About me

I am a PhD student at the Laboratory of Software Technology of ETH Zurich under the supervision of Prof. Thomas R. Gross. My research is about optimizing performance for NUMA-multicore processors by using memory allocation and computation scheduling techniques that are custom-tailored for this class of machines.

I come from Cluj/Klausenburg/Kolozsvár/Claudiopolis/Kloiznburg, Romania. I graduated in 2007 with an engineer's degree in Computer Science at the Technical University of Cluj-Napoca. My diploma project was about integrating a software transaction system into a Java Virtual Machine. After graduation I worked as a network engineer and also as a teaching assistant at the Technical University of Cluj-Napoca. I joined ETH Zurich in 2008.

Publications

Conferences

• Zoltan Majo, Thomas R. Gross. Matching Memory Access Patterns and Data Placement for NUMA Systems. International Symposium on Code Generation and Optimization (CGO 2012).
  [paper] [bibtex] [slides (pptx)]
• Zoltan Majo, Thomas R. Gross. Memory Management in NUMA Multicore Systems: Trapped between Cache Contention and Interconnect Overhead. International Symposium on Memory Management (ISMM 2011).
  [paper] [bibtex] [slides (pptx)] [slides (ppt)]
• Zoltan Majo, Thomas R. Gross. Memory System Performance in a NUMA Multicore Multiprocessor. The 4th Annual International Systems and Storage Conference (SYSTOR 2011).
  [paper] [bibtex] [slides (pptx)] [slides (ppt)]

Workshops

• Zoltan Majo, Thomas R. Gross. A Template Library to Integrate Thread Scheduling and Locality Management for NUMA Multiprocessors. 4th USENIX Workshop on Hot Topics in Parallelism (HotPar 2012).
  [paper] [bibtex] [slides (pdf)]
• Irina Tuduce, Zoltan Majo, Adrian Gauch, Brad Chen, Thomas R. Gross. Asymmetries in Multi-Core Systems -- Or Why We Need Better Performance Measurement Units. The Exascale Evaluation and Research Techniques Workshop (EXERT) at ASPLOS 2010.
  [paper] [bibtex]

Teaching

HS 2012 - Design of Parallel and High-Performance Computing
SS 2012 - Advanced Compiler Design
HS 2011 - Design of Parallel and High-Performance Computing
SS 2011 - Advanced Compiler Design; Research Topics in Software Engineering
HS 2010 - Compiler Design 1
SS 2010 - Parallel Programming
HS 2009 - Parallel Programming Practice
SS 2009 - Parallel Programming
HS 2008 - Software Engineering Seminar

Talks (some of the files are accessible only from inside the ETHZ network)

• May 7, 2012 - Technical University of Cluj-Napoca -- Performance Optimizations for NUMA-Multicore Systems [pptx]
• May 2, 2011 - Apáczai Csere János High School - Multicore Processors: Advantages and Challenges (in Hungarian) [pptx]
• April 26, 2010 - Institute of Computer Systems Seminar - ASPLOS 2010 Trip Report [pdf]
• November 30, 2009 - Institute of Computer Systems Seminar - Memory Bandwidth on the Intel Nehalem

Student Projects

Open Projects

If you are interested in doing a semester/master/diploma project, please look at the list of project proposals. Come and talk to me if you need more information or you have suggestions.

Supervised Projects

• Jonas Oeschger (ongoing): Hardware-supported data locality monitoring
• Otto Bibartiu (ongoing): Memory allocation on NUMA machines
• Shuoran Yang (August 2012): A fast, parallel spanning tree algorithm for NUMA multicore systems
• Ivo Steinmann (September 2011): Evaluating the cost of data migration in a NUMA-multicore architecture
• Ankush Gupta (October 2010): A performance model and its evaluation for Java on a multi-core system

Last updated on: May 30, 2013