MLIR

Multi-Level Intermediate Representation OverviewThe MLIR project is a novel approach to building reusable and extensible compiler infrastructure. MLIR aims to address software fragmentation, improve compilation for heterogeneous hardware, significantly reduce the cost of building domain specific compilers, and aid in connecting existing compilers together. Weekly Public MeetingWe host a weekly pub

[rawwell]

“The ability to represent dataflow graphs (such as in TensorFlow), including dynamic shapes, the user-extensible op ecosystem, TensorFlow variables, etc.”