Nis 2017
Short Course in Dataflow Programming

Short Course in Dataflow Programming
April 6-8, 2017 (10hrs)

Place: Computer Engineering Building, North Campus, Boğaziçi University


Big data analytics, deep learning, oil and gas, finances and scientific computing applications are compute, data  and memory intensive  and require energy efficient data centers and supercomputers. Dataflow Computing is a well-known paradigm which has been popular recently due to high-performance energy-efficient computing requirements of today's data centers and supercomputers. DataFlow computers, compared to ControlFlow computers, offer speedups of 20 to 200 (even 2000 for some applications), power reductions of about 20, and equipment size reductions of also about 20. However, the programming paradigm used on such systems, called spatial programming,  is different, and has to be mastered. Maxeler Dataflow Supercomputers are currently used in various applications by commercial companies such as Amazon AWS, Hitachi Data Systems, JP Morgan, etc. A recent study from Tsinghua University in China is presented, which reveals that, for Shallow Water Weather Forecast (a BigData problem), on the 1U level, the Maxeler DataFlow machine is 14 times faster than the Tianhe machine, rated #1 on the Top 500 list (based on Linpack, which is a smalldata benchmark). In this short course, Prof Veljko Milutinovic will teach Dataflow Programming on Maxeler Dataflow Supercomputer with several in-class examples and hands-on programming practices.


Prof. Veljko Milutinovic (Member of Academia Europaea, Life Member of ACM, Fellow Member of IEEE) 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. Now, he serves as the Chairman of the Board for the Maxeler operation in Belgrade, Serbia. His recent research is mostly on datamining algorithms and dataflow computing, with emphasis on mapping of data analytics algorithms onto fast energy efficient architectures. Forewords of his seven books were written by seven 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. He delivered short courses on the dataflow computing subject  at various universities worldwide including MIT, Harvard, Boston, NEU, Columbia, NYU, Princeton, Temple, Purdue, IU, UIUC, Michigan, EPFL, ETH, Karlsruhe, Heidelberg and also at the World Bank in Washington DC, BNL, IBM TJ Watson and Yahoo.

Course Outline:

April 6, 15:00-16:50 Dataflow Computing Basics/Maxeler Dataflow 

April 7, 09:00-10:50 Q&A session

April 7, 11:00-12:50 Programming Maxeler Dataflow Supercomputer

April 8, 09:00-10:50 Hands-on Exercises

April 8, 11:00-12:50 Design and Assignments


Even though the course is free of charge, registration is mandatory for organizational requirements. Please fill this form:


All attendants should come with their Internet-enabled laptop computers. 


Accompanying Papers and Textbooks of the Lecturer

Trifunovic, N., Milutinovic, V., et al,

The for BigData SuperComputing,

Journal of Big Data, Springer, 2016.

Milutinovic, V., et al,

Guide to DataFlow SuperComputing,

Springer, 2015 (textbook).

Hurson, A., Milutinovic, V., editors,

Advances in Computers: DataFlow,

Elsevier, 2015 and 2017 (textbooks).

Trifunovic, N., Milutinovic, V. et al,

Paradigm Shift in SuperComputing: DataFlow vs ControlFlow,

Journal of Big Data, 2015

Jovanovic, Z., Milutinovic, V.,

"FPGA Accelerator for Floating-Point Matrix Multiplication,"

The IET Computers and Digital Techniques Premium Award for 2014,

Volume 6, Issue 4, 2012 (pp. 249-256).

Flynn, M., Mencer, O., Milutinovic, V., at al,

Moving from PetaFlops to PetaData,

Communications of the ACM, May 2013.

Trobec, R. Vasiljevic, R., Tomasevic, M., Milutinovic, V., et al,

"Interconnection Networks for PetaComputing,"

ACM Computing Surveys, November 2016.