Global Sources
EE Times-Asia
Stay in touch with EE Times Asia
?
EE Times-Asia > FPGAs/PLDs
?
?
FPGAs/PLDs??

Sun evangelist, social activist

Posted: 02 Jan 2006 ?? ?Print Version ?Bookmark and Share

Keywords:loring wirbel? ee times? sun microsystems? sun? john gage?

Sun Microsystems Inc. co-founder John Gage holds the title of chief researcher, allowing him to explore advanced computing and networking concepts on a cross-corporate, cross-academic basis one day, while advocating social-policy goals the next. As a social-policy advocate, Gage plays positivist foil to the dark musings of fellow co-founder Bill Joy, Sun's chief scientist, who fears the implications of runaway technology. Gage comes across as a no-nonsense humanitarian, engaged in efforts for education, poverty relief and digital literacy in the developing world. He is gregarious enough to make friends wherever he goes, but sober enough to know he must be a realistic ambassador for his company at a time when Sun is involved in the first survival struggle in its 20-year history. EE Times sat down with Gage before the executive's speech at the National Association of Broadcasters (NAB) conference.

EE Times: What has captured your interest in Sun's R&D teams?
John Gage: There are interesting implications to bringing back Sun co-founder Andy Bechtolsheim to work on Opteron architectures as chief architect and VP for network systems. Andy's not only responsible for the new Opteron-based server line, but he's been looking at multiprocessing Opteron architectures for video streaming, combining the servers with 48 500GB drives in a single system for multiple terabytes on the desktop. There's more here than meets the eye. Andy and Dick Sillman are working on a very clever streaming device and on a redundancy mechanism that is much better than RAID arrays. In theory, their work could give you permanent, perfect storage.
We also have some interesting work coming on the processor side. Niagara [the 32-thread, 8-core Ultrasparc engine] represents the ultimate Ultrasparc gain realized by concepts such as multithreading. We think we can show some significant advantages in overall heat dissipation in large systems, vs. server clusters based on something like Intel's Itanium.
Beyond that, we took a clean-slate approach to come up with Rock, which will abandon deep pipelines, out-of-order execution and anything else that makes a CPU subsystem needlessly complex. Rock is the design effort within Sun to go back to Sparc simplicity.

Everyone at NAB this year was talking about content management. How do you view emerging content-description efforts?
We're very interested in some industry projects, such as WGBH-Boston's metadata project on developing a standard for describing what's held in a digital-media repository. I'm still waiting to see more efforts to tie this kind of asset management into the communications network and what the hardware vendors are doing to define the metadata at the moment of image creation.

Your NAB speech goes to one of the more conservative broadcast sectors, the radio industry. What do you plan to tell them?
I'll make a lot of points about digital radio changing the way we think about spectrum ownership and how most traditional broadcasters still haven't left the world of 'this is mine and you can't have my spectrum.' It's also present in the TV broadcast world, but at least the switch from analog to SD [standard-definition] and HDTV broadcast has gotten the TV industry to think about the power of spectrum reuse. The impact of technology changes such as spread-spectrum has not been recognized in the radio industry at large and the subtlety possible in allocating spectrum certainly hasn't been recognized in the legal domain.
Some new technologies are catching most players by surprise. At the NAB Futures Conference in March 2005, Paul Jacobs of the Qualcomm wireless Internet group made a presentation on the new MediaFlo technology. He told the audience, 'Look, we're buying towers in metro areas and acquiring spectrum to send video to cellphones, but you needn't think we're going to compete with you.' The NAB attendees were really livid, saying that Jacobs hadn't been truthful about interference issues in the past, as usual.

What's the genesis of the residential access box you're showing at NAB? You say it could theoretically drop the cost of a multistream home gateway from $300 to $30.
It's very much related to Bechtolsheim's and Sillman's massive array of disks, the terabytes-on-the-desktop effort. Glenn Edens, who is going to head our media and entertainment effort, was fooling around with some related projects, catching the usual engineering bug of saying, 'OK, what can we do with this?' Sillman, who had a background with WebTV, had been toying with these little Opteron boards, and he and Glenn were trying to define what could be done in very tiny Java Virtual Machines.
Our own interests were turning toward metadata and ways of characterizing the content, but we were tying that to an effort on the client end to take streaming-video input and decode the Internet Protocol packets on the fly.
It's not really Sun's direct business to try making little home devices. We want to push the technology, but we're not just being altruistic. We want to drive the massive-storage concept for servers.

You've been an evangelist for Sun as it's endured some tough quarters.
I was thinking about the whole 'love is blind' thing that people have with their own loyalties to companies and architectures. We can see larger trends in the server and workstation fields that can affect Sun. The whole effort at promoting Java, at opening up software, has always been about not getting into a rut. But we have to examine our own mistakes, even when loyal customers are willing to give us a pass.
I like to think about this detrace analytical technology that lets you see what a program is doing internally. It really startles the Linux people, who often assume that their code is already as optimized as possible. We've spotted plenty of problems in our own implementations of both hardware and Solaris services over time.

You've been very aware of civil-liberties issues over the years, yet the metadata concepts and distributed-storage architectures you're working on seem tailor-made for intelligence community projects.
We're engaged with many of the agencies and we realize this is a double-edged sword. Information is being collected and collated everywhereintelligence agencies, credit bureaus and even individuals. It's going to get worse as RFID becomes another element in metadata analysis. However, the only way you can intelligently talk about preserving some kind of privacy rights is to be totally informed and honest about capabilities. I can see us coming to a point where even minor personal misrepresentations become impossible. Look at simple things like electronic tags for toll roads and bridges. Soon, there will be nowhere to hide.

- Loring WirbelEE Times




Article Comments - Sun evangelist, social activist
Comments:??
*? You can enter [0] more charecters.
*Verify code:
?
?
Webinars

Seminars

Visit Asia Webinars to learn about the latest in technology and get practical design tips.

?
?
Back to Top