Roman Shaposhnik's

With every single IT publication now explaining the difficulty of parallelism and multithreaded programming, one has to wonder why do we have to go to all this trouble of managing multicore in software. Isn't it all just a manifestation of a desperate hardware industry trying to ram surplus of transistors down developer's throats much the same way industrial agriculture rams the surplus of crops? Are multicore chips going to be as much a damage to your brain as soft drinks (AKA liquid corn) are a damage to your stomach? And finally, is there a better way? In other words, what is the ethanol revolution of the hardware industry?[Read More]

I've just got back from a conference dubbed by most of my friends as Russian Super Computing and I must say that it was quite an event. Lots of people asking lots of really good technical questions on what Sun is doing about HPC in Russia and what is our strategy in general. The most curious question, however, happened to be non-technical at all. A guy asked me what's the best thing about Sun and what's the worst thing about Sun. And you know what, the answer to both parts of this question happens to be the same one. You can't beat the euphoria feeling you get from being able to work with the guys who could crank up something like that in 1992. That's the best part. The worst one? Well, how about sales/marketing/etc who couldn't sell something like that till iPhone happened to be announced some 15 years later. But hey -- I'm an engineer and Sun is my eternal playground. Why, I can even forgive the sales guys -- at least they didn't turn Duke into something like Bob.