February 2021 Archives by thread

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

Starting: Mon Feb 1 00:03:03 PST 2021
Ending: Sat Feb 27 17:33:12 PST 2021
Messages: 276

• [Mlir-commits] [mlir] d9b953d - [mlir][Linalg] Replace SimplePad with PadTensor in hoist-padding   Hanhan Wang
• [Mlir-commits] [mlir] a4b7d52 - [mlir] Fix missing null termination in cuLinkAddData argument.   Christian Sigg
• [Mlir-commits] [mlir] 2790cbe - Revert "[mlir][Linalg] Replace SimplePad with PadTensor in hoist-padding"   Tres Popp
• [Mlir-commits] [mlir] 94fac81 - [Branch-Rename] Fix some links   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] b3f611b - [mlir][Linalg] Replace SimplePad with PadTensor in hoist-padding   Hanhan Wang
• [Mlir-commits] [mlir] 21f1462 - [mlir][spirv] Add support for OpImageType   Lei Zhang
• [Mlir-commits] [mlir] 75347ba - Revert "[mlir][spirv] Add support for OpImageType"   Lei Zhang
• [Mlir-commits] [mlir] 32ef6d8 - Avoid string comparisons on the fast path of MLIR Identifier lookup (NFC)   Mehdi Amini
• [Mlir-commits] [mlir] 35f746c - [mlir][spirv] Add support for OpImageType   Lei Zhang
• [Mlir-commits] [mlir] 342d466 - [mlir] Add custom directive hooks for printing mixed integer or value operands.   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 21724dd - [MLIR][TOSA] Comparison based elementwise operations for tosa-to-linalg   Rob Suderman
• [Mlir-commits] [mlir] 49c9c3a - [mlir][Standard] Extend n-D vector lowering to LLVM to [s|z]exti ops.   Nicolas Vasilache
• [Mlir-commits] [mlir] 0409eb2 - [mlir] Keep track of region signature conversions as argument replacements   Alex Zinenko
• [Mlir-commits] [mlir] 0a2a260 - [mlir][Linalg] Refactor Linalg vectorization for better reuse and extensibility.   Nicolas Vasilache
• [Mlir-commits] [mlir] 94f540c - [mlir][Linalg] Fix unused variable warning in Release builds. NFC.   Benjamin Kramer
• [Mlir-commits] [mlir] 8fce228 - [mlir][Linalg] Fix and properly test CodegenStrategy API   Nicolas Vasilache
• [Mlir-commits] [mlir] b24e3cc - [mlir] Put template specialization in the same namespace   Lei Zhang
• [Mlir-commits] [mlir] b2b3569 - [mlir] Fix scf.for single iteration canonicalization check   Lei Zhang
• [Mlir-commits] [mlir] e901188 - [mlir][spirv] Define sp.VectorShuffle   Lei Zhang
• [Mlir-commits] [mlir] a2e791e - Revert "[mlir] Fix scf.for single iteration canonicalization check"   Lei Zhang
• [Mlir-commits] [mlir] f1bdf9f - [mlir][NFC] Use explicit `mlir` namespace in generated code   Mehdi Amini
• [Mlir-commits] [mlir] d8c3738 - [mlir][NFC] Add missing include guards to MlirOptMain.h   Mehdi Amini
• [Mlir-commits] [mlir] 7cc7998 - [mlir] Allow to use constant lambda as callbacks for `TypeConverter`   Mehdi Amini
• [Mlir-commits] [mlir] 9593584 - [mlir] Print more verbose message in case of type inference error   Mehdi Amini
• [Mlir-commits] [mlir] 67dfe9c - [mlir] Return new Operation from `Rewriter::replaceOpWithNewOp`   Mehdi Amini
• [Mlir-commits] [mlir] 5b38816 - [mlir] Delay adding the __resume function   Christian Sigg
• [Mlir-commits] [mlir] 2aa1af9 - [MLIR] [CMake] Support building MLIR standalone   Isuru Fernando
• [Mlir-commits] [mlir] b7d8005 - Fix namespace for MLIR Async Runtime   Renato Golin
• [Mlir-commits] [mlir] ec10f06 - [mlir][Pattern] Create a new IRRewriter class to enable sharing code with pattern rewrites   River Riddle
• [Mlir-commits] [mlir] 29fffff - Revert "Fix namespace for MLIR Async Runtime"   Mehdi Amini
• [Mlir-commits] [mlir] cf5c517 - [mlir][Vector] Add lowering to LLVM for vector.bitcast   Diego Caballero
• [Mlir-commits] [mlir] 5b7619c - [mlir] Fix scf.for single iteration canonicalization check   Lei Zhang
• [Mlir-commits] [mlir] dd2dac2 - Fix MLIR Async Runtime DLL on Windows   Renato Golin
• [Mlir-commits] [mlir] 8a43ec7 - Set GPU context before {cu, hip}MemHostRegister.   Christian Sigg
• [Mlir-commits] [mlir] 4a35941 - Delete CUDA context after linking device code.   Christian Sigg
• [Mlir-commits] [mlir] 8d73bee - [mlir] Add gpu async integration test.   Christian Sigg
• [Mlir-commits] [mlir] 9db6114 - Add API for adding arguments to blocks   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] a1d5bdf - Make the folder more robust against op fold() methods that generate a type mismatch   Mehdi Amini
• [Mlir-commits] [mlir] c95c0db - [MLIR] Fix building unittests in in-tree build   Mehdi Amini
• [Mlir-commits] [mlir] 1029c82 - [mlir][Linalg] NFC - Extract a standalone LinalgInterfaces   Nicolas Vasilache
• [Mlir-commits] [mlir] f245b7a - [mlir][Linalg] Generalize the definition of a Linalg contraction.   Nicolas Vasilache
• [Mlir-commits] [mlir] 5b91060 - [mlir] Apply source materialization in case of transitive conversion   Alex Zinenko
• [Mlir-commits] [mlir] ba87f99 - [mlir] make vector to llvm conversion truly partial   Alex Zinenko
• [Mlir-commits] [mlir] f4ac9f0 - [mlir][Linalg] Drop SliceOp   Nicolas Vasilache
• [Mlir-commits] [mlir] 09c18a6 - [mlir] Return scf.parallel ops resulted from tiling.   Alexander Belyaev
• [Mlir-commits] [mlir] e4a503a - [mlir][Linalg] Introduce a ContractionOpInterface   Nicolas Vasilache
• [Mlir-commits] [mlir] 07fc852 - [mlir][ODS] Small fixes for ODS classes   Mehdi Amini
• [Mlir-commits] [mlir] cafdf46 - [mlir][ODS] Add explicit namespace to `ViewLikeInterface` definition   Mehdi Amini
• [Mlir-commits] [mlir] 953086d - [mlir][ODS] Use StringLiteral instead of StringRef when applicable   Mehdi Amini
• [Mlir-commits] [mlir] 215441f - Remove dead code from Linalg vectorization to fix GCC warning (NFC)   Mehdi Amini
• [Mlir-commits] [mlir] f9f6b4f - [mlir] Silence GCC warnings   Diego Caballero
• [Mlir-commits] [mlir] 63dc264 - Revert "[mlir][ODS] Use StringLiteral instead of StringRef when applicable"   Lei Zhang
• [Mlir-commits] [mlir] 042db54 - [mlir] Small touchups to LangRef attribute section   Sean Silva
• [Mlir-commits] [mlir] e21adfa - [mlir] Mark LogicalResult as LLVM_NODISCARD   River Riddle
• [Mlir-commits] [mlir] 7f58196 - [mlir][linalg] Linalg.fill on tensor should not have side-effects   Nicolas Vasilache
• [Mlir-commits] [mlir] ef9e1e5 - [mlir][Linalg] Add option to anchor on func name in TestLinalgCodegenStrategy   Nicolas Vasilache
• [Mlir-commits] [mlir] 0fcbbde - [mlir][Linalg] NFC - Refactor vectorization to be more composable   Nicolas Vasilache
• [Mlir-commits] [mlir] b40f9fb - [mlir][Linalg] Fix spurious test change   Nicolas Vasilache
• [Mlir-commits] [mlir] f349abc - [mlir] Add `const` qualifiers to `AffineMap` methods   Vladislav Vinogradov
• [Mlir-commits] [mlir] 1b10103 - [mlir] Turn Linalg to LLVM into a partial conversion   Alex Zinenko
• [Mlir-commits] [mlir] 6da8d6c - [mlir][Linalg] NFC - Improve usage of mlir::linalg::isaContractionOpInterface   Nicolas Vasilache
• [Mlir-commits] [mlir] 874ce9b - [mlir][vector] Add patterns to cast away leading 1-dim   Lei Zhang
• [Mlir-commits] [mlir] 9f622b3 - [mlir][spirv] Add more vector conversion patterns   Lei Zhang
• [Mlir-commits] [mlir] 8dae909 - [mlir][vector] Add constant folding for fp16 to fp32 bitcast   Lei Zhang
• [Mlir-commits] [mlir] 1d0b023 - Drop LLVM_i1, LLVM_i8, LLVM_i32, LLVM_IntBase types   Alex Zinenko
• [Mlir-commits] [mlir] 7630520 - [mlir][vector] Add pattern to shuffle bitcast ops   Lei Zhang
• [Mlir-commits] [mlir] 0453d2d - Add a link to the LLVM Dev recording from the MLIR tutorial landing page   Mehdi Amini
• [Mlir-commits] [mlir] d6efb6f - Rework ExecutionEngine::invoke() to make it more friendly to use from C++   Mehdi Amini
• [Mlir-commits] [mlir] 05c6c64 - [MLIR] [affine-loop-fusion] Fix a bug about non-result ops in affine-loop-fusion   Uday Bondhugula
• [Mlir-commits] [mlir] 035abe3 - [mlir][ODS] Allow to specify custom namespace for `NativeOpTrait`   Vladislav Vinogradov
• [Mlir-commits] [mlir] 7827753 - Reorder MLIRContext location in BuiltinAttributes.h   Tres Popp
• [Mlir-commits] [mlir] 511dd4f - Revert "Reorder MLIRContext location in BuiltinAttributes.h"   Tres Popp
• [Mlir-commits] [mlir] c2c83e9 - Revert "Revert "Reorder MLIRContext location in BuiltinAttributes.h""   Tres Popp
• [Mlir-commits] [mlir] 86bde76 - [MLIR][LangRef doc] Fix a small typo.   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 88d5c4c - [MLIR][SPIRV] NFC: Split serialization code among multiple files.   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 2b92f21 - [mlir] Drop deprecated syntax for LLVM dialect types   Alex Zinenko
• [Mlir-commits] [mlir] d57a305 - [mlir][Linalg] Fix padding related bugs.   Nicolas Vasilache
• [Mlir-commits] [mlir] 333d2cf - [MLIR][NFC] Fix std.copysign op documentation   Uday Bondhugula
• [Mlir-commits] [mlir] 8f130f1 - [MLIR] Add C API for navigating up the IR tree   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] b6910fd - [MLIR][AVX512] Add integration test for vp2intersect   Matthias Springer
• [Mlir-commits] [mlir] 4c640e4 - [mlir][linalg] Verify indexing map required attributes   Lei Zhang
• [Mlir-commits] [mlir] 068bf9e - [mlir][linalg] Define a depthwise 2-D convolution op   Lei Zhang
• [Mlir-commits] [mlir] fa581f9 - [mlir] Add stacksave, stackrestore to llvm dialect   Alex Zinenko
• [Mlir-commits] [mlir] bfa508e - [mlir][linalg] Fix one more missing NoSideEffect in linalg tensor op   Thomas Raoux
• [Mlir-commits] [mlir] 7784ce0 - [mlir][linalg] Fix depthwise conv C++ symbol to be consistent   Lei Zhang
• [Mlir-commits] [mlir] 5fa893c - [mlir] add support for verification in integration tests   Tobias Gysi
• [Mlir-commits] [mlir] 5099a48 - [MLIR] Replace dialect registration hooks with dialect handle   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] dd719fd - Revert "[mlir] add support for verification in integration tests"   Tobias Gysi
• [Mlir-commits] [mlir] e8d3175 - [mlir][Linalg] Add a build method for linalg.pad_tensor   Hanhan Wang
• [Mlir-commits] [mlir] 2ef2413 - [mlir][spirv] Add support for sampled image type   Lei Zhang
• [Mlir-commits] [mlir] fe7c0d9 - [mlir][IR] Remove the concept of `OperationProperties`   River Riddle
• [Mlir-commits] [mlir] 6962bd6 - [MLIR] Add context accessor to identifier   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] b9c876b - [mlir] Add initial support for an alias analysis framework in MLIR   River Riddle
• [Mlir-commits] [mlir] 6e3292b - [mlir][OpFormatGen] Refactor `type_ref` into a more general `ref` directive   River Riddle
• [Mlir-commits] [mlir] 4bd68f2 - Add NoSideEffect trait to shape.split_at and shape.concat   Jacques Pienaar
• [Mlir-commits] [mlir] 018645b - Fix side-effect detection in LLVMIRIntrinsicGen.   Mehdi Amini
• [Mlir-commits] [mlir] 74c3615 - Add LLVMIR Dialect counterparts of @llvm.maximum and @llvm.minimum.   Mehdi Amini
• [Mlir-commits] [mlir] 5400f60 - [MLIR] Update affine.for unroll utility for iter_args support   Uday Bondhugula
• [Mlir-commits] [mlir] fdfd647 - [MLIR] NFC Fix vector transforms build warnings   Uday Bondhugula
• [Mlir-commits] [mlir] f30f347 - [mlir][shape] Generalize broadcast to a variadic number of shapes   Tres Popp
• [Mlir-commits] [mlir] 3da5152 - [mlir] enable delayed registration of dialect interfaces   Alex Zinenko
• [Mlir-commits] [mlir] 2996a8d - [mlir] avoid exposing mutable DialectRegistry from MLIRContext   Alex Zinenko
• [Mlir-commits] [mlir] bb69de3 - [mlir][Linalg] Add a vectorization pattern for linalg::PadTensorOp   Nicolas Vasilache
• [Mlir-commits] [mlir] 0ac3d97 - [mlir][Linalg] Fix pad hoisting.   Nicolas Vasilache
• [Mlir-commits] [mlir] 11f32a4 - Add convenience C++ helper to manipulate ranked strided memref   Mehdi Amini
• [Mlir-commits] [mlir] e49967f - Revert "Add convenience C++ helper to manipulate ranked strided memref"   Mehdi Amini
• [Mlir-commits] [mlir] 9680ea5 - Add convenience C++ helper to manipulate ranked strided memref   Mehdi Amini
• [Mlir-commits] [mlir] 0b1764a - [mlir][sparse] sparse tensor storage implementation   Aart Bik
• [Mlir-commits] [mlir] 544cebd - Change type constraint of the "index" in "shape.split_at" to Shape_SizeOrIndexType   Jacques Pienaar
• [Mlir-commits] [mlir] 8198739 - Fix StridedMemRefType operator[] SFINAE to allow correctly selecting the `int64_t` overload for non-container operands   Mehdi Amini
• [Mlir-commits] [mlir] 4643fd2 - [mlir][Linalg] Fix crash when tileSizeComputationFunction is left unspecified   Nicolas Vasilache
• [Mlir-commits] [mlir] 24db783 - [mlir] NFC - Extend inferResultType API for SubViewOp and SubTensorOp   Nicolas Vasilache
• [Mlir-commits] [mlir] 6b07a97 - [mlir] Introduce more intuitive wording for attributes.   Sean Silva
• [Mlir-commits] [mlir] b83361b - Minor fixes to Type ODS docs.   Sean Silva
• [Mlir-commits] [mlir] c19a412 - [MLIR][TOSA] Tosa elementwise broadcasting   Rob Suderman
• [Mlir-commits] [mlir] 09cfec6 - Fix CMake configuration for MLIR unittests   Mehdi Amini
• [Mlir-commits] [mlir] b1aaed0 - Enable `Pass::initialize()` to fail by returning a LogicalResult   Mehdi Amini
• [Mlir-commits] [mlir] 11bec2a - [mlir][sparse] reduce tensor dimensions in sparse test   Aart Bik
• [Mlir-commits] [mlir] a76761c - NFC comment-only cleanups   Sanjoy Das
• [Mlir-commits] [mlir] bac1f12 - NFC; fix typo in comment   Sanjoy Das
• [Mlir-commits] [mlir] 9325b8d - [mlir][Linalg] Add conv ops with TF definition.   Hanhan Wang
• [Mlir-commits] [mlir] 33a58c1 - [mlir][gpu] Allow all dialects in SCF to GPU conversion.   Stephan Herhut
• [Mlir-commits] [mlir] 9a08f76 - [mlir] Make JitRunnerMain main take a DialectRegistry   Alex Zinenko
• [Mlir-commits] [mlir] 0881a4f - [mlir] make ModuleTranslation mapping fields private   Alex Zinenko
• [Mlir-commits] [mlir] e332c22 - [mlir][LLVM] NFC - Refactor a lookupOrCreateFn to reuse common function creation.   Nicolas Vasilache
• [Mlir-commits] [mlir] ed98676 - Support multi-configuration generators correctly in several config files   Stella Stamenova
• [Mlir-commits] [mlir] 5bc4f88 - s[mlir] Tighten computation of inferred SubView result type.   Nicolas Vasilache
• [Mlir-commits] [mlir] 5f022ad - [mlir] detect integer overflow in debug mode   Aart Bik
• [Mlir-commits] [mlir] 16213e1 - [mlir] Allow users of `PromoteBuffersToStackPass` to customize `small buffer` func.   Alexander Belyaev
• [Mlir-commits] [mlir] 891e769 - [mlir] Initialize `isSmallAlloc` in `initialize` method.   Alexander Belyaev
• [Mlir-commits] [mlir] 4348d8a - [mlir][math] Split off the math dialect.   Stephan Herhut
• [Mlir-commits] [mlir] 2bfe27d - [mlir][math] Fix cmake files after dialect splitting.   Stephan Herhut
• [Mlir-commits] [mlir] 4c4876c - [mlir] Use target-specific GPU kernel attributes in lowering pipelines   Alex Zinenko
• [Mlir-commits] [mlir] 530d6ea - [mlir][spirv] Lower sexti -> SConvert   Benjamin Kramer
• [Mlir-commits] [mlir] 973e133 - [mlir][Linalg] Improve region support in Linalg ops.   Nicolas Vasilache
• [Mlir-commits] [mlir] f3fb2dd - [mlir][Linalg] NFC - Add an OpFoldResult-based builder for InitTensorOp   Nicolas Vasilache
• [Mlir-commits] [mlir] b77bac0 - [mlir] Introduce dialect interfaces for translation to LLVM IR   Alex Zinenko
• [Mlir-commits] [mlir] 66900b3 - [mlir] Use dialect interfaces to translate OpenMP dialect to LLVM IR   Alex Zinenko
• [Mlir-commits] [mlir] 3f22547 - Revert "[mlir][Linalg] Improve region support in Linalg ops."   Mehdi Amini
• [Mlir-commits] [mlir] ee66e43 - [mlir][Vector] Introduce 'vector.load' and 'vector.store' ops   Diego Caballero
• [Mlir-commits] [mlir] 656674a - [mlir][Vector] Align gather/scatter/expand/compress API   Diego Caballero
• [Mlir-commits] [mlir] aa4e466 - [mlir][Linalg] Improve region support in Linalg ops   Mehdi Amini
• [Mlir-commits] [mlir] a65fb19 - Add a "kind" attribute to ContractionOp and OuterProductOp.   Mehdi Amini
• [Mlir-commits] [mlir] 6e31a6b - fix linalg ods gen cross compiling like other gen executables   Mehdi Amini
• [Mlir-commits] [mlir] 3643828 - [CMake][mlir] Fix mlir-linalg-ods-gen/CMakeLists.txt after D96645   Fangrui Song
• [Mlir-commits] [mlir] 428bc6f - [mlir][Linalg] Fix constant detection in linalg.pad_tensor vectorization.   Nicolas Vasilache
• [Mlir-commits] [mlir] 99f3510 - Reland "[mlir] add support for verification in integration tests"   Tobias Gysi
• [Mlir-commits] [mlir] 34ea608 - [mlir] Support repeated delayed registration of dialect interfaces   Alex Zinenko
• [Mlir-commits] [mlir] 89d900b - [mlir] Add error message on shape.broadcast verification failure   Tres Popp
• [Mlir-commits] [mlir] 176379e - [mlir] Use the interface-based translation for LLVM "intrinsic" dialects   Alex Zinenko
• [Mlir-commits] [mlir] 1d6f08e - [mlir] use new cmake targets in mlir-*-runner   Alex Zinenko
• [Mlir-commits] [mlir] 3842d4b - Make shape.is_broadcastable/shape.cstr_broadcastable nary   Tres Popp
• [Mlir-commits] [mlir] 381a65f - [mlir] Add clone method to ShapedType   Jacques Pienaar
• [Mlir-commits] [mlir] 02d053e - [mlir][Vector] Add a canonicalization pattern for vector.contract + add   Nicolas Vasilache
• [Mlir-commits] [mlir] d01ea0e - [mlir] Drop reliance of SliceAnalysis on specific ops.   Nicolas Vasilache
• [Mlir-commits] [mlir] 9f58181 - Add Expm1 op to the math dialect.   Adrian Kuegel
• [Mlir-commits] [mlir] 07cc771 - Lower math.expm1 to intrinsics in the GPUToNVVM and GPUToROCDL conversions.   Adrian Kuegel
• [Mlir-commits] [mlir] 21debea - [mlir][Linalg] Generalize vector::transfer hoisting on tensors.   Nicolas Vasilache
• [Mlir-commits] [mlir] 787d771 - [mlir] Don't return nullptrs from scf::IfOp::getSuccessorRegions   Tres Popp
• [Mlir-commits] [mlir] d8c7f44 - [mlir][vector] Add support for unrolling vector.fma   Lei Zhang
• [Mlir-commits] [mlir] cb1a423 - [mlir][vector] Move splitting transfer ops into a separate entry point   Lei Zhang
• [Mlir-commits] [mlir] 807e546 - [mlir] Add canonicalization for tensor_cast + tensor_to_memref   Thomas Raoux
• [Mlir-commits] [mlir] 397336d - [mlir][vector] Add missing support for contract of integer lowering.   Thomas Raoux
• [Mlir-commits] [mlir] 9cd47a2 - [mlir] add verifiers for NVVM and ROCDL kernel attributes   Alex Zinenko
• [Mlir-commits] [mlir] 2ab57c5 - [mlir] tighten LLVM dialect verifiers to generate valid LLVM IR   Alex Zinenko
• [Mlir-commits] [mlir] ce8f10d - [mlir] Simplify ModuleTranslation for LLVM IR   Alex Zinenko
• [Mlir-commits] [mlir] adfd3c7 - [mlir] Fix memref_cast + subview folder when reducing rank   Thomas Raoux
• [Mlir-commits] [mlir] 99c0458 - separate AffineMapAccessInterface from AffineRead/WriteOpInterface   Jeremy Bruestle
• [Mlir-commits] [mlir] 81264df - [mlir][Linalg] Add utility method to reshape ops to express output shape in terms of input shape.   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 4c3f1be - [mlir][python] Add python binding for AffineMapAttribute.   Stella Laurenzo
• [Mlir-commits] [mlir] 82b692e - [mlir][Shape] Mark BroadcastOp as not having side effects   Benjamin Kramer
• [Mlir-commits] [mlir] 63a35f3 - [mlir][Shape] Generalize cstr_broadcastable folding for n-ary broadcasts   Benjamin Kramer
• [Mlir-commits] [mlir] 7742620 - [mlir][spirv] Add spv.GLSL.FrexpStruct   Lei Zhang
• [Mlir-commits] [mlir] c80484e - [mlir][StandardToSPIRV] Add support for lowering trunci to SPIR-V to i1 types.   Hanhan Wang
• [Mlir-commits] [mlir] 519f591 - [mlir] Add fma operation to std dialect   Eugene Zhulenev
• [Mlir-commits] [mlir] 4a3473f - [mlir] silence unused-function warnings in table-generated code   Alex Zinenko
• [Mlir-commits] [mlir] 55756f3 - [MLIR][TOSA] Expand Tosa int types to I8 and I16   Rob Suderman
• [Mlir-commits] [mlir] ff6c84b - [mlir][sparse] generalize sparse storage format to many more types   Aart Bik
• [Mlir-commits] [mlir] 12875ed - [mlir] generate enum translation functions with unused attribute   Alex Zinenko
• [Mlir-commits] [mlir] 8aa6c37 - [MLIR] Create memref dialect and move several dialect-specific ops from std.   Julian Gross
• [Mlir-commits] [mlir] a89035d - Revert "[MLIR] Create memref dialect and move several dialect-specific ops from std."   Alexander Belyaev
• [Mlir-commits] [mlir] 624fccb - [mlir] Add `linalg.tiled_loop` op.   Alexander Belyaev
• [Mlir-commits] [mlir] 25b4a6a - [MLIR][TOSA] Add lowering from TOSA to Linalg for math-based and elementwise ops   Rob Suderman
• [Mlir-commits] [mlir] 08c681f - Perform memory accesses in the same addrspace as the corresponding memref.   Aart Bik
• [Mlir-commits] [mlir] 8e01e2e - [mlir][Vector] Fold tensor_cast + vector.transfer_read   Nicolas Vasilache
• [Mlir-commits] [mlir] b006902 - [mlir] Fold trivial subtensor / subtensor_insert ops.   Nicolas Vasilache
• [Mlir-commits] [mlir] b9ff670 - [MLIR] Make structured op tests permutation invariant   Geoffrey Martin-Noble
• [Mlir-commits] [mlir] cd8cc00 - Revert "[MLIR] Make structured op tests permutation invariant"   Mehdi Amini
• [Mlir-commits] [mlir] d690cbf - Add DivOp to the Shape dialect   Jacques Pienaar
• [Mlir-commits] [mlir] ae15b1e - Fix MLIR Toy tutorial JIT example and add a test to cover it   Mehdi Amini
• [Mlir-commits] [mlir] db01177 - Reland "[MLIR] Make structured op tests permutation invariant"   Geoffrey Martin-Noble
• [Mlir-commits] [mlir] c86c96a - [mlir] Load dynamic libraries in JitRunner from absolute paths so that GDB can find the symbol tables.   Christian Sigg
• [Mlir-commits] [mlir] 2556d62 - [mlir][sparse] assert fail on mismatch between rank and annotations array   Aart Bik
• [Mlir-commits] [mlir] b3c227a - [mlir] Better support for rank-reducing subview / subtensor type inference.   Nicolas Vasilache
• [Mlir-commits] [mlir] d12fa33 - [mlir] Add a TensorLoadToMemref canonicalization   Nicolas Vasilache
• [Mlir-commits] [mlir] 53367b8 - [mlir][nfc] Fix indentation in LinalgOps.td.   Alexander Belyaev
• [Mlir-commits] [mlir] 62f5c46 - [mlir][Linalg] NFC - Expose more options to the CodegenStrategy   Nicolas Vasilache
• [Mlir-commits] [mlir] 236aab0 - [MLIR] Delete unused functions getCollapsedInitTensor and getExpandedInitTensor   Geoffrey Martin-Noble
• [Mlir-commits] [mlir] 0ee4bf1 - [mlir] Add folding of tensor.cast -> subtensor_insert   Nicolas Vasilache
• [Mlir-commits] [mlir] f99ccf6 - [mlir] Add math polynomial approximation pass   Eugene Zhulenev
• [Mlir-commits] [mlir] f360604 - Revert "Fix MLIR Toy tutorial JIT example and add a test to cover it"   Stella Stamenova
• [Mlir-commits] [mlir] f8c1f3b - Revert "Revert "Fix MLIR Toy tutorial JIT example and add a test to cover it""   Mehdi Amini
• [Mlir-commits] [mlir] f32b340 - [mlir][sparse] convert function pass to module pass   Aart Bik
• [Mlir-commits] [mlir] 02d7b26 - [mlir] Register the print-op-graph pass using ODS   Jacques Pienaar
• [Mlir-commits] [mlir] fa211f3 - Update test error string post pass registration change   Jacques Pienaar
• [Mlir-commits] [mlir] 6c9541d - Implement simple type polymorphism for linalg named ops.   Stella Laurenzo
• [Mlir-commits] [mlir] 04c66ed - [mlir] Add simple jupyter kernel   Jacques Pienaar
• [Mlir-commits] [mlir] 2d62212 - [mlir] Export CUDA and Vulkan runtime wrappers on Windows   Kern Handa
• [Mlir-commits] [mlir] 5b20d80 - [mlir] Mark std.subview as NoSideEffect   Tres Popp
• [Mlir-commits] [mlir] 1533298 - [MLIR][affine] Prevent fusion when ops with memory effect free are present between producer and consumer   Uday Bondhugula
• [Mlir-commits] [mlir] ed4d12c - [mlir][Shape] Fix a crash when folding nary broadcast ops   Benjamin Kramer
• [Mlir-commits] [mlir] 2ce6a42 - [MLIR] Add Linalg support for integer (generalized) matmuls   Geoffrey Martin-Noble
• [Mlir-commits] [mlir] 817d343 - [MLIR] Fix tilePerfectlyNested utility for handling non-unit step size   Uday Bondhugula
• [Mlir-commits] [mlir] 54529c4 - Add missing dep to fix shared libs build   Geoffrey Martin-Noble
• [Mlir-commits] [mlir] e2224dd - Fix typo introduced in https://reviews.llvm.org/D97006   Geoffrey Martin-Noble
• [Mlir-commits] [mlir] 0df59f2 - [sparse][mlir] simplify lattice optimization logic   Aart Bik
• [Mlir-commits] [mlir] 06e25d5 - [mlir][IR] Refactor the `getChecked` and `verifyConstructionInvariants` methods on Attributes/Types   River Riddle
• [Mlir-commits] [mlir] ddd556f - [mlir][pdl] Fix bug when ordering predicates   River Riddle
• [Mlir-commits] [mlir] 154cabe - [mlir][pdl][NFC] Extract the execution of each bytecode operation into its own function   River Riddle
• [Mlir-commits] [mlir] 99b0032 - Move the MLIR integration tests as a subdirectory of test (NFC)   Mehdi Amini
• [Mlir-commits] [mlir] 67e0d58 - [MLIR][LinAlg] Start detensoring implementation.   llvmlistbot at llvm.org
• [Mlir-commits] [mlir] 72d5afa - [mlir] Add a new debug action framework.   River Riddle
• [Mlir-commits] [mlir] dc6a84f - [mlir] Add support for DebugCounters using the new DebugAction infrastructure   River Riddle
• [Mlir-commits] [mlir] 1fff7c8 - Fix unused variable   Frederik Gossen
• [Mlir-commits] [mlir] 551ba72 - [mlir] NFC - Use declarative assembly for scf::YieldOp   Nicolas Vasilache
• [Mlir-commits] [mlir] 8cf14b8 - [mlir][Linalg] Retire hoistViewAllocOps.   Nicolas Vasilache
• [Mlir-commits] [mlir] af8adea - make Affine parallel and yield ops MemRefsNormalizable   Jeremy Bruestle
• [Mlir-commits] [mlir] 17fa919 - [mlir][sparse] incorporate vector index into address computation   Aart Bik
• [Mlir-commits] [mlir] 65a3197 - [mlir] Refactor InterfaceMap to use a sorted vector of interfaces, as opposed to a DenseMap   River Riddle
• [Mlir-commits] [mlir] abd3c6f - [mlir][Inliner] Use llvm::parallelForEach instead of llvm::parallelTransformReduce   River Riddle
• [Mlir-commits] [mlir] 16a50c9 - [mlir][Inliner] Keep the number of async pass managers constant   River Riddle
• [Mlir-commits] [mlir] 3c4cdd0 - [mlir] ExecutionEngine needs special handling for COFF binaries   Kern Handa
• [Mlir-commits] [mlir] 59f0e46 - [mlir][Inliner] Don't optimize callees in async mode if there is only one to optimize   River Riddle
• [Mlir-commits] [mlir] 945b76d - [mlir][linalg] Fix Linalg roundtrip test.   Alexander Belyaev
• [Mlir-commits] [mlir] eb8d6af - [mlir] Specify cuda-runner pass pipeline as command line options.   Christian Sigg
• [Mlir-commits] [mlir] 7377ef9 - [mlir] Add a builder to `linalg.tiled_loop`.   Alexander Belyaev
• [Mlir-commits] [mlir] ce976d2 - [mlir] Add polynomial approximation for math::LogOp (using builders API)   Eugene Zhulenev
• [Mlir-commits] [mlir] 5f8a808 - [mlir] Add constBuilderCall to TypeAttr to simplify builders   Lei Zhang
• [Mlir-commits] [mlir] ce2ad93 - [mlir][spirv] Define spv.GLSL.Ldexp   Lei Zhang
• [Mlir-commits] [mlir] 705068c - [mlir][linalg] Support for using output values in TC definitions.   Hanhan Wang
• [Mlir-commits] [mlir] 21895a2 - [mlir][linalg] Reuse the symbol if attribute uses are identical.   Hanhan Wang
• [Mlir-commits] [mlir] e79cd47 - [mlir][docs] Small fix to local Pass Manager reproduction documentation   River Riddle
• [Mlir-commits] [mlir] c519460 - Allow !shape.size type operands in "shape.from_extents" op.   Sean Silva
• [Mlir-commits] [mlir] 6990411 - [mlir] Fix emitting attribute documentation   Marius Brehler
• [Mlir-commits] [mlir] 2d870a2 - [mlir][nfc] Fix typo in documentation comment   Marius Brehler
• [Mlir-commits] [mlir] f03826f - Pass GPU events instead of streams across async regions.   Christian Sigg
• [Mlir-commits] [mlir] f4d78a5 - [mlir][NFC] Add missing namespace qualifier to ODS generated code   Vladislav Vinogradov
• [Mlir-commits] [mlir] 203d5ee - [MLIR][affine-loop-fusion] Handle defining ops between the source and dest loops   Diego Caballero
• [Mlir-commits] [mlir] ebca222 - [mlir] Check 'iter_args' in 'isLoopParallel' utility   Diego Caballero
• [Mlir-commits] [mlir] 8c074cb - [mlir] Mark OpState::getAttrs() deprecated.   Christian Sigg
• [Mlir-commits] [mlir] a813e9b - [MLIR][TOSA] Added Tosa to Standard/SCF Lowerings (const, if, while)   Rob Suderman
• [Mlir-commits] [mlir] 24539f1 - Add Alignment argument to IRBuilder CreateAtomicRMW and CreateAtomicCmpXchg.   James Y Knight
• [Mlir-commits] [mlir] c47aa3c - Revert [MLIR][TOSA] Added Tosa to Standard/SCF Lowerings (const, if, while)   Rob Suderman
• [Mlir-commits] [mlir] 0b05908 - [mlir] Remove some rarely used OpState members and use Operation members instead.   Christian Sigg
• [Mlir-commits] [mlir] ce0f10a - [MLIR][affine] Certain Call Ops to prevent fusion   Uday Bondhugula
• [Mlir-commits] [mlir] dffc487 - [mlir] Mark OpState::removeAttr() deprecated.   Christian Sigg
• [Mlir-commits] [mlir] 56774bd - [mlir] Replace deprecated 'getAttrs'   Marius Brehler
• [Mlir-commits] [mlir] 4941fef - [mlir] Silence some deprecation warnings after dffc487b07d9a50f8c65eccb9241f72af3486c79   Benjamin Kramer
• [Mlir-commits] [mlir] 855a119 - [mlir][linalg] Allow TC ops taking an unused shaped operand.   Hanhan Wang
• [Mlir-commits] [mlir] bfd3771 - [mlir][linalg] Add pooling ops to Linalg TC ops.   Hanhan Wang
• [Mlir-commits] [mlir] 21bb638 - [MLIR][linalg] Make integer matmul ops cast before multiplying   Geoffrey Martin-Noble
• [Mlir-commits] [mlir] caccddc - [MLIR][TOSA] Lower tosa.reshape to linalg.reshape   Rob Suderman
• [Mlir-commits] [mlir] df5ccf5 - [mlir][vector] add higher dimensional support to gather/scatter   Aart Bik
• [Mlir-commits] [mlir] f685c9a - [MLIR][TOSA] Lower tosa.identity and tosa.identitiyn to linalg   Rob Suderman
• [Mlir-commits] [mlir] 91ab48e - [mlir] Add regions to OpAdaptor   Jacques Pienaar
• [Mlir-commits] [mlir] 16abaca - [MLIR][TOSA] Resubmit Tosa to Standard/SCF Lowerings (const, if, while)"   Rob Suderman
• [Mlir-commits] [mlir] e6260ad - [mlir] Simplify various pieces of code now that Identifier has access to the Context/Dialect   River Riddle
• [Mlir-commits] [mlir] ee90bb3 - Store (cache) the Argument number (index in the argument list) inside the BlockArgumentImpl   Mehdi Amini
• [Mlir-commits] [mlir] dd2f50a - [mlir] Improve test coverage for print-op-graph   Jacques Pienaar
• [Mlir-commits] [mlir] a6d76cf - Change the error message when `-split-input-file` is used with mlir-opt to make it recognizable by IDEs   Mehdi Amini
• [Mlir-commits] [mlir] 7b06786 - Fix Block::eraseArguments to properly update the cached positions   Mehdi Amini
• [Mlir-commits] [mlir] 0145759 - Fix Block::eraseArguments: keep track the first removed element while removing   Mehdi Amini
• [Mlir-commits] [mlir] 5867c18 - [mlir][linalg] Generate additional interfaces for named ops.   Stella Laurenzo
• [Mlir-commits] [mlir] 2ceedc3 - [mlir][linalg] Add symbolic type conversion to linalg named ops.   Stella Laurenzo
• [Mlir-commits] [mlir] 769cd20 - NFC: Adds labels to a linalg test and extend a missing case.   Stella Laurenzo
• [Mlir-commits] [mlir] 6afaea6 - [mlir][sparse] fixed inaccury in maintaining universal index   Aart Bik

Last message date: Sat Feb 27 17:33:12 PST 2021
Archived on: Sat Feb 27 17:38:08 PST 2021

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