The demise of scaling laws in micro-electronics has led to an era of innovation in software and hardware architectures aimed at improving the energy efficiency of computing systems. This talk discusses programming models and software abstractions that help cope with demanding applications with stringent constraints on highly heterogeneous and emerging computing systems. Concretely, we describe dataflow and actor-based abstractions along with an optimization methodology for baseband processing. Dataflow and actor-based programming models are key to coordinate the execution of software components. To optimize data-centric components, the talk describes high-level abstractions, transformations and a code generation for emerging in- and near-memory computing systems.
September 6 @ 09:25
09:25 — 10:05 (40′)
Professor Jeronimo Castrillon (TU Dresden)