Universität Wien FIND

Bedingt durch die COVID-19-Pandemie können kurzfristige Änderungen bei Lehrveranstaltungen und Prüfungen (z.B. Absage von Vor-Ort-Lehre und Umstellung auf Online-Prüfungen) erforderlich sein. Melden Sie sich für Lehrveranstaltungen/Prüfungen über u:space an, informieren Sie sich über den aktuellen Stand auf u:find und auf der Lernplattform moodle. ACHTUNG: Lehrveranstaltungen, bei denen zumindest eine Einheit vor Ort stattfindet, werden in u:find momentan mit "vor Ort" gekennzeichnet.

Regelungen zum Lehrbetrieb vor Ort inkl. Eintrittstests finden Sie unter https://studieren.univie.ac.at/info.

052820 VU Advanced Topics in Parallel Computing (2018S)

Prüfungsimmanente Lehrveranstaltung


Hinweis: Ihr Anmeldezeitpunkt innerhalb der Frist hat keine Auswirkungen auf die Platzvergabe (kein "first come, first serve").


max. 25 Teilnehmer*innen
Sprache: Englisch


Termine (iCal) - nächster Termin ist mit N markiert

Lectures will be given at the beginning in a blocked manner in the time slot April 11 - April 15; afterwards the assignments shall be done.

For questions please contact Eduard Mehofer <eduard.mehofer@univie.ac.at>

Donnerstag 15.03. 11:30 - 13:00 Seminarraum 11, Währinger Straße 29 2.OG (Vorbesprechung)
Mittwoch 11.04. 16:00 - 22:00 Seminarraum 11, Währinger Straße 29 2.OG
Donnerstag 12.04. 16:00 - 22:00 Seminarraum 12, Währinger Straße 29 2.OG
Freitag 13.04. 16:00 - 22:00 Seminarraum 12, Währinger Straße 29 2.OG
Samstag 14.04. 10:00 - 22:00 Seminarraum 12, Währinger Straße 29 2.OG


Ziele, Inhalte und Methode der Lehrveranstaltung

Course title: DataFlow SuperComputing for BigData Analytics

This course analyses the essence of DataFlow SuperComputing, defines its advantages and sheds light on the related programming model. DataFlow computers, compared to ControlFlow computers, offer speedups of 20 to 200 (even 2000 for some applications), power reductions of about 20, and size reductions of also about 20. However, the programming paradigm is different, and has to be mastered. The course explains the paradigm, using Maxeler as an example, and sheds light on the ongoing research, which, in the case of the speaker, was higlhy influenced by four different Nobel Laureates: (a) from Richard Feynman it was learned that future computing paradigms will be successful only if the ammount of communications is minimized; (b) from Ilya Prigogine it was learned that the entropy of a computing system would be minimized if spatial and temporal data get decoupled; (c) from Daniel Kahneman it was learned that the system software should offer options realted to approximate computing; and (d) from Andre Geim it was learned that the system software should be able to trade between latency and precision. The course teaches the programming model details of the Maxeler MultiScale Data Flow Element (DFE) approach, with lots of hands-on examples. It also includes the advanced programming techniques for higher speedup and precision, and for lower power and complexity. The course also examines the Google TPU approach, comparatively with the Maxeler DFE approach. To shed more light on the issues related to speed, precision, power, and complexity, the course also shows relevant aspects of the desing of Control Flow machines like ManyCore or MultiCore.


About the Speaker:

Prof. Veljko Milutinovic (1951) received his PhD from the University of Belgrade, spent about a decade on various faculty positions in the USA (mostly at Purdue University), and was a co-designer of the DARPAs first GaAs RISC microprocessor. Later, for almost 3 decades, he taught and conducted research at the University of Belgrade, in EE, BA, MATH, and PHYS/CHEM. Now he serves as the Chairman of the Board for the Maxeler operation in Belgrade, Serbia. His research is mostly in datamining algorithms and dataflow computing, with the emphasis on mapping of data analytics algorithms onto fast energy efficient architectures. For 7 of his books, forewords were written by 7 different Nobel Laureates with whom he cooperated on his past industry sponsored projects. He has over 40 IEEE journal papers, over 40 papers in other SCI journals (4 in ACM journals), over 400 Thomson-Reuters citations, and about 4000 Google Scholar citations. Short courses on the subject he delivered so far in a number of universities worldwide: MIT, Harvard, Boston, NEU, Columbia, NYU, Princeton, Temple, Purdue, IU, UIUC, Michigan, EPFL, ETH, Karlsruhe, Heidelberg, University of Vienna, Vienna Politechnical University, Napoli, Salerno, Siena, Pisa, etc. Also at the World Bank in Washington DC, BNL, IBM TJ Watson, Yahoo NY, ABB Zurich, Oracle Zurich, etc.

About the TA of the course:

Milos Kotlar (1993) is a PHD student of Computing at the University of Belgrade, with years of professional experiance at ABB in Zurich, Switzerland. He is the author of a number of dataflow implementations in Machine Learning and Tensor Calculus.

Art der Leistungskontrolle und erlaubte Hilfsmittel

assignments and oral exam

Mindestanforderungen und Beurteilungsmaßstab

3 assignments and oral exam positive; grading can be improved by one grade level by 4th assignment


Lecture materials and accompanying literature


Milutinovic, V., et al,
Guide to DataFlow SuperComputing,
Springer, 2015 (one textbook) and 2017 (two textbooks).

Hurson, A., Milutinovic, V., editors,
Advances in Computers: DataFlow,
Elsevier, 2015 (one SCI textbook) and 2017 (two SCI textbooks).

Zuordnung im Vorlesungsverzeichnis

Module: AT-PC

Letzte Änderung: Mo 07.09.2020 15:30