June 2020 Archives by author

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

Starting: Mon Jun 1 23:18:50 PDT 2020
Ending: Tue Jun 30 22:02:03 PDT 2020
Messages: 265

• [Mlir-commits] [mlir] a09bb6d - Replace dyn_cast<>() with isa<>() when the result isn't used (NFC)   Mehdi Amini
• [Mlir-commits] [mlir] 48c800c - Fix build: TableGen uses `is<T>` instead of `isa<T>` as predicate   Mehdi Amini
• [Mlir-commits] [mlir] a25f5cd - Revert "[MLIR] Lower shape.num_elements -> shape.reduce."   Mehdi Amini
• [Mlir-commits] [mlir] 83d920c - Fix MLIR test: -dump-input-on-failure is no longer a valid option   Mehdi Amini
• [Mlir-commits] [mlir] 51a8227 - Register printer and context CL options with the toyc example   Mehdi Amini
• [Mlir-commits] [mlir] 1cf1486 - Revert "[mlir][spirv] Enhance structure type member decoration handling"   Mehdi Amini
• [Mlir-commits] [mlir] 95371ce - Enable FileCheck -enable-var-scope by default in MLIR test   Mehdi Amini
• [Mlir-commits] [mlir] 6f0ce46 - Revert "[mlir][spirv] Enhance structure type member decoration handling"   Mehdi Amini
• [Mlir-commits] [mlir] a9a21bb - Revert "[mlir] Add support for lowering tanh to LLVMIR."   Mehdi Amini
• [Mlir-commits] [mlir] 1333147 - Make OpOperand constructor private (NFC)   Mehdi Amini
• [Mlir-commits] [mlir] bd970ef - Fix MLIR test after 1d33c09f220e: matrix intrinsics have "nocapture" on some arguments (NFC)   Mehdi Amini
• [Mlir-commits] [mlir] e81bf67 - [MLIR] Modify HasParent trait to allow one of several op's as a parent   Mehdi Amini
• [Mlir-commits] [mlir] bc14c77 - Fix `check-mlir` target when the host target isn't configured   Mehdi Amini
• [Mlir-commits] [mlir] 20d0ab6 - Fix warning caused by TableGen verifier predicate (NFC)   Mehdi Amini
• [Mlir-commits] [mlir] 5ac47c3 - Move explicit template class specialization out of the class to fix gcc builds (NFC)   Mehdi Amini
• [Mlir-commits] [mlir] 5a675f0 - [Mlir] Add assembly format for `shape.mul`.   Alexander Belyaev
• [Mlir-commits] [mlir] 04fb2b6 - [Mlir] Implement printer, parser, verifier and builder for shape.reduce.   Alexander Belyaev
• [Mlir-commits] [mlir] 50f68c1 - [mlir] Add verifier for `shape.yield`.   Alexander Belyaev
• [Mlir-commits] [mlir] e80617d - [MLIR] Lower shape.num_elements -> shape.reduce.   Alexander Belyaev
• [Mlir-commits] [mlir] 250dcf6 - Revert "Revert "[MLIR] Lower shape.num_elements -> shape.reduce.""   Alexander Belyaev
• [Mlir-commits] [mlir] 80be54c - [mlir] Lower Shape binary ops (AddOp, MulOp) to Standard.   Alexander Belyaev
• [Mlir-commits] [mlir] 0f8d40f - [mlir][linalg] Add a builder for `linalg.(indexed_)generic`.   Alexander Belyaev
• [Mlir-commits] [mlir] 0b781db - [mlir] Add new builders to linalg.reshape.   Alexander Belyaev
• [Mlir-commits] [mlir] 9d1e0dd - [mlir][linalg] Fix the type (indicies->indices).   Alexander Belyaev
• [Mlir-commits] [mlir] 4e19ba4 - [mlir][shape] Add assemblyFormat for `shape.add`.   Alexander Belyaev
• [Mlir-commits] [mlir] e9ac792 - [mlir] Fix some of the warnings in MLIR code.   Alexander Belyaev
• [Mlir-commits] [mlir] cd32044 - [mlir][shape] Lower Shape `ConstSizeOp` to Standard `ConstantOp`.   Alexander Belyaev
• [Mlir-commits] [mlir] 3813f24 - [mlir][shape] Add a pattern to rewrite `shape.reduce` as `scf.for`.   Alexander Belyaev
• [Mlir-commits] [mlir] 71c1080 - [mlir][shape] Fix the comment in ShapeToStandard.cpp.   Alexander Belyaev
• [Mlir-commits] [mlir] 7a9258e - [mlir][shape] Add a func to populate ShapeToShape patterns.   Alexander Belyaev
• [Mlir-commits] [mlir] dfafba3 - [mlir][linalg] Add callback-based builders for `linalg.(indexed_)generic`.   Alexander Belyaev
• [Mlir-commits] [mlir] 7808bf8 - NFC: Make sure function arguments have the same name in declaration and definition   Kirill Bobyrev
• [Mlir-commits] [mlir] 9b72b47 - Revert "[mlir][Linalg] Retire C++ MatmulOp in favor of a linalg-ods-gen'd op."   Kirill Bobyrev
• [Mlir-commits] [mlir] 0f6999a - [MLIR] Update linalg.conv lowering to use affine load in the absence of padding   Uday Bondhugula
• [Mlir-commits] [mlir] 136d78c - [MLIR][NFC] Update vim syntax file   Uday Bondhugula
• [Mlir-commits] [mlir] 7965dd7 - [MLIR] Fix memref region compute for 0-d memref accesses   Uday Bondhugula
• [Mlir-commits] [mlir] aec5344 - [MLIR] Fix affine loop fusion private memref alloc   Uday Bondhugula
• [Mlir-commits] [mlir] 2b5d177 - [MLIR][Affine-loop-fusion] Fix a bug in affine-loop-fusion pass when there are non-affine operations   Uday Bondhugula
• [Mlir-commits] [mlir] 8a418e5 - [mlir][Affine] Enable fusion of loops with vector loads/stores   Diego Caballero
• [Mlir-commits] [mlir] 5c990d6 - [mlir] Add support for bf16 to StandardToLLVM conversion   Diego Caballero
• [Mlir-commits] [mlir] 7d59f49 - [mlir] Fix representation of BF16 constants   Diego Caballero
• [Mlir-commits] [mlir] 2e7a084 - [mlir][Affine] Revisit fusion candidates after successful fusion   Diego Caballero
• [Mlir-commits] [mlir] a728878 - [mlir][EDSC] Add divis and diviu and vector.extractelement   Diego Caballero
• [Mlir-commits] [mlir] 6d15451 - [mlir] Make PassManager.h self-contained   Kadir Cetinkaya
• [Mlir-commits] [mlir] 6cd2320 - [MLIR][NFC] Inline lambda to workaround gcc 9.1, 9.2 bug   Kiran Chandramohan
• [Mlir-commits] [mlir] 2fd6403 - [mlir][gpu] Introduce mlir-rocm-runner.   Wen-Heng Chung
• [Mlir-commits] [mlir] 47073cc - [mlir][mlir-rocm-runner] Detect HIP version and AMD ISA version.   Wen-Heng Chung
• [Mlir-commits] [mlir] 603b974 - [mlir][gpu] Fix logic error in D79508 computing number of private attributions.   Wen-Heng Chung
• [Mlir-commits] [mlir] 7bfcb91 - Use python3 in generate-test-checks.py.   Wen-Heng Chung
• [Mlir-commits] [mlir] b7c4912 - [mlir][mlir-rocm-runner] Remove compile-time warning. NFC.   Wen-Heng Chung
• [Mlir-commits] [mlir] 6bb4fc9 - Fix a corner case in vector.shape_cast when the trailing dimensions are of size 1.   Wen-Heng Chung
• [Mlir-commits] [mlir] 7b226fd - [MLIR] Add an Op util which returns its name with the dialect stripped.   Lucy Fox
• [Mlir-commits] [mlir] 1db1a08 - [mlir] Avoid pontentially ambiguous class name   Jean-Michel Gorius
• [Mlir-commits] [mlir] 05b4ff0 - [mlir-tblgen] Use fully qualified names in generated code files   Jean-Michel Gorius
• [Mlir-commits] [mlir] 3713314 - [MLIR] Shape to standard dialect lowering   Frederik Gossen
• [Mlir-commits] [mlir] 24edbdf - [MLIR] Clean up `shape` to `std` lowering   Frederik Gossen
• [Mlir-commits] [mlir] 867bc41 - [MLIR] Add type conversion for `shape.shape`   Frederik Gossen
• [Mlir-commits] [mlir] 970bb4a - [MLIR] Add `to/from_extent_tensor` lowering to the standard dialect   Frederik Gossen
• [Mlir-commits] [mlir] 2159141 - [MLIR][Shape] Add support for `OpAsmInterface` in `shape.const_size`   Frederik Gossen
• [Mlir-commits] [mlir] e4184c8 - [MLIR][Shape] Make dimension an operand of `get_extent`   Frederik Gossen
• [Mlir-commits] [mlir] 904f91d - [MLIR][Standard] Make the `dim` operation index an operand.   Frederik Gossen
• [Mlir-commits] [mlir] 6196c37 - [MLIR] Add missing traits and assembly format to `shape.from/to_extent_tensor`   Frederik Gossen
• [Mlir-commits] [mlir] 361f664 - [MLIR][Standard] Add documentation for `std.dim` and fix test cases   Frederik Gossen
• [Mlir-commits] [mlir] a8c186c - [MLIR][Standard] Simplify complex operand unpacking   Frederik Gossen
• [Mlir-commits] [mlir] 0990f1a - [MLIR][Standard] Lower `std.dim` with dynamic dimension operand to LLVM   Frederik Gossen
• [Mlir-commits] [mlir] 6f2943f - [MLIR][Standard] Fix use of `dyn_cast_or_null`   Frederik Gossen
• [Mlir-commits] [mlir] eaf4913 - [MLIR][Shape] Realize `shape` to `std` lowering with declarative patterns   Frederik Gossen
• [Mlir-commits] [mlir] 945d20f - [MLIR][Shape] Lower `size_to_index` and `index_to_size` with declarative rules   Frederik Gossen
• [Mlir-commits] [mlir] ac3e5c4 - [MLIR][Shape] Lower `shape.shape_of` to standard dialect   Frederik Gossen
• [Mlir-commits] [mlir] 2c06199 - [MLIR][Shape] Add `shape.rank` operation   Frederik Gossen
• [Mlir-commits] [mlir] 8146952 - [MLIR][Shape] Add constant folding to `shape.rank`   Frederik Gossen
• [Mlir-commits] [mlir] 7bca97d - [MLIR][Shape] Add canonicalization pattern for `shape.rank`   Frederik Gossen
• [Mlir-commits] [mlir] 24debf5 - [MLIR][Shape] Lower `shape.rank`   Frederik Gossen
• [Mlir-commits] [mlir] e34b883 - [MLIR][Shape] Lower `shape_of` for unranked tensors   Frederik Gossen
• [Mlir-commits] [mlir] 5a7cd5d - [MLIR][Shape] Fix ambiguous symbol   Frederik Gossen
• [Mlir-commits] [mlir] bf2a4f3 - [MLIR][Shape] Canonicalize subsequent `index_to_size` and `size_to_index`   Frederik Gossen
• [Mlir-commits] [mlir] 66e0f66 - [MLIR][Shape] Canonicalize subsequent `size_to_index` and `index_to_size`   Frederik Gossen
• [Mlir-commits] [mlir] 76d72c9 - [MLIR][Shape] Lower `shape.get_extent` to `std.dim` when possible   Frederik Gossen
• [Mlir-commits] [mlir] d876e32 - [MLIR][Shape] Lower `shape.get_extent` to `extract_element` when possible   Frederik Gossen
• [Mlir-commits] [mlir] 8577a09 - [MLIR][Shape] Fix lowering of `shape.get_extent`   Frederik Gossen
• [Mlir-commits] [mlir] 2ff6fad - Revert "[mlir] make the bitwidth of device side index computations configurable"   Tobias Gysi
• [Mlir-commits] [mlir] cd73081 - [mlir] parallel loop tiling optimization for loops with static bounds   Tobias Gysi
• [Mlir-commits] [mlir] 48f1d4f - [mlir] parallel loop canonicalization   Tobias Gysi
• [Mlir-commits] [mlir] 652a796 - [mlir] fix off-by-one error in collapseParallelLoops   Tobias Gysi
• [Mlir-commits] [mlir] 6d18c20 - [Matrix] Update load/store intrinsics.   Florian Hahn
• [Mlir-commits] [mlir] 2c8afe1 - [mlir][gpu] Add support for f16 when lowering to nvvm intrinsics   Stephan Herhut
• [Mlir-commits] [mlir] ba9e65f - [mlir][doc] Fix typos in tutorial chapters   Stephan Herhut
• [Mlir-commits] [mlir] 1e60678 - [MLIR] Fix parallel loop tiling.   Stephan Herhut
• [Mlir-commits] [mlir] 2416e28 - [mlir] Add support for alignment annotations to the LLVM dialect to LLVM translation.   Stephan Herhut
• [Mlir-commits] [mlir] 4bcd08e - [mlir] Add for loop specialization   Stephan Herhut
• [Mlir-commits] [mlir] 67ecd7e - [mlir] Clean up NVVM intrinsics definitions a little.   Stephan Herhut
• [Mlir-commits] [mlir] 6f5da84 - [mlir] Extended BufferPlacement to support nested region control flow.   Stephan Herhut
• [Mlir-commits] [mlir] 7099d8e - [mlir] Fix case in MLIRGPUtoNVVMTransforms   Stephan Herhut
• [Mlir-commits] [mlir] 0f43fce - [mlir] Fix case in MLIRGPUtoGPURuntimeTransforms   Stephan Herhut
• [Mlir-commits] [mlir] 2eaadfc - [NFC] Use llvm::hasSingleElement() in place of .size() == 1   Rahul Joshi
• [Mlir-commits] [mlir] 3d316eb - [MLIR] Move SymbolOpInterface::isPublic() and friends to SymbolOpInterface Trait.   Rahul Joshi
• [Mlir-commits] [mlir] d150662 - [MLIR][NFC] Eliminate .getBlocks() when not needed   Rahul Joshi
• [Mlir-commits] [mlir] c20875a - [MLIR][NFC] Adopt hasNItems() for SizedRegion predicate   Rahul Joshi
• [Mlir-commits] [mlir] e7f7137 - [MLIR] [NFC] Add new line and empty line before printing modified loop   Rahul Joshi
• [Mlir-commits] [mlir] 60f914e - [NFC][MLIR] Undo anonymous namespace change from https://reviews.llvm.org/D82417   Rahul Joshi
• [Mlir-commits] [mlir] d891d73 - [MLIR][NFC] Adopt variadic isa<>   Rahul Joshi
• [Mlir-commits] [mlir] ee394e6 - [MLIR] Add variadic isa<> for Type, Value, and Attribute   Rahul Joshi
• [Mlir-commits] [mlir] ff4c510 - [mlir] Extended BufferPlacement to support more sophisticated scenarios in which   Marcel Koester
• [Mlir-commits] [mlir] 33879aa - [mlir] Fixed GCC compile issues and linking problems using SHARED_LIBS.   Marcel Koester
• [Mlir-commits] [mlir] 48cd9d9 - [Support] Use outs() in ToolOutputFile   Pavel Labath
• [Mlir-commits] [mlir] 10bd67c - Install the MLIRTableGen static library.   Stella Laurenzo
• [Mlir-commits] [mlir] 99d6e05 - [lit] Improve naming of test result categories   Julian Lettner
• [Mlir-commits] [mlir] 5048933 - [mlir] Added the dialect inliner to the SCF dialect   Feng Liu
• [Mlir-commits] [mlir] 6984623 - [MLIR] expose applyCmpPredicate   Stephen Neuendorffer
• [Mlir-commits] [mlir] d3ead06 - [JitRunner] add support for i32 and i64 output   Stephen Neuendorffer
• [Mlir-commits] [mlir] 8dcf89c - [MLIR][cmake] use add_mlir_interface() wherever possible   Stephen Neuendorffer
• [Mlir-commits] [mlir] 635cde6 - [mlir] Provide defaults to make enabling dumping simpler   Jacques Pienaar
• [Mlir-commits] [mlir] 5b454b9 - [mlir] Remove unneeded inference trait/fns   Jacques Pienaar
• [Mlir-commits] [mlir] b0921f6 - [mlir] Add verify method to adaptor   Jacques Pienaar
• [Mlir-commits] [mlir] 92cb0ce - [mlir] Change to re-enable cuda-runner tests   Jacques Pienaar
• [Mlir-commits] [mlir] 48c28d5 - [mlir] Unranked memref type has no rank   Jacques Pienaar
• [Mlir-commits] [mlir] 1c189d7 - [mlir] Add number of operands verification for shape.assuming_all operation   Jacques Pienaar
• [Mlir-commits] [mlir] 7f13d51 - [mlir] Remove Broadcastable ODS trait   Jacques Pienaar
• [Mlir-commits] [mlir] 8472ae1 - [mlir] Add additional header   Jacques Pienaar
• [Mlir-commits] [mlir] 3dbb667 - [mlir] Mark CastOp class's shape constraint   Jacques Pienaar
• [Mlir-commits] [mlir] e303a19 - [mlir] Add Adaptor alias   Jacques Pienaar
• [Mlir-commits] [mlir] 2d2c73c - [mlir] Remove OperandAdaptor   Jacques Pienaar
• [Mlir-commits] [mlir] 2b41bc5 - [mlir][shape] Update test case to new op asm format   Jacques Pienaar
• [Mlir-commits] [mlir] 7c59120 - [mlir][ods] Look through OpVariable for type constraint   Jacques Pienaar
• [Mlir-commits] [mlir] 0164119 - [MLIR] Remove TableGen redundant calls to native calls when creating new operations in DRR TableGen files   Jacques Pienaar
• [Mlir-commits] [mlir] ada0d41 - [mlir][ods] Allow filtering of ops   Jacques Pienaar
• [Mlir-commits] [mlir] 71b9d89 - [ods] Update Operator to record Arg->[Attr|Operand]Index mapping   Jacques Pienaar
• [Mlir-commits] [mlir] 1c3e38d - [mlir] Add a shape op that returns a constant witness   Tres Popp
• [Mlir-commits] [mlir] 6b3a5bf - [mlir] Folding of shape.assuming_all   Tres Popp
• [Mlir-commits] [mlir] 4a255bb - [mlir] Add folding for shape.any   Tres Popp
• [Mlir-commits] [mlir] 6aab709 - [mlir] Canonicalization and folding of shape.cstr_broadcastable   Tres Popp
• [Mlir-commits] [mlir] 0a554e6 - [mlir] Folding and canonicalization of shape.cstr_eq   Tres Popp
• [Mlir-commits] [mlir] 655e08c - [mlir] Canonicalization of shape.assuming   Tres Popp
• [Mlir-commits] [mlir] 4ffe6bd - [mlir] NFC formatting cleanup.   Tres Popp
• [Mlir-commits] [mlir] cf72027 - [mlir] Move attr-dict to end of Shape dialect ops   Tres Popp
• [Mlir-commits] [mlir] 12e31f6 - Revert "[mlir] Folding and canonicalization of shape.cstr_eq"   Tres Popp
• [Mlir-commits] [mlir] 4261b02 - Revert "[mlir] Canonicalization and folding of shape.cstr_broadcastable"   Tres Popp
• [Mlir-commits] [mlir] 5d77bd7 - [mlir] Restructure Shape dialect's CMakeLists.   Tres Popp
• [Mlir-commits] [mlir] d216f98 - Revert "Revert "[mlir] Canonicalization and folding of shape.cstr_broadcastable""   Tres Popp
• [Mlir-commits] [mlir] 68a8336 - Revert "Revert "[mlir] Folding and canonicalization of shape.cstr_eq""   Tres Popp
• [Mlir-commits] [mlir] 3324598 - [mlir] Add a pass to remove all shape.cstr_ and assuming_ ops.   Tres Popp
• [Mlir-commits] [mlir] bbe79e2 - [mlir][spirv] Fix encoding of cooperative matrix type to match SPIRV spec   Thomas Raoux
• [Mlir-commits] [mlir] 81dd3a4 - [mlir][spirv] Fix coop matrix getExtension   Thomas Raoux
• [Mlir-commits] [mlir] 661235e - [mlir][gpu] Add subgroup Id/Size/Num to GPU dialect   Thomas Raoux
• [Mlir-commits] [mlir] 25cbfa0 - [mlir][spirv] Allow mixed type cooperative matrix muladd   Thomas Raoux
• [Mlir-commits] [mlir] afd43a7 - [mlir][vulkan-runner] add support for memref of i8, i16 types in vulkan runner   Thomas Raoux
• [Mlir-commits] [mlir] e4bc08f - [mlir] Allow vector.contract to have mixed types operands   Thomas Raoux
• [Mlir-commits] [mlir] 670455c - [mlir][spirv] Legalize subviewop when used with vector transfer   Thomas Raoux
• [Mlir-commits] [mlir] b885b1b - [mlir] Fix gcc build break due to previous commit   Thomas Raoux
• [Mlir-commits] [mlir] 0e76c0a - [mlir][vulkan-runner] Make vulkan runner use GPU device memory   Thomas Raoux
• [Mlir-commits] [mlir] 446b901 - [mlir] Fix case in MLIRGPUtoVulkanTransforms   Thomas Raoux
• [Mlir-commits] [mlir] c0cd1f1 - [mlir] Refactor BoolAttr to be a special case of IntegerAttr   River Riddle
• [Mlir-commits] [mlir] 5111468 - [mlir][NFC] Split Parser into several different files.   River Riddle
• [Mlir-commits] [mlir] 3d56f16 - [mlir][StandardOps] Updated IndexCastOp to support tensor<index> cast   River Riddle
• [Mlir-commits] [mlir] a0dd5e8 - [MLIR] Print function name when ReturnOp verification fails   River Riddle
• [Mlir-commits] [mlir] 685d7ee - [MLIR] Add ArrayAttr::empty()   River Riddle
• [Mlir-commits] [mlir] 4759351 - [MLIR] Emit debug message if inlining fails   River Riddle
• [Mlir-commits] [mlir] 0e36074 - [mlir][DialectConversion] Cache type conversions and add a few useful helpers   River Riddle
• [Mlir-commits] [mlir] 552ef9f - [mlir][DialectConversion] Add overload of addDynamicallyLegalDialect to support lambdas   River Riddle
• [Mlir-commits] [mlir] eddf4dc - Fix SourceMgrDiagnosticHandler::convertLocToSMLoc for unknown line/column scenerio.   River Riddle
• [Mlir-commits] [mlir] f4ef77c - [mlir][Inliner] Properly handle callgraph node deletion   River Riddle
• [Mlir-commits] [mlir] 3e98fbf - [mlir] Refactor RewritePatternMatcher into a new PatternApplicator class.   River Riddle
• [Mlir-commits] [mlir] 80d7ac3 - [mlir] Allow for patterns to match any root kind.   River Riddle
• [Mlir-commits] [mlir] 8d67d18 - [mlir][DialectConversion] Refactor how block argument types get converted   River Riddle
• [Mlir-commits] [mlir] 7d1452d - [mlir] Refactor OpInterface internals to be faster and factor out common bits.   River Riddle
• [Mlir-commits] [mlir] e6a343e - [mlir][DialectConversion][NFC] Add comment blocks and organize a bit of the code   River Riddle
• [Mlir-commits] [mlir] 6b9a706 - Add front/back accessors to indexed_accessor_range.   River Riddle
• [Mlir-commits] [mlir] f625f52 - [mlir] Remove the default template parameters from AttrBase and TypeBase.   River Riddle
• [Mlir-commits] [mlir] 25b3806 - [MLIR] Rework generate-test-checks.py to attach CHECK lines to the source (test) file.   Tim Shen
• [Mlir-commits] [mlir] a6150de - [MLIR] Remove generated spaces at eof for generate-test-checks.py.   Tim Shen
• [Mlir-commits] [mlir] b877f33 - [MLIR] Add documentation for generate-check-lines.py   Tim Shen
• [Mlir-commits] [mlir] 5cba1c6 - [SVE] Remove calls to VectorType::getNumElements from mlir   Christopher Tetreault
• [Mlir-commits] [mlir] 3f6a35e - [mlir] Introduce CallOp converter for buffer placement   Ehsan Toosi
• [Mlir-commits] [mlir] 4214031 - [mlir] Introduce allowMemrefFunctionResults for the helper operation converters of buffer placement   Ehsan Toosi
• [Mlir-commits] [mlir] 245b299 - [mlir][OpenMP] Add custom parser and pretty printer for parallel construct   David Truby
• [Mlir-commits] [mlir] 7de4587 - [mlir] NFC - Add AffineMinMaxOpBase getDim/SymbolOperands   Nicolas Vasilache
• [Mlir-commits] [mlir] e349fb7 - [mlir][Linalg] NFC - Make markers use Identifier instead of StringRef   Nicolas Vasilache
• [Mlir-commits] [mlir] 3463d98 - [mlir][Linalg] Add a hoistViewAllocOps helper function   Nicolas Vasilache
• [Mlir-commits] [mlir] 6953cf6 - [mlir][Linalg] Add a hoistRedundantVectorTransfers helper function   Nicolas Vasilache
• [Mlir-commits] [mlir] 6b0dfd7 - [mlir][Linalg] Add missing CMake dependency on SCFTransforms   Nicolas Vasilache
• [Mlir-commits] [mlir] 247e185 - [mlir][Vector] Move temporary alloc to top of the function alloca when lowering vector_transfers   Nicolas Vasilache
• [Mlir-commits] [mlir] 38c407b - [mlir][SCF] Add single iteration scf.for promotion to the FuncOp level helper.   Nicolas Vasilache
• [Mlir-commits] [mlir] 56ce65e - [mlir][Linalg] NFC - Cleanup debug, address post-commit review.   Nicolas Vasilache
• [Mlir-commits] [mlir] b56bf30 - [mlir][Vector] Add folding of memref_cast into vector_transfer ops   Nicolas Vasilache
• [Mlir-commits] [mlir] eb7db87 - [mlir][test][CPU] Reduce the size of mlir-cpu-runner-tests   Nicolas Vasilache
• [Mlir-commits] [mlir] b6c8854 - [mlir] Fix spurious f64 -> f16 change in CPU runner test   Nicolas Vasilache
• [Mlir-commits] [mlir] b54a4d0 - [mlir][Linalg] NFC - Make useFullTileBuffersByDefault option take a boolean.   Nicolas Vasilache
• [Mlir-commits] [mlir] 8c6c49f - [mlir][Linalg] Retire C++ MatmulOp in favor of a linalg-ods-gen'd op.   Nicolas Vasilache
• [Mlir-commits] [mlir] eae76fa - [mlir][Linalg] Retire C++ MatmulOp in favor of a linalg-ods-gen'd op.   Nicolas Vasilache
• [Mlir-commits] [mlir] cc11ced - [mlir][Linalg] Add support for fusion between indexed_generic ops and generic ops on tensors.   Hanhan Wang
• [Mlir-commits] [mlir] 27fca57 - [mlir][Linalg] Add support for fusion between indexed_generic ops and tensor_reshape ops   Hanhan Wang
• [Mlir-commits] [mlir] 0b025d2 - [mlir][StandardToSPIRV] Handle i1 case for lowering std.zexti to SPIR-V.   Hanhan Wang
• [Mlir-commits] [mlir] 32c757e - [mlir] Add support for lowering tanh to LLVMIR.   Hanhan Wang
• [Mlir-commits] [mlir] 487ca07 - [mlir][NFC] Fix file comments.   Hanhan Wang
• [Mlir-commits] [mlir] 9cb1029 - [mlir] Add support for lowering tanh to LLVMIR.   Hanhan Wang
• [Mlir-commits] [mlir] 809bcf4 - [mlir] Fix a doc link in LinalgBase.td   Hanhan Wang
• [Mlir-commits] [mlir] 915e55c - [mlir][spirv] Add support for matrix type   Lei Zhang
• [Mlir-commits] [mlir] cc2349e - [MLIR][SPIRV] Support flat, location, and noperspective decorations   Lei Zhang
• [Mlir-commits] [mlir] a6d6b0a - [MLIR][Toy] Fix a few typos in the comments/docs.   Lei Zhang
• [Mlir-commits] [mlir] fda5192 - [MLIR][SPIRVToLLVM] Add skeleton for SPIR-V to LLVM dialect conversion   Lei Zhang
• [Mlir-commits] [mlir] d93d8fc - [MLIR][SPIRVToLLVM] Implemented conversion for arithmetic ops and 3 bitwise ops.   Lei Zhang
• [Mlir-commits] [mlir] 4b7aa6c - [mlir][spirv] Enhance structure type member decoration handling   Lei Zhang
• [Mlir-commits] [mlir] fc148a4 - [MLIR][SPIRVToLLVM] Added conversion for SPIR-V comparison ops   Lei Zhang
• [Mlir-commits] [mlir] 5d74df5 - [mlir][spirv] Enhance structure type member decoration handling   Lei Zhang
• [Mlir-commits] [mlir] d7e6f11 - [mlir][spirv] Enhance structure type member decoration handling   Lei Zhang
• [Mlir-commits] [mlir] cf2b4d5 - [MLIR][SPIRVToLLVM] Implemented shift conversion pattern   Lei Zhang
• [Mlir-commits] [mlir] cd93906 - [mlir] Fix case in MLIRGPUtoSPIRVTransforms   Lei Zhang
• [Mlir-commits] [mlir] 771b788 - [MLIR][SPIRVToLLVM] Support cast ops, some logical ops, UModOp   Lei Zhang
• [Mlir-commits] [mlir] 02022ff - [mlir][spirv] Enhance AccessChainOp index type handling   Lei Zhang
• [Mlir-commits] [mlir] a4dc613 - [MLIR][SPIRVToLLVM] Implementation of spv.func conversion, and return ops   Lei Zhang
• [Mlir-commits] [mlir] 4837562 - [MLIR][SPIRV] Extend automation script to generate coverage report.   Lei Zhang
• [Mlir-commits] [mlir] a2edbd8 - [MLIR][LLVMDialect] Added bitreverse and ctpop intrinsics   Lei Zhang
• [Mlir-commits] [mlir] 2bcb620 - [mlir][spirv] Add TransposeOp   Lei Zhang
• [Mlir-commits] [mlir] b5c24c2 - [MLIR][SPIRVToLLVM] Implementation of SPIR-V module conversion pattern   Lei Zhang
• [Mlir-commits] [mlir] d6485ed - [MLIR][SPIRV] Add support for OpCopyMemory.   Lei Zhang
• [Mlir-commits] [mlir] a2004c3 - [mlir][spirv] Add RewriteInserts pass.   Lei Zhang
• [Mlir-commits] [mlir] c8295de - [MLIR][SPIRVToLLVM] Conversion for bitrverse and bitcount ops   Lei Zhang
• [Mlir-commits] [mlir] cd1bc5c - [MLIR][SPIRVToLLVM] Convert bitwise and logical not   Lei Zhang
• [Mlir-commits] [mlir] 3819789 - [MLIR][SPIRVToLLVM] Added Bitcast conversion pattern   Lei Zhang
• [Mlir-commits] [mlir] 195d857 - [mlir] post-commit review fixes   Alex Zinenko
• [Mlir-commits] [mlir] b596ecd - [mlir] Toy tutorial: avoid erasing and then re-creating loop terminators   Alex Zinenko
• [Mlir-commits] [mlir] eb8edd8 - [mlir] SCFToGPUPass: fix macros referring to LOOPS to use SCF instead   Alex Zinenko
• [Mlir-commits] [mlir] 5c5dafc - [mlir] support materialization for 1-1 type conversions   Alex Zinenko
• [Mlir-commits] [mlir] 6163fa7 - [mlir] DialectConversion: remove vtable from TypeConverter   Alex Zinenko
• [Mlir-commits] [mlir] 2beacda - [mlir][Linalg][Doc] Fix of misleading example in Property 2   Alex Zinenko
• [Mlir-commits] [mlir] 36150c3 - [mlir] Affine symbols: do not expect AffineScope to always exist   Alex Zinenko
• [Mlir-commits] [mlir] 3f5bd53 - [mlir] Introduce callback-based builders for AffineForOp   Alex Zinenko
• [Mlir-commits] [mlir] 3adced3 - [mlir] Introduce callback-based builders to SCF Parallel and Reduce ops   Alex Zinenko
• [Mlir-commits] [mlir] b4bc72a - [mlir] refactor Linalg LoopNestBuilder to use common infra   Alex Zinenko
• [Mlir-commits] [mlir] d14d96b - [mlir] [Vector] Add missing edsc intrinsics.   Alex Zinenko
• [Mlir-commits] [mlir] e31e8f1 - [MLIR][Linalg] Retire C++ MatvecOp in favor of a linalg-ods-gen'd op   Alex Zinenko
• [Mlir-commits] [mlir] a75e093 - [mlir] Provide OpBuilder-based replacements for edsc::BlockBuilder   Alex Zinenko
• [Mlir-commits] [mlir] 8647a9b - [mlir] Refactor affine loop nest builders   Alex Zinenko
• [Mlir-commits] [mlir] 68628c9 - [mlir] Update Toy tutorial to use callback-based loop constructors   Alex Zinenko
• [Mlir-commits] [mlir] 5c5ec96 - [mlir] Remove EDSC LoopBuilder, derived classes and related functionality   Alex Zinenko
• [Mlir-commits] [mlir] 0af2262 - [mlir] Remove EDSC BlockBuilder, BlockHandle and related functionality   Alex Zinenko
• [Mlir-commits] [mlir] 63b7e1e - [mlir] Remove EDSC NestedBuilder   Alex Zinenko
• [Mlir-commits] [mlir] d10b1a3 - [mlir] make the bitwidth of device side index computations configurable   Alex Zinenko
• [Mlir-commits] [mlir] cde2dc2 - [mlir] Fix linalg.generic matmul example in the doc   Alex Zinenko
• [Mlir-commits] [mlir] 6323065 - [mlir] support returning unranked memrefs   Alex Zinenko
• [Mlir-commits] [mlir] 8304ab5 - [mlir] Avoid creating local OpBuilders in Standard-to-LLVM conversion   Alex Zinenko
• [Mlir-commits] [mlir] fbeceb9 - [mlir] Modernize LLVM dialect rountrip test   Alex Zinenko
• [Mlir-commits] [mlir] 42de94f - [mlir] do not hardcode the name of the undefined function in the error message   Alex Zinenko
• [Mlir-commits] [mlir] 25055a4 - [mlir] add unsigned comparison builders to Affine EDSC   Alex Zinenko
• [Mlir-commits] [mlir] 4ab4398 - [mlir] minor tweaks in standard-to-llvm lowering   Alex Zinenko
• [Mlir-commits] [mlir] 2bcd192 - [mlir][SCFToGPU] Remove conversions from scf.for to gpu.launch.   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 6391da9 - [mlir] [VectorOps] Use 'vector.flat_transpose' for 2-D 'vector.tranpose'   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] c19fae5 - [mlir] [VectorOps] Add missing comments to CreateMaskOp lowering   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 1e45b55 - [mlir] [VectorOps] Handle 'vector.shape_cast' lowering for all cases   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 2abad34 - [mlir][rocdl] Adding vector to ROCDL dialect lowering   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] eedd8fe - [mlir][rocdl] Fixing breakage of dim operator from 904f91db   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 91801a7 - [mlir] [integration-test] [VectorOps] Start an integration test directory for MLIR   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 8d73ab8 - [mlir] [integration_test] Make integration tests default OFF   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 462e3cc - [mlir][StandardDialect] Add some folding for operations in standard dialect.   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 9b22b29 - [mlir] [VectorOps] Add create mask integration tests   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 55d53d4 - [mlir][spirv] Add MatrixTimesScalar operation   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 8a82bc3 - [mlir] NFC: Fix link in traits documentation   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] c9eeeb3 - [mlir] [VectorOps] remove print_i1 from runtime support library   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 01277bc - [mlir] [integration-test] [LLVMIR] Add reduction intrinsic tests   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 0d82ab7 - [mlir] [VectorOps] Improve vector.constant_mask lowering   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 55d09df - [mlir] [VectorOps] Improve vector.create_mask lowering   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] ba69019 - [mlir] [integration-test] Let target check-mlir imply target check-mlir-integration too   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] ceb1b32 - [mlir] [VectorOps] Add the ability to mark FP reductions with "reassociate" attribute   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 4a80f19 - [mlir] [VectorOps] Extend vector reduction integration test with reassoc=true cases.   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 63b3933 - [mlir] [VectorOps] Replace zero fma with mult for vector.contract   llvmlistbot at llvm.org

Last message date: Tue Jun 30 22:02:03 PDT 2020
Archived on: Mon Nov 23 06:19:14 PST 2020

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