summaryrefslogtreecommitdiffstats
path: root/mlir/include
Commit message (Expand)AuthorAgeFilesLines
...
* Add std.log* and llvm.intr.log* that correspond to the LLVMIR intrinsicsNicolas Vasilache2019-12-112-0/+46
* Fix OSS buildNicolas Vasilache2019-12-111-4/+4
* Expose a convenience function to add interface attributes to a function.Mahesh Ravishankar2019-12-111-6/+12
* Continue refactoring StructuredOps utilitiesNicolas Vasilache2019-12-115-185/+228
* Roll-forward initial liveness analysis including test cases.Alexander Belyaev2019-12-111-0/+157
* Automated rollback of commit 98fbf41044d3364dbaf18db81b9e8d9520d14761Alexander Belyaev2019-12-111-157/+0
* Add a function to get lowering patterns from GPU to NVVM.Stephan Herhut2019-12-111-0/+4
* Add initial liveness analysis including test cases.Marcel Koester2019-12-111-0/+157
* Add VectorOp transform pattern which splits vector TransferReadOps to target ...Andy Davis2019-12-102-0/+5
* More affine expr simplifications for floordiv and modUday Bondhugula2019-12-101-2/+3
* Move gpu.launch_func to ODS. NFCAlex Zinenko2019-12-103-52/+144
* Refactor the various operand/result/type iterators to use indexed_accessor_ra...River Riddle2019-12-106-206/+212
* [Linalg] Add a Linalg iterator permutation transformationJose Ignacio Gomez2019-12-103-5/+35
* Uniformize Vector transforms as patterns on the model of Linalg - NFCNicolas Vasilache2019-12-102-19/+9
* More convenience build methods for SPIR-V ops.Mahesh Ravishankar2019-12-102-1/+8
* Drop Markdown style annotationsAlex Zinenko2019-12-1014-114/+114
* Fix build breakage on gcc-5Jacques Pienaar2019-12-091-4/+4
* [VectorOps] Add a ShuffleOp to the VectorOps dialectAart Bik2019-12-091-0/+53
* Refactor the Block support classes.River Riddle2019-12-092-157/+167
* Add new indexed_accessor_range_base and indexed_accessor_range classes that s...River Riddle2019-12-095-92/+170
* [spirv] Add CompositeConstruct operation.Denis Khalikov2019-12-092-14/+68
* [spirv] Add spv.IAdd, spv.ISub, and spv.IMul foldersLei Zhang2019-12-091-0/+2
* Factor out commonly reusable names across structured ops dialectsNicolas Vasilache2019-12-092-12/+56
* Add lowering for module with gpu.kernel_module attribute.Mahesh Ravishankar2019-12-091-7/+11
* Unify vector op unrolling transformation.Andy Davis2019-12-091-0/+1
* Minor spelling tweaksKazuaki Ishizaki2019-12-0916-21/+21
* [StructuredOps][Linalg] Add a primitive pattern to rewrite the linalg.generic...Nicolas Vasilache2019-12-094-4/+26
* Add RegionRange for when need to abstract over different region iterationJacques Pienaar2019-12-093-9/+60
* Post-submit cleanups in RecursiveMatchersNicolas Vasilache2019-12-091-2/+2
* Replace spurious SmallVector constructions with ValueRangeUday Bondhugula2019-12-092-3/+3
* Add a layer of recursive matchers that compose.Nicolas Vasilache2019-12-081-17/+96
* NFC: Expose constFoldBinaryOp via a headerLei Zhang2019-12-081-0/+82
* Update the builder API to take ValueRange instead of ArrayRef<Value *>River Riddle2019-12-0714-68/+68
* Add a new ValueRange class.River Riddle2019-12-066-15/+78
* Improve Linalg documentation following the Structured Ops presentation.Nicolas Vasilache2019-12-063-46/+130
* Add a flag to the IRPrinter instrumentation to only print after a pass if the...River Riddle2019-12-061-2/+18
* NFC - update doc, comments, vim syntax fileUday Bondhugula2019-12-062-10/+11
* Change inferReturnTypes to return LogicalResult and valuesJacques Pienaar2019-12-061-3/+4
* Replace custom getBody method with an ODS-generated in gpu::LaunchOpAlex Zinenko2019-12-061-3/+0
* Move GPU::LaunchOp to ODS. NFC.Alex Zinenko2019-12-062-68/+140
* Use named traits in the ODS definition of LLVMFuncOpAlex Zinenko2019-12-061-3/+1
* [VecOps] Rename vector.[insert|extract]element to just vector.[insert|extract]Aart Bik2019-12-061-10/+10
* LLVM::GlobalOp: take address space as builder argumentAlex Zinenko2019-12-061-1/+2
* Move GPU::FuncOp definition to ODS - NFCAlex Zinenko2019-12-063-82/+141
* Generate builder for ops that use InferTypeOpInterface trait in ODSJacques Pienaar2019-12-061-1/+1
* Add conversions of GPU func with memory attributions to LLVM/NVVMAlex Zinenko2019-12-062-6/+22
* Unroll vector masks along with their associated vector arguments.Andy Davis2019-12-062-29/+18
* LLVM::AddressOfOp: properly take into account the address spaceAlex Zinenko2019-12-061-2/+3
* [Linalg] Add permutation information to tilingJose Ignacio Gomez2019-12-054-9/+51
* Refactor the IRPrinting instrumentation to take a derivable config.River Riddle2019-12-051-8/+55
OpenPOWER on IntegriCloud