Vlad Slavici
Email: vslav at ccs dot neu dot edu
370 West Village H (the High-Performance Computing Lab)
College of Computer and Information Science
Northeastern University
Boston, MA
I am a PhD student in the College of Computer and Information Science
at Northeastern University. My advisor is Gene Cooperman.
Research
My main research area is Large Scale Computing, mostly Parallel Disk-based Computing.
I am interested in efficient solutions which scale up well for space-limited problems. In my research,
scaling up is closely related to Gustafson's Law.
For scaling up
beyond available RAM to parallel disks as main memory I mostly use Roomy, a
free open-source C/C++ library for parallel disk-based computing developed by Daniel Kunkle.
I am also working on efficient multi-threaded algorithms for shared-memory machines.
Publications
- Fast Multiplication of Large Permutations for Disk, Flash Memory and RAM
Vlad Slavici, Xin Dong, Daniel Kunkle and Gene Cooperman
in Proceedings of the International Symposium on Symbolic and Algebraic Computation (ISSAC '10), Munich, Germany, 355-362, 2010. [pdf]
- Parallel Disk-Based Computation for Large, Monolithic Binary Decision Diagrams
Daniel Kunkle, Vlad Slavici and Gene Cooperman
in Proceedings of the International Workshop on Parallel Symbolic Computation (PASCO '10), Grenoble, France, 63-72, 2010. [pdf]
Internships
I was an intern at Akamai Technologies in Cambridge, MA during the Summers of 2009 and 2010.
Here is a brief description of my work at Akamai:
- Developed unit and regression tests for nameservers security features.
- Developed software for gathering statistics about source port randomization in nameservers
around the world (related to the Kaminsky bug).
- Developed simulation, diagnosis and testing tools for nameservers performance.
In the Summer of 2007, I was an intern at Boston Virtual Imaging in Boston, MA,
where I worked on a GUI (implemented as a Java applet) for designing postcard-like documents.