I just watched this the other day - http://www.youtube.com/watch?v=J9kobkqAicU Cray-1 Supercomputer 30th Anniversary. I would give up my career and turn it around if given a chance to work in HPC.
What part of HPC would you like to work in? I have some contact with various HPC facilities but have never envied the people who work there -- they're just sysadmins who happen to work in larger, noisier server rooms than most.
Well, I'm just one of those sysadmins (but the clusters on
which I work are much more smaller than the 'monsters' in
the top500). I don't know if someone could envy me but there are surely other things apart the noise of HVAC
systems (by the way we are using remote console when
possible :-)).
How about working with a lot of different computer nodes combining them with a fast network (Infiniband) and
exporting the storage space through the cluster with a
parallel file system?
How about optimizing every aspect of the software
installation (OS, compilers, scientific libraries)
to give your users the best resources to run their simulations (biophysicist, electrical engineers, etc.)?
To not to mention follow the aspects regarding the structure of the data center: cooling systems, UPS,
raised floors, etc.? It doesn't sound too bad to me :-)
Thanks, but I doubt I will ever be so lucky, especially considering even if I did have an opportunity I'd probably lack in experience needed for such a job. Anyways, while fantasizing, my dream job would be to work in r&d on building those HPC machines (software and system wise, algos especially, not EE), or writing/optimizing code that runs on them, especially vector processing units. My area of interest is graphics research.
I'm curious about the applications of these systems. Why is it that finance would be the third largest (known) group for supercomputer use? What kind of number crunching would they be doing?
How does that relate to finance? I know that protein folding involves massive computation, as it was what our university cluster was being used for 40% of the time.
Consolidation of multi-dimensional hierarchical data can be surprisingly compute intensive. Combine that with VaR calculations etc. then it doesn't surprise me that serious kit is required.
That is: you look at the historical prices of all commodities over time and try to figure out which ones tend to vary together (eg copper-mining companies go up when copper prices go up... but you're looking for less obvious examples than that). Then you look at whether current prices diverge from these trends at all, and if they do you buy/sell accordingly. At least, that's the handwavey version I know -- I'm sure whatever they're doing at Rennaisance and DE Shaw is something I don't even know about.
Not a lot of it is statistical arbitrage - yes this is what Rennaisance and D.E. Shaw do, but this is not what banks (sans perhaps Goldman Sachs) devote much of their compute power to. It's just too hard to make money doing this compared to more traditional activities like market making.
As stated, risk management is a big application: VaR and market stress scenarios are computationally intensive, particularly for portfolios with path-dependent derivatives. Pricing is the other big application: it is similarly computationally intensive to value derivatives against the market-implied term structure of volatility.
While the supercomputers themselves are interesting, I really like graphic. I think it displays the information in a more clear and compelling way compared to something like a stacked column chart, like http://www.highcharts.com/demo/?example=column-stacked&t..., which would just be too busy with a lot of information.
22 comments
[ 3.6 ms ] story [ 54.1 ms ] threadSome derivative pricing models require a lot of cycles.
That is: you look at the historical prices of all commodities over time and try to figure out which ones tend to vary together (eg copper-mining companies go up when copper prices go up... but you're looking for less obvious examples than that). Then you look at whether current prices diverge from these trends at all, and if they do you buy/sell accordingly. At least, that's the handwavey version I know -- I'm sure whatever they're doing at Rennaisance and DE Shaw is something I don't even know about.
As stated, risk management is a big application: VaR and market stress scenarios are computationally intensive, particularly for portfolios with path-dependent derivatives. Pricing is the other big application: it is similarly computationally intensive to value derivatives against the market-implied term structure of volatility.