summaryrefslogtreecommitdiff
path: root/mlir/lib/Conversion/VectorToGPU/VectorToGPU.cpp
AgeCommit message (Expand)Author
2023-02-14[mlir][Vector] Significantly improve VectorToGPU.cppNicolas Vasilache
2023-02-14[mlir][gpu] Add support for unsigned integer extend in vector to gpu.subgroup...Quinn Dawkins
2023-02-09[mlir] Handle different pointer sizes in unranked memref descriptorsKrzysztof Drewniak
2023-02-09Add generic type attribute mapping infrastructure, use it in GpuToXKrzysztof Drewniak
2023-02-07[mlir][gpu] Add support for integer types in gpu.subgroup_mma opsQuinn Dawkins
2023-01-19[mlir] Update VectorToGPU to new memory spaceThomas Raoux
2022-12-15[mlir][VectorToGPU] Support transposed+broadcasted 2D MMA loadLei Zhang
2022-12-15[mlir][VectorToGPU] Support transposed+broadcasted 1D MMA loadLei Zhang
2022-12-05[mlir] List more elementwise ops in VectorToGPU MMA conversionLei Zhang
2022-12-05Support `transpose` mode for `gpu.subgroup` WMMA opsNavdeep Katel
2022-12-04[mlir] Use std::nullopt instead of None in comments (NFC)Kazu Hirata
2022-12-03[mlir] Use std::nullopt instead of None (NFC)Kazu Hirata
2022-12-01Revert "[WIP] Add support for MMA conversion for 1-D vector.transfer followed...Nicolas Vasilache
2022-12-01[WIP] Add support for MMA conversion for 1-D vector.transfer followed by a br...Nicolas Vasilache
2022-11-29[mlir][gpu] Adding support for transposed mma_load_matrixQuinn Dawkins
2022-11-27mlir/VectorToGPU: use std::optional (NFC)Ramkumar Ramachandra
2022-11-21Merge kDynamicSize and kDynamicSentinel into one constant.Aliia Khasanova
2022-11-06Apply clang-tidy fixes for llvm-else-after-return in VectorToGPU.cpp (NFC)Mehdi Amini
2022-10-19[mlir][NVGPU] Handle native mma.sync and ldmatrix(x4) sizesManish Gupta
2022-10-05[mlir][nvgpu] NFC - move NVGPU conversion helpers to NvGpu utils libraryChristopher Bate
2022-09-29[mlir][arith] Change dialect name from Arithmetic to ArithJakub Kuderski
2022-09-18[mlir] Use empty (NFC)Kazu Hirata
2022-09-12[mlir] Change IteratorType in ContractionOp in Vector dialect from string to ...Oleg Shyshkov
2022-08-31[MLIR] Update pass declarations to new autogenerated filesMichele Scuttari
2022-08-30Revert "[MLIR] Update pass declarations to new autogenerated files"Michele Scuttari
2022-08-30[MLIR] Update pass declarations to new autogenerated filesMichele Scuttari
2022-08-01[mlir][NVGPU] nvgpu.mmasync on F32 through TF32Manish Gupta
2022-07-31[mlir] Remove types from attributesJeff Niu
2022-07-19[mlir] Flip LinAlg dialect to _BothJacques Pienaar
2022-06-30[mlir][VectorToGPU] Fix support for i4, col-major operand supportChristopher Bate
2022-06-20Don't use Optional::hasValue (NFC)Kazu Hirata
2022-06-20[mlir] move SCF headers to SCF/{IR,Transforms} respectivelyAlex Zinenko
2022-06-17[mlir][nvgpu] shared memory access optimization passChristopher Bate
2022-06-09[mlir][gpu] Move GPU headers into IR/ and Transforms/Mogball
2022-06-03[mlir][VectorToGPU] Fix bug generating incorrect ldmatrix opsThomas Raoux
2022-05-20[MLIR][GPU] Add NvGpu mma.sync path to the VectorToGPU passChristopher Bate
2022-03-28[mlir] Flip Vector dialect accessors used to prefixed form.Jacques Pienaar
2022-03-25[mlir][gpu] Relax restriction on mma load/store opThomas Raoux
2022-03-08[mlir] Update FuncOp conversion passes to Pass/InterfacePass<FunctionOpInterf...River Riddle
2022-01-31[mlir][vector][NFC] Split into IR, Transforms and UtilsMatthias Springer
2022-01-27[VectorToGPU] Fix horizontal stride calculation for N-D memrefThomas Raoux
2022-01-19[mlir] Make locations required when adding/creating block argumentsRiver Riddle
2022-01-18[mlir][Pass] Deprecate FunctionPass in favor of OperationPass<FuncOp>River Riddle
2022-01-02Apply clang-tidy fixes for performance-for-range-copy to MLIR (NFC)Mehdi Amini
2022-01-02Apply clang-tidy fixes for readability-simplify-boolean-expr to MLIR (NFC)Mehdi Amini
2021-12-20[mlir] Switching accessors to prefixed form (NFC)Jacques Pienaar
2021-12-01[mlir][Vector] Thread 0-d vectors through vector.transfer opsNicolas Vasilache
2021-11-15[mlir] Move min/max ops from Std to Arith.Alexander Belyaev
2021-11-11[mlir][VectorToGPU] Support more cases in conversion to MMA opsThomas Raoux
2021-11-09[mlir] Remove the non-templated DenseElementsAttr::getSplatValueRiver Riddle
generated by cgit v1.2.3 (git 2.25.1) at 2026-06-08 00:57:23 +0000