OK, I’m back from vacation in Oregon, and while I promised to bore everyone catching up on old news, I think that news will still be old later — Better to start with some new news.
It’s time to leak some information about the Digipede Network Version 2.0, coming this summer to a grid near you.
Never mind that we’re plagued by the same version-number inconsistency that affects every other software company (and yes, our most recent release really is called 1.3.2f; want to make something of it?) — this is the Summer of 2.0.
We’ve been chewing away on suggestions (ranging from obvious to brilliant) brought forth by our customers, partners, prospects, and fans over the past several months, and the new release will have something for everybody.
Shortly after we brought out 1.3, I wrote here that this release was about “developers, developers, developers.” And it was. And it is. And it shall be to come. It’s no secret now that the secret sauce of the Digipede Network is in the way we make it drop-dead simple for developers to adapt real-world applications to a grid — without changing programming paradigms or development tools.
So first and foremost — you’ll see more of the same. Developers get more ways to manipulate pools of compute resources, more development patterns for definition of jobs and tasks, more code samples to jump-start their own applications — more of the best SDK in the business.
Second, you’ll see the evolutionary new Digipede Control. Yes, it’s familiar — but it’s more powerful, with new ways for administrators to work with larger groups of Digipede Agents, users, and applications. As we work with customers with larger and larger grids, we’re constantly improving overall manageability; 2.0 will continue this trend, and so will 2.1, and 2.3.2f.
Third, you’ll see your results even faster. You’ll see lower latency throughout the system, improving performance on short tasks significantly. And with more clever options for taking advantage of multiple cores, broad classes of applications can now see even greater performance increases with very little effort.
Fourth, you’ll see even more integration with Microsoft products. You’ll be able to schedule jobs directly from the Digipede Network onto a Windows CCS cluster via the CCS Job Scheduler (nice). You’ll have a Visual Studio plug-in that allows debugging of a master application and a distributed application all on a single machine (sweet). And — well actually, there’s lots more, but why give it all away now? I’ll have more to say as we get closer to a release date.