There is currently a large number of data programming models and their respective frontends such as relational tables, graphs, tensors, and streams. This has lead to a plethora of runtimes that typically focus on the efficient execution of just a single frontend. This fragmentation manifests today into highly complex pipelines that bundle multiple runtimes to support the necessary models. Hence, joint optimisation and execution of such pipelines across these frontend-bound runtimes is infeasible. We propose Arc as the first unified Intermediate Representation (IR) for data analytics that incorporates stream semantics based on a modern specification of streams, windows and stream aggregation, to combine batch and stream computation models. Arc extends Weld, an IR for batch computation, and adds stream interoperability as a natural extension to describe static computational graphs suitable for stream processing.
Sun 23 Jun Times are displayed in time zone: Tijuana, Baja California change
11:20 - 11:40 Talk | Streaming saturation for large RDF graphs with dynamic schema information DBPL Mohammad Amin FarvardinPSL, Université Paris-Dauphine, LAMSADE, Dario Colazzo, Khalid BelhajjamePSL, Université Paris-Dauphine, LAMSADE, Carlo Sartiani | ||
11:40 - 12:00 Talk | Arc: An IR for Batch and Stream Programming DBPL Lars KrollKTH Royal Institute of Technology, Sweden, Klas SegeljaktKTH, Paris CarboneKTH, Sweden, Christian SchulteKTH Royal Institute of Technology, Sweden, Seif Haridi Pre-print Media Attached | ||
12:00 - 12:20 Talk | Towards Compiling Graph Queries in Relational Engines DBPL Ruby TahboubPurdue University, Xilun WuPurdue University, Gregory Essertel, Tiark RompfPurdue University |