From Idit Keidar who has had a great run as the editor for the SIGACT DC column.
The September Distributed Computing column includes:
– Spanner’s concurrency control by Dahlia Malkhi and Jean-Philippe Martin
– Fault tolerant transaction architectures by Ittay Eyal
Columns are archived at:
http://webee.technion.ac.il/~idish/sigactNews/
http://people.csail.mit.edu/idish/sigactNews
This is my last distributed computing column, after six exciting and enjoyable years. I would like to take this
opportunity to thank the many authors who contributed articles over these years. I couldn’t have done
it without you!
I also wish Jennifer Welch, who replaces me, that her tenure as editor will be at least as enjoyable as mine was.
Filed under: Uncategorized | Tags: Byzantine agreement, spectral, theory
Accepted papers for SODA 2014 are now published. Valerie King and I have a paper there on Faster Agreement via a Spectral Method for Detecting Malicious Behavior. This is one of the first papers that I know of that uses a spectral approach to solve a problem in reliable distributed computing. Slides from an early talk on the research in this paper are available on my web page.
Filed under: Uncategorized | Tags: distributed computing, high performance computing, theory
I recently returned from a visit to Oakridge National Lab’s Computer Science and Math Division. I gave a talk there on “Building a Reliable System out of Unreliable Components”. A few observations from my trip:
- It was nice to see a significant UNM presence at Oak Ridge. Barney Maccabe, a former Professor at UNM, is the division director. James Horey and Manju Venkata are two former UNM PhD students who now work as researchers in the division. It’s always nice to visit a place where there are familiar faces.
- It was great to talk to a large number of HPC researchers, and get an update on the state of the art. I learned that silent faults where single bits are flipped are now the most common faults, occurring at a rate of about 1 per hour. The trend in HPC of trying to reduce power to individual gates suggests that this rate will only increase.
- I heard that there are many postdoc opportunities at ORNL, and not enough qualified applicants. This mystifies me since the lab seems like a great place to work. I certainly met many smart, productive people who seemed happy to work there.
- ORNL is distinguished as the only national lab that allows deer and turkey hunting on the grounds. I wonder when Los Alamos will follow its lead?
Cultivating Your Research Taste
This is a thoughtful article on how to cultivate good taste in doing research problems. Determining what makes “exciting” research problems is probably one of the most crucial skills that a PhD student should learn. I think this is a skill that most frequently divides the average researchers from the truly exceptional.
Machinations 