summaryrefslogtreecommitdiff
path: root/mlir
Commit message (Expand)AuthorAgeFilesLines
* [mlir][linalg] Use attributes in named ops' indexing mapsLei Zhang2021-01-133-44/+290
* [mlir][Python] Add checking process before create an AffineMap from a permuta...zhanghb972021-01-132-0/+24
* Delete unused function (was breaking the -Werror build)David Blaikie2021-01-121-26/+0
* [mlir] Update LLVM dialect type documentationAlex Zinenko2021-01-121-69/+105
* [MLIR] Disallow `sym_visibility`, `sym_name` and `type` attributes in the par...Rahul Joshi2021-01-124-9/+37
* [mlir][spirv] NFC: split deserialization into multiple source filesLei Zhang2021-01-1210-1264/+1364
* [mlir] Fix for LIT testsVladislav Vinogradov2021-01-121-0/+1
* [mlir][CAPI] Fix inline function declarationVladislav Vinogradov2021-01-121-1/+1
* Reland "[mlir][linalg] Support parsing attributes in named op spec"Lei Zhang2021-01-122-4/+199
* [mlir][spirv] NFC: place ops in the proper file for their categoriesLei Zhang2021-01-1215-1847/+1908
* [mlir][openacc] Use TableGen information for default enumValentin Clement2021-01-125-27/+34
* [mlir][Linalg] NFC - Refactor fusion APIsNicolas Vasilache2021-01-127-107/+128
* [mlir][openmp][NFCI] Rename `continuationIP` to `continuationBlock`Sourabh Singh Tomar2021-01-121-4/+4
* [mlir] use built-in vector types instead of LLVM dialect types when possibleAlex Zinenko2021-01-1254-1220/+1284
* [MLIR][Linalg] Refactor transforms to use linalg::getDynOperands helperRob Suderman2021-01-117-38/+73
* Update syntax for tensor and memref types to match parser.Richard Uhler2021-01-112-9/+9
* [mlir][vector] verify memref of vector memory opsAart Bik2021-01-112-12/+51
* Revert "[mlir][linalg] Support parsing attributes in named op spec"Mehdi Amini2021-01-112-198/+4
* [mlir][CAPI] Introduce standard source layout for mlir-c dialect registration.Stella Laurenzo2021-01-1117-53/+315
* Enable python bindings for tensor, shape and linalg dialects.Stella Laurenzo2021-01-116-12/+84
* [mlir][vector] Add side-effect information to different load/store opsThomas Raoux2021-01-112-6/+25
* [mlir][IR][NFC] Move the definitions of Complex/Function/Integer/Opaque/Tuple...River Riddle2021-01-115-307/+249
* [mlir][TypeDefGen] Add support for adding builders when generating a TypeDefRiver Riddle2021-01-119-95/+541
* [mlir][ODS] Add a C++ abstraction for OpBuildersRiver Riddle2021-01-116-68/+209
* [mlir] Add structural conversion to async dialect lowering.Christian Sigg2021-01-112-0/+81
* [mlir] Expose MemRef layout in Python bindingsAlex Zinenko2021-01-114-19/+86
* [mlir] More Python bindings for AffineMapAlex Zinenko2021-01-116-16/+384
* [mlir] Add Python bindings for AffineExprAlex Zinenko2021-01-117-0/+708
* [mlir][Linalg] Fix reshape fusion to reshape the outs instead of creating new...MaheshRavishankar2021-01-114-239/+179
* [mlir][vector] Add memory effects to transfer_read transfer_write opsThomas Raoux2021-01-114-4/+50
* [mlir][Linalg] Fold init_tensor -> linalg.tensor_reshape.MaheshRavishankar2021-01-112-6/+156
* [mlir] Fix gpu-to-llvm lowering for gpu.alloc with dynamic sizes.Christian Sigg2021-01-115-13/+18
* [mlir][linalg] Support permutation when lowering to loop nestsLei Zhang2021-01-114-50/+137
* [mlir][linalg] Support parsing attributes in named op specLei Zhang2021-01-112-4/+198
* [mlir] Make GpuAsyncRegion pass depend on async dialect.Christian Sigg2021-01-113-1/+5
* [mlir] Remove unnecessary llvm.mlir.cast in AsyncToLLVM lowering.Christian Sigg2021-01-111-7/+1
* Remove redundant casts.Adrian Kuegel2021-01-111-6/+4
* [MLIR][SPIRV] Add (de-)serialization support for SpecConstantOpeation.ergawy2021-01-116-7/+235
* [IR Parser] Fix a crash handling zero width integer attributes.Chris Lattner2021-01-102-0/+13
* [mlir] NFC - Drop spurious assertion on symbols during `promoteComposedSymbol...Nicolas Vasilache2021-01-101-10/+2
* [mlir] Enhance mlir-opt show-dialects test case9eb3e564d3bLewuathe2021-01-091-14/+27
* [mlir][vector] modified scatter/gather syntax, pass_thru mandatoryAart Bik2021-01-0910-81/+87
* [mlir][spirv] Replace SPIRVOpLowering with OpConversionPatternLei Zhang2021-01-0910-152/+203
* [mlir] AsyncRuntime: use LLVM ThreadPool to run async tasksEugene Zhulenev2021-01-091-1/+7
* Update the maximum integer bitwidth in MLIR.Andrew Lenharth2021-01-082-3/+3
* [mlir][PassManager] Properly set the initialization generation when cloning a...River Riddle2021-01-081-0/+1
* [mlir] AsyncRuntime: disable mlir-runner init/disable for WIN32Eugene Zhulenev2021-01-081-3/+2
* [mlir][vector] generalized masked l/s and compressed l/s with indicesAart Bik2021-01-0813-269/+321
* [mlir] Add a hook for initializing passes before execution and use it in the ...River Riddle2021-01-086-25/+100
* [mlir:JitRunner] Use custom shared library init/destroy functions if availableEugene Zhulenev2021-01-083-8/+119