Posted on 06/27/2007 11:50:49 AM PDT by LibWhacker
A prototype of what may be the next generation of personal computers has been developed by researchers in the University of Maryland's A. James Clark School of Engineering. Capable of computing speeds 100 times faster than current desktops, the technology is based on parallel processing on a single chip.
Parallel processing is an approach that allows the computer to perform many different tasks simultaneously, a sharp contrast to the serial approach employed by conventional desktop computers. The prototype developed by Uzi Vishkin and his Clark School colleagues uses a circuit board about the size of a license plate on which they have mounted 64 parallel processors. To control those processors, they have developed the crucial parallel computer organization that allows the processors to work together and make programming practical and simple for software developers.
"The single-chip supercomputer prototype built by Prof. Uzi Vishkin's group uses rich algorithmic theory to address the practical problem of building an easy-to-program multicore computer," said Charles E. Leiserson, professor of computer science and engineering at MIT. "Vishkin's chip unites the theory of yesterday with the reality of today."
Desktop Parallel Processing
Parallel processing on a massive scale using numerous interconnected chips or computers has been used for years to create supercomputers. However, its application to desktop systems has been a challenge because of severe programming complexities. The Clark School team found a way to use single chip parallel processing technology to change that.
Vishkin, a professor in the Clark School's electrical and computer engineering department and the University of Maryland Institute for Advanced Computer Studies (UMIACS), explained the advantage of parallel processing like this: "Suppose you hire one person to clean your home, and it takes five hours, or 300 minutes, for the person to perform each task, one after the other," Vishkin said. "That's analogous to the current serial processing method. Now imagine that you have 100 cleaning people who can work on your home at the same time! That's the parallel processing method.
"The 'software' challenge is: Can you manage all the different tasks and workers so that the job is completed in 3 minutes instead of 300?" Vishkin continued. "Our algorithms make that feasible for general-purpose computing tasks for the first time."
Vishkin and his team are now demonstrating their technology, which in future devices could include 1,000 processors on a chip the size of a finger nail, to government and industry groups. To show how easy it is to program, Vishkin is also providing access to the prototype to students at Montgomery Blair High School in Montgomery County, Md.
From Theory to Reality
For years, the personal computer industry achieved advancements in computer clock speed, the fundamental rate at which a computer performs operations, thanks to innovations in chip fabrication technologies and miniaturization. Moore's Lawwhich dictates that the number of transistors on integrated circuits in computers will double every 18 to 24 monthswas coupled with a corresponding improvement in clock speed.
But no advancements in clock speed have been achieved since 2004. From an early stage, Vishkin foresaw that Moore's Law would ultimately fail to help improve clock speed due to physical limitations. This has guided his perseverance over his professional career in seeking to improve computer productivity by distributing the load among multiple processors, accomplishing computer tasks in parallel.
In 1979, Vishkin, a pioneer in parallel computing, began his work on developing a theory of parallel algorithms that relied on a mathematical model of a parallel computer, since, at that time, no viable parallel prototype existed. By 1997, advances in technology enabled him to begin building a prototype desktop device to test his theory; he and his team completed the device in December 2006.
The prototype device's physical hardware attributes are strikingly ordinarystandard computer components executing at 75 MHz. It is the device's parallel architecture, ease of programming and processing performance relative to other computers with the same clock speed that get people's attention.
"Based on the very positive reactions of my graduate students this spring," Vishkin stated, "I knew that it was time to take the technology public."
Earlier this month, Vishkin and his Ph.D. student, Xingzhi Wen, published a paper about his newly-built parallel processing technology for the Association for Computing Machinery (ACM) Symposium on Parallelism in Algorithms and Architectures, and showcased it at a major computing conference, the ACM International Conference on Supercomputing (ICS) in Seattle.
At the ICS event, Vishkin allowed conference participants to connect to the device remotely and run programs on it in a full-day tutorial session he conducted, offering colleagues and student participants the opportunity to experience the prototype technology firsthand.
Vishkin also participated in a panel discussion at a special invitation-only Microsoft Workshop on Many-Core Computing on June 20-21 in Seattle, Wash. In August, Vishkin will present a keynote address at the Workshop on Highly Parallel Processing on a Chip in Rennes, France, held in conjunction with the 13th Euro-Par, an international European conference on parallel and distributed computing.
"This system represents a significant improvement in generality and flexibility for parallel computer systems because of its unique abilities," said Burton Smith, technical fellow for advanced strategies and policy at Microsoft. "It will be able to exploit a wider spectrum of parallel algorithms than today's microprocessors can, and this in turn will help bring general purpose parallel computing closer to reality."
Vishkin has filed several patents on his parallel processing technology since 1997. Funded by the National Science Foundation and the Department of Defense, his research has also received significant interest from the computer industry, which he believes his technology will revitalize.
"The manufacturers have done an excellent job over the years of increasing a single processor's clock speed through clever miniaturization strategies and new materials," he noted. "But they have now reached the limits of this approach. It is time for a practical alternative that will allow a new wave of innovation and growthand that's what we have created with our parallel computing technology."
In addition to Xingzhi Wen, Vishkin's research teams includes students Aydin Balkan, George Caragea, Mike Detwiler, Tom Dubois, Mike Horak, Fuat Keceli, Mary Kiemb and Alex Tzannes, as well as electrical and computer engineering professors Rajeev Barua and Gang Qu.
Naming Contest
To increase awareness of his new technology, Vishkin is inviting the public to propose names for it. The name should reflect the features and bold aspirations of the new machine and its parallel computing capabilities, Vishkin said.
The winner will receive a $500 cash prize and be credited with the naming of the innovative technology. Visitors can submit their ideas online (http://www.ece.umd.edu/supercomputer/). The deadline for submissions is September 15, 2007.
Source: University of Maryland
As a former Terp, I could care less! : )
Bombastic Vishkin, way to go!
I got the latest issue of Terp Magazine in the mail the other day (Univ. of MD alumni magazine). Some professor was harping about how distressing it is that since its already been established that global warming (G2K) is man’s fault, he’s so upset that some people still question that.
That was enough for me to tear the thing up and throw it away.
Wow! Now I’ll be able to get my spam email really, really fast...
That was enough for me to tear the thing up and throw it away.
:::::::
Thank you for not recycling. No sarcasm intended.
I’d have burned it, makes more CO2.
(humor)
LOL.
I submitted a proposed name: ParTrek.
Is that worth $500?? I definitely think so :)
I took a look at his papers and, best that I can tell, he assumes that calculations can in essense be reduced to tree-searches/operations (e.g., when adding eight numbers, add #1, #2 and #3, #4 and #5, #6 and #7 and #8 (all in parallel) and then add the 1st and 2nd results and the 3rd and 4th results (all in parallel) and then add those two together to get the final number: 7 additions instead of 8 but in, more of less, only about 3/8ths of the time (it gets better with a larger number of numbers to add — assuming a lot of processors).
However, I expect that his method will fail the test of practicality in “The Real World” because of the old problem that *all* parallel processing has - the requirement to rewrite all of that legacy software...
Such rewrites just will not work in the commercial world.
Now, if he could figure out how to build an automatically parallelizing compiler, then he *would* definitely have something :)
Pretty stuff anyhow.
PVC chassis and a radiator fan :)
However, preparing 100 page document for printing isn't much faster today than it was back then.
A perfect example how bloatware wastes resources.
100x faster than today's PC does not mean that the actual work will be much faster.
100 times faster until Mircosoft sends out service pack 1,2,3....9 and you still need Norton......
Just Damn.
I want a galvanized rigid conduit case and fan. Then I’ll be impressed.
With that prop it looks like it could fly....
Preferably, somebody that remembers when memory and cpu cycles weren't cheap.
There are actually parallel libraries out there that work —
But how often does the typical PC user invert a matrix or calculate a heat flow problem (partial differential equation thingus)...
I would argue that typical PC stuff is inherently I/O bound rather than compute bound.
I don’t think fine-grained parallelism will be of much use these days for PCs...
Intel already released a compiler that makes parallelizing code a lot easier, and does some of it by itself. Apple also already has many of its OS Core libraries set up so that a call to one of them automatically runs parallel.
What's new in this?
100x faster can be consumed by Microsoft bloatware with ease......
My AMD 3000 boots 5X slower than my old AT-12
But my AT couldn’t play Call of Duty either. 20 years ago, I could not fathom have a a gig of hard drive space much less 1 gig of RAM. My MP3 player has more RAM than the mainframe I used 20 years ago.
********************************************
CodeSourcery to Port Sourcery VSIPL++(TM) to the Cell Broadband Engine(TM) Processor
**********************EXCERPT**************************
http://www.cs.sandia.gov/CSRI/Workshops/2006/HPC_WPL_workshop/Presentations/05-Hofstee-Cell.pdf
Wonder why Sandia is interested?
A PERSONAL computer spends most of its time waiting for keystrokes and handling “heartbeat” interrupts to go out and do other housekeeping tasks.
Back when I did this stuff (on IBM mainframes) I worked with 6 different operating systems that performed user computing. Although I primarily worked with VM and VSE, it was clear that MVS and its successors, OS/390 and Z/OS, were very good at subtasking in the multiprocessor environment. I/O tasks, calls to service programs such as transaction managers, database managers, and communication subsystems, and other such processes were processed separately from the primary user program logic, frequently in separate processors.
Parallel processing is not a new concept, but it differs from the way humans analyze problems - although it probably mimics the way our brains work!
Question: Didn’t Tandem Computers develop parallel processing?
At what rpm does that big ol’ fan have to run? 200?
For Windows maybe 2600?
I gather the rheostat is for variable manual fan speed?
Two power supplies?
Too bad that hard drive caddy doesn’t allow for hot-swapability.
Wow, a floppy drive. Must be a museum picture!
What’s the thingie with the red light?
Having been made out of PVC, doesn’t it tend to wobble?
HF
how about calling it CRAY?
>Thank you for not recycling. No sarcasm intended. I’d have burned it, makes more CO2.
I'd have sold a promise not to burn it on eBay as a Carbon Credit.
But how often does the typical PC user invert a matrix or calculate a heat flow problem (partial differential equation thingus)...
You're not a gamer, are you?
I can buy those?! I will rush as I want to purchase many while supplies last!
“Vishkin and his team are now demonstrating their technology, which in future devices could include 1,000 processors on a chip the size of a finger nail, to government and industry groups. To show how easy it is to program, Vishkin is also providing access to the prototype to students at Montgomery Blair High School in Montgomery County, Md.”
-—<>-—<>-—<>-—<>-—<>-—
Sounds promising. I wonder if I can get in on this experiment...
No, I am NOT a gamer at all...
But, I see your point.
Sony Might Have Gotten It Right with the PS3 from the Beginning
Softpedia | November 5th, 2007 | Filip Truta
Posted on 11/25/2007 1:38:14 PM EST by SunkenCiv
http://www.freerepublic.com/focus/f-chat/1930299/posts
Neat stuff, I hope the first ones come with their own fire extinguishers.
The A. James Clark School of Engineering (of which I am an alumnus: Fear the Turtle) includes a Department of Fire Protection Engineering. So maybe they have it covered. ;'}
Disclaimer: Opinions posted on Free Republic are those of the individual posters and do not necessarily represent the opinion of Free Republic or its management. All materials posted herein are protected by copyright law and the exemption for fair use of copyrighted works.