SI
SI
discoversearch

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor.  We ask that you disable ad blocking while on Silicon Investor in the best interests of our community.  If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.
Technology Stocks : All About Sun Microsystems -- Ignore unavailable to you. Want to Upgrade?


To: QwikSand who wrote (44365)8/4/2001 3:58:00 PM
From: Prognosticator  Respond to of 64865
 
Ok...so the point remains that applications don't really have "inherent" thread-level parallelism in the sense that it happens without the programmer knowing or caring about it, as instruction-level parallelism does in Itanic. To take advantage of thread-level parallelism, an application has to be built that way. That means that, for example, the advantages of USV architecture would indeed extend to a C++ program that was coded using, e.g., pthreads. Java isn't the only language that can take advantage of this architecture, it's just easier to develop concurrent programs in Java.

Perfectly stated.

Extrapolating recent performance, it will be remarkable if and when Sun and TI/ whoever get this device built and shipping. How do you get good yield on a single wafer with 1000 complex processor cores on it...put 2,000 cores on it and expect half of them to be bad??? Dat'sa some spicy interconnect!

Yes. The beautiful thing about server software is that it is inherently I/O limited. So, you have 500 CPU's handling the disk/network interface, each of them running multiple threads, not really talking with each other. The other 500 can be busy building and parsing database queries, which are being handled by other CPU-modules and their multiple processors. In other words, server software, especially written in Java, scales.

And I don't agree that they have until 2010, because 10 years in the computer business is beyond anyone's predictable event horizon.

Not me. I can predict perfectly 10 years out. That's why I'm rich, living on this archipeligo that I purchased with my gains from the last 10 years. Actually, much less will change in 10 years than you think. Remember the previous 10. I was using the Internet 10 years ago, and it hasn't changed much since then, other than the public perception and user-level.

But if they actually manage to do it in some reasonable timeframe like five years, while Intel follows the risky Itanic route, I agree this USV thing could be a win of proportions that Wall Street analysts certainly don't comprehend (not that they comprehend much of anything).

Agreed about WallStreet. They just don't get much about technology, to them HP and SUN are like Proctor and Gamble/Unilever: different companies producing different brands of the same soap powder.

P.



To: QwikSand who wrote (44365)8/4/2001 9:41:52 PM
From: Charles Tutt  Read Replies (1) | Respond to of 64865
 
Another way programs in general can benefit from multithreading is if the JVM itself is multithreaded. Anything done to speed up the JVM also speeds up the programs run under it. This is similar to your comment about the OS being multithreaded benefiting applications.

There has been some work done re interconnecting wafer scale integration after testing to determine where the defects are. I don't have a link to offer you.

JMHO.

Charles Tutt (TM)