [mlir] db188ad - [mlir][Vector] NFC - Compress vector to outerproduct lowering.   Nicolas Vasilache
• [Mlir-commits] [mlir] cb5de7c - [mlir][Vector] NFC - Compress vector to outerproduct lowering.   Nicolas Vasilache
• [Mlir-commits] [mlir] 0c4e538 - [mlir][Linalg] Add an InitTensor -> DimOp canonicalization pattern.   Nicolas Vasilache
• [Mlir-commits] [mlir] 9a0af63 - [mlir][Linalg] Proper handling of ForOp and TiledLoopOp   Nicolas Vasilache
• [Mlir-commits] [mlir] 35df2f6 - Refactor GenericPadTensorOpVectorizationPattern   Nicolas Vasilache
• [Mlir-commits] [mlir] d0b282e - [mlir][Linalg] Rewrite PadTensorOp to enable its comprehensive bufferization.   Nicolas Vasilache
• [Mlir-commits] [mlir] 6c0fd4d - [mlir][MemRef] Fix DimOp folding of OffsetSizeAndStrideInterface.   Nicolas Vasilache
• [Mlir-commits] [mlir] 31f8039 - Revert "[mlir][MemRef] Fix DimOp folding of OffsetSizeAndStrideInterface."   Nicolas Vasilache
• [Mlir-commits] [mlir] 4747e1b - [mlir][Linalg] Fix tensor.extract_slice(linalg.init_tensor) canonicalization for rank-reducing extract   Nicolas Vasilache
• [Mlir-commits] [mlir] 6b16683 - [mlir][Linalg] Improve comprehensive bufferization for scf.yield.   Nicolas Vasilache
• [Mlir-commits] [mlir] e312fc4 - [mlir][Linalg] Add layout specification support to bufferization.   Nicolas Vasilache
• [Mlir-commits] [mlir] af55335 - [mlir][Linalg] Better support for bufferizing non-tensor results.   Nicolas Vasilache
• [Mlir-commits] [mlir] 68ae8ba - [mlir][Linalg] Properly specify Linalg attribute.   Nicolas Vasilache
• [Mlir-commits] [mlir] 7b47de7 - [mlir] NFC - Add AffineMap::replace variant with dim/symbol inference   Nicolas Vasilache
• [Mlir-commits] [mlir] df538fd - [mlir][affine] Add single result affine.min/max -> affine.apply canonicalization.   Nicolas Vasilache
• [Mlir-commits] [mlir] 01bdb0f - [mlir][linalg] Improve implementation of hoist padding.   Nicolas Vasilache
• [Mlir-commits] [mlir] 8ed66cb - [mlir][memref] Fix collapsed shape ops memref.cast folding with changed type   Nicolas Vasilache
• [Mlir-commits] [mlir] 14c1450 - [mlir][Vector] Add vector to outerproduct lowering for the [reduction, parallel] case.   Nicolas Vasilache
• [Mlir-commits] [mlir] eb6c63c - [mlir] Fix RankedTensorType::walkImmediateSubElements method   Vladislav Vinogradov
• [Mlir-commits] [mlir] 50529af - [mlir][Linalg] Add 3D pooling named ops to Linalg.   Hanhan Wang
• [Mlir-commits] [mlir] 9c49195 - [mlir][Linalg] Migrate 2D pooling ops from tc definition to yaml definition.   Hanhan Wang
• [Mlir-commits] [mlir] 3de0626 - [mlir][Linalg] Update signatures of the callback functions.   Hanhan Wang
• [Mlir-commits] [mlir] 23326b9 - [mlir][spirv] Fix a few issues in ModuleCombiner   Lei Zhang
• [Mlir-commits] [mlir] 256a83b - [mlir] Fix CMake option for enabling SPIR-V CPU runner   Lei Zhang
• [Mlir-commits] [mlir] 9f5300c - [mlir][spirv] Fix storing bool with proper storage capabilities   Lei Zhang
• [Mlir-commits] [mlir] 0065bd2 - [mlir][spirv] Fix loading bool with proper storage capabilities   Lei Zhang
• [Mlir-commits] [mlir] 233a3a7 - [mlir][spirv] Add support for i8 serialization   Lei Zhang
• [Mlir-commits] [mlir] 9a82482 - [mlir][linalg] Fix pad tensor cast folding with changed type   Yi Zhang
• [Mlir-commits] [mlir] a8b7e56 - [mlir] Set insertion point of vector constant to the top of the vectorized loop body   Amy Zhuang
• [Mlir-commits] [mlir] 6c1f655 - [mlir] Async: special handling for parallel loops with zero iterations   Eugene Zhulenev
• [Mlir-commits] [mlir] d94426d - [mlir] Math: add algebraic simplification patterns to math transforms   Eugene Zhulenev
• [Mlir-commits] [mlir] 6ea22d4 - Optionally eliminate blocking runtime.await calls by converting functions to coroutines.   Eugene Zhulenev
• [Mlir-commits] [mlir] 9a5bc83 - Add an escape-hatch for conversion of funcs with blocking awaits to coroutines.   Eugene Zhulenev
• [Mlir-commits] [mlir] 1c14441 - Refactor AsyncToAsyncRuntime pass to boost understandability.   Eugene Zhulenev
• [Mlir-commits] [mlir] b5d847b - [mlir] factor out common parts of the converstion to the LLVM dialect   Alex Zinenko
• [Mlir-commits] [mlir] 50ad774 - [mlir][CAPI] Export mlirValueEqual in C API   Alex Zinenko
• [Mlir-commits] [mlir] 684dfe8 - [mlir] factor out ConvertToLLVMPattern   Alex Zinenko
• [Mlir-commits] [mlir] 75e5f0a - [mlir] factor memref-to-llvm lowering out of std-to-llvm   Alex Zinenko
• [Mlir-commits] [mlir] d4df382 - [mlir] don't drop undef initializers in translation to LLVM IR   Alex Zinenko
• [Mlir-commits] [mlir] c282d55 - [mlir] add support for reductions in OpenMP WsLoopOp   Alex Zinenko
• [Mlir-commits] [mlir] 26e59cc - [mlir] factor math-to-llvm out of standard-to-llvm   Alex Zinenko
• [Mlir-commits] [mlir] e4b79a5 - [mlir] add an interface to support custom types in LLVM dialect pointers   Alex Zinenko
• [Mlir-commits] [mlir] 881dc34 - [mlir] replace llvm.mlir.cast with unrealized_conversion_cast   Alex Zinenko
• [Mlir-commits] [mlir] a24e020 - [mlir] add missing build dependency   Alex Zinenko
• [Mlir-commits] [mlir] c1f719d - [mlir] harden result type verification in llvm.call   Alex Zinenko
• [Mlir-commits] [mlir] 49f745f - [mlir] run the verifier before translating a module   Alex Zinenko
• [Mlir-commits] [mlir] cdf7b66 - [mlir][Linalg] Fix incorrect logic in deciding when to fuse reshapes by linearization.   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 2910253 - [mlir][vector] Refactor Vector Unrolling and remove Tuple ops   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] ae4cea3 - [mlir] Add support for tensor.extract to comprehensive bufferization   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 6296e10 - [mlir][Vector] Remove Vector TupleOp as it is unused   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] a36e9ee - [mlir][SCF] populateSCFStructuralTypeConversionsAndLegality WhileOp support   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 5994201 - [mlir][Linalg] NFC: Rename FusionOfTensors pass to FusionOfElementwiseOps pass.   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] f6f88e6 - [mlir] Add software pipelining transformation for scf.For op   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 381c3b9 - Dyanamic shape support for memref reassociation reshape ops   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 45cb414 - [mlir] Extend scf pipeling to support loop carried dependencies   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 1dd3797 - [mlir] Fix various issues in TimerImpl.   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 73a9d6d - [mlir][linalg] Fix bug in contraction op vectorization with output perm   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] b7a4649 - [mlir] ConversionTarget legality callbacks refactoring   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] fe7ca1a - [mlir][openacc] Initial translation for DataOp to LLVM IR   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 1e9799e - [mlir][spirv] Fix crash in convert-gpu-to-spirv pass with memrefs with affine maps   llvmlistbot at llvm.org

Last message date: Sat Jul 31 13:42:13 PDT 2021
Archived on: Sat Jul 31 13:42:15 PDT 2021

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