I came across this article this morning and was thinking about other applications of offloading computations to the GPU.  I previously looked at the PS3, and the possibility of an Erlang cluster of PS3s; the problem was the lack of RAM.  That killed it for the PS3, to run enough green processes, Erlang’s memory requirements would have saturated ran and paging would kill performance.  On a high end GPU there is a bunch of RAM.  I’ll look into CUDA and potential Erlang ports to CUDA.  I guess another possibility is dispatching semi complex jobs using Erlang, that way you inherit the error processing capabilities of Erlang and then dispatching jobs written in CUDA to the GPUs (Or maybe I’m just over engineering a solution to a problem I don’t have).

A programmer on Edwards’ staff suggested trying to run the models on graphics processing units (GPUs). (GPUs or graphics cards are specialized chips that run inside PCs to display 2D and 3D graphics. They tend to contain hundreds of floating point processors that are good at handling mathematically intensive and parallel processes such as Monte Carlo simulations.) The programmer ran a proof of concept in March 2008 using the cash flow generation part of the algorithm and showed a dramatic increase in performance. That programmer now runs the team of technologists that work on the bond pricing system.

Show me more… »

Tags: Bonds,CUDA,erlang,GPU,parallel computing,PS3,Wall St
Categories: Technology
No Comments »

So Dunxu came through, he had a project idea.  Its a pretty awesome idea too!  Not that I’ll share it with you yet, but you will see it eventually.  Now instead of going out at night, I’ll just be hacking away at my desk.  It will definitely save me money, I guess I’ll still show up at the analyst happy hours.  (And pretty much whenever my friends go out…)

Technologies I’m planning on using in one place or another:

ruby on rails – web frontend, so far its pretty easy to hack in…

erlang – powering some more compute intensive operations using mapreduce potentially spawned over a compute grid, but only if the site takes off.

python – because why not, its fast enough and plays well with others, its my project and I’ll hack it together however I want!

Amazon AWS – eventually…

memcached – used pretty much everywhere, databases are too slow for popular lookups…

Some database system, but I’m not sure which yet, but it will be behind the cache.  I’m thinking maybe ErlyDB or CouchDB.  As I said earlier, its my project and I’ll hack it together however I want.

Show me more… »

Tags: Amazon AWS,CouchDB,erlang,ErlyDB,Facebook Auth,JSON,MapReduce,Memcached,OpenID,python,Ruby,Ruby on Rails,SOA,SOAP
Categories: Technology
No Comments »

Ok, so anyone who knows me, knows that I’m a hacker at heart.  I love hacking out new projects, and learning a few lessons from them.  Then I usually start tweaking them, lose interest, and move onto something else (e.g. Biographiki, College-Ink, My various attempts at timesharing router labs…)

So here are my technology ideas:

erlang – Yes, Liron – I am finally coming around and I’ll admit that erlang is pretty awesome.  Its massively scalable and who doesnt love functional programming…  Erlyweb seems like the framework to use, ErlyDB is probably my best bet too.  Maybe something p2p.

oCaml – Its the best ML .  Once again, who doesn’t love functional programming…

python – Its fast enough, and really fast to code in.  I like how indentation actually matters.  I’ve heard good things about django, and can run it on Google’s App Engine.  (I’m getting sick of hearing the word app though, Apple ruined it)

Show me more… »

Tags: Amazon,erlang,hacking,hadoop,Ocaml,projects,software engineering
Categories: Technology
No Comments »