Modeling and Simulation of Invasive Applications and Architectures

ISBN-13: 9789811383892 / Angielski / Miękka / 2020 / 168 str.

Sascha Roloff; Frank Hannig; Jürgen Teich

Spis treści

Introduction.- Fundamentals.- InvadeSIM–A Simulation Framework for Invasive Parallel Programs and Architectures.- Hybrid Network-on-Chip Simulation.- Parallel MPSoC Simulation and Architecture Evaluation.- ActorX10 and Run-Time Application Embedding.- Conclusions and Future Directions.

O autorze

Sascha Roloff is a development engineer for autonomous driving at the Robert BOSCH GmbH and was a researcher at the chair for Hardware/Software Co-Design at the department of computer science at the Friedrich-Alexander Universität Erlangen-Nürnberg (FAU) from 2011 to 2018. He defended his PhD degree on the topic of “Modeling and Simulation of Invasive Applications and Architectures” in July 2018. He received his Diploma degree (Dipl.-Ing.) in Systems of Information and Multimedia Technologies from Friedrich-Alexander Universität Erlangen-Nürnberg (FAU) in 2011. His research interests include parallel and distributed programming models and simulation of heterogeneous many-core architectures including processor, accelerator, and network-on-chip simulation.

Frank Hannig received the Diploma degree in an interdisciplinary course of study in electrical engineering and computer science from the University of Paderborn, Germany, in 2000; the Ph.D. degree (Dr.-Ing.) and Habilitation degree in computer science from Friedrich-Alexander University Erlangen-Nürnberg (FAU), Germany, in 2009 and 2018, respectively.

He has led the Architecture and Compiler Design Group in the Computer Science Department, FAU, since 2004. His primary research interests are the design of massively parallel architectures, ranging from dedicated hardware to multicore architectures, mapping methodologies for domain-specific computing, and architecture/compiler codesign. He has authored or coauthored more than 160 peer-reviewed publications. Dr. Hannig serves on the program committees of several international conferences (ARC, ASAP, CODES+ISSS, DATE, DASIP, SAC). He is a Senior Member of the IEEE and an affiliate member of the European Network of Excellence on High Performance and Embedded Architecture and Compilation (HiPEAC).

Jürgen Teich received the M.Sc. degree (Dipl.-Ing. with honors) from the University of Kaiserslautern, Kaiserslautern, Germany, in 1989 and the Ph.D. degree (summa cum laude) from the University of Saarland, Saarbrücken, Germany, in 1993. In 1994, he joined the DSP design group of Prof. E. A. Lee in the Department of Electrical Engineering and Computer Sciences (EECS), University of California at Berkeley, Berkeley, CA, USA (postdoctoral work). From 1995 to 1998, he held a position at the Institute of Computer Engineering and Communications Networks Laboratory (TIK), ETH Zurich, Zurich, Switzerland (habilitation). From 1998 to 2002, he was Full Professor in the Electrical Engineering and Information Technology Department, University of Paderborn, Paderborn, Germany. Since 2003, he has been Full Professor in the Department of Computer Science, Friedrich-Alexander University Erlangen-Nürnberg (FAU), Erlangen, Germany, holding a Chair in Hardware/Software Co-Design.

Prof. Teich is a Fellow of the IEEE and member of the Academia Europaea. Since 2010, he is the coordinator of the Transregional Research Center 89 on Invasive Computing funded by the German Research Foundation (DFG).

Blurb

This book covers two main topics: First, novel fast and flexible simulation techniques for modern heterogeneous NoC-based multi-core architectures. These are implemented in the full-system simulator called InvadeSIM and designed to study the dynamic behavior of hundreds of parallel application programs running on such architectures while competing for resources. Second, a novel actor-oriented programming library called ActorX10, which allows to formally model parallel streaming applications by actor graphs and to analyze predictable execution behavior as part of so-called hybrid mapping approaches, which are used to guarantee real-time requirements of such applications at design time independent from dynamic workloads by a combination of static analysis and dynamic embedding.