Tuesday, February 19, 2008

Parallel Processing

Research current online literature to identify a computer model with exceptional parallel processing ability. Identify the manufacturer, the maximum number or processors the computers uses, how fast the machine can perform calculations, and typical applications for it. Cite your sources. If you answer includes terms not used in this chapter be sure to define them.

Blog on!

13 Comments:

Anonymous Anonymous said...

Parallel Processing is defined as:
The simultaneous processing of different tasks by two or more microprocessors, as by a single computer with more than one central processing unit or by multiple computers connected together in a network.
http://www.answers.com/topic/parallel-processing?cat=technology


Linux-compatible SMP’s uses parallel processing but it is hard to find one with more than four processors. A SMP is







(1) Short for Symmetric Multiprocessing, a computer architecture that provides fast performance by making multiple CPUs available to complete individual processes simultaneously (multiprocessing).

http://webopedia.com/TERM/S/SMP.html

I can’t really find the other bits of info you are looking for. Sorry about that.

Lonnie

9:35 AM  
Anonymous Anonymous said...

Parallel Processing refers to the concept of speeding up the execution of a program by dividing the program into multiple fragments that can execute simultaneously, each on its own processor.
Apple has one of the fastest computer today. The Power MAC G5 with Dual 2.0 GHz 64-bit Power PC G5, Dual Independent 1GHz front side Buses, 512MB 400MHz Dual Channel (128-bit) DDR, 8DIMMs, 8GB Maximum memory, 160GB Serial ATA Hard Drive, AGP 8xPro graphics slot, RADEON 9600 Pro-64MB DDR, 3PCI-X Slots (one 64-bit 133MHz, two 64-bit 100MHz), and 4x Super Drive.
http://www.apple.com/pr/library/2003/jun/23pmg5.html

Wilfredo Guzman

4:44 PM  
Anonymous Anonymous said...

The simultaneous use of more than one CPU to execute a program. Ideally, parallel processing makes a program run faster because there are more engines (CPUs) running it. In practice, it is often difficult to divide a program in such a way that separate CPUs can execute different portions without interfering with each other. Most computers have just one CPU, but some models have several. There are even computers with thousands of CPUs. With single-CPU computers, it is possible to perform parallel processing by connecting the computers in a network. However, this type of parallel processing requires very sophisticated software called distributed processing software.

Note that parallel processing differs from multitasking, in which a single CPU executes several programs at once.

Parallel processing is also called parallel computing.

6:31 AM  
Blogger Unknown said...

This comment has been removed by the author.

10:11 AM  
Blogger Unknown said...

The Cray T3E-1200E has 256 processors in one liquid cooled cabinet and up to 8 of these cabinets can be joined together to make a distributed memory system. It processes at 420 megabytes per second. This machine has led to many scientific breakthroughs but at most of the locations is now retired. It was used at The San Diego Supercomputer Center (SDSC), The High Performance Computing Center in Stuttgart, The Edinburgh Parallel Computing Centre at The University of Edinburgh, UK (EPCC), and The Pittsburgh Supercomputing Center (PSC),

-Steven Walker
http://www.cs.cmu.edu/~scandal/gifs.html

10:14 AM  
Anonymous Anonymous said...

Four times faster than its predecessor and capable of 63 million million calculations a second - the UK Research Councils have launched the largest and most advanced supercomputing facility in the UK.

HECToR (High-End Computing Terascale Resources) will facilitate innovative and world leading research and represents the equivalent of approximately 12,000 desktop systems.

Based at the University of Edinburgh's Advanced Computing Facility (ACF), the £113m service will run for six years and be operated by EPCC (Edinburgh Parallel Computing Centre). The computer is a Cray XT4 system and support for applications software is provided by NAG Ltd. The procurement project for HECToR was funded and managed by the Engineering and Physical Sciences Research Council (EPSRC) on behalf of the UK Research Councils



Daniel

12:39 PM  
Anonymous Anonymous said...

source : http://www.epsrc.ac.uk/PressReleases/LaunchOFNewSupercomputer.htm
Daniel

12:40 PM  
Anonymous Anonymous said...

Parallel processing, as the course textbook defines it, is the process of operating two or more CPU's in parallel, with more than one CPU executing instructions at the same time.
The NCR WorldMark 3500/3500-XP is a computer model that uses parallel processing. It's manufacturer is NCR Canada Ltd. It has i486 processors in one MPP system configuration (MPP meaning it is a Massively Parallel processing unit). Very large commercial and business applications are the typical applications for it. The NCR WorldMark 3500/3500-XP works good under critical time environments and has up to 64 nodes thats 1,024 CPU's.

-David Del Castillo

Sources:
NCR Canada Ltd. website
http://strategis.ic.gc.ca/app/ccc/srch/nvgt.do?lang=fra&prtl=1&sbPrtl=&estblmntNo=115370160000&profile=cmpltPrfl&app=1

McHoes, Ann Mciver. "Understanding Operator Systems". 2008.

3:15 PM  
Anonymous Anonymous said...

Parallel processing computers have many processors working in parallel; the difficulty is to make sure the problem is synchronized properly and the programs are organized to take advantage.
Cray Computer's supercomputer XT3 is a scalable, parallel design which can be scaled up to simply huge.
In a single cabinet, it can hold 96 AMD Opteron processors, which can operate at 998 GFlops per cabinet using dual-core processors.
To support this it has a 64K l1 instruction cache, a 64K l1 data cache, and a 1 MB L2 cache per processor, and up to 8 GB ECC RAM per cabinet; the RAM operates at 6.4 GB/sec per processor.
The real secret of the XT3's power is the routing and communications ASIC for each processor. This not ties together the processors within a cabinet, but allows a system to be scaled up to 192 cabinets, giving a total of more than 30K processors per system or 60K cores with dual-core processors. These interconnections can be arranged in a three- dimensional geometry.
What would one use all this computing muscle for? Not even the national debt needs that! But there are calculations that are that complicated. One of the first customers for the XT5 system (an even more massive upgrade to the XT3) is the Danish Meteorological Institute.
Says Peter Aakjaer, director general of DMI, "The extreme scalability and unprecedented sustained performance of the Cray XT5 supercomputer will allow us to run an operational weather forecast with more than 10 times the calculations and I/O throughput than we can with our current system. This will enable us to better safeguard human life and property, and provide a foundation for economic and environmental planning throughout the vast geographical area of Denmark, the Faroes and Greenland, which is a significant part of the North Atlantic and Arctic region."

Aakjaer, Peter, investors.cray.com/ phoenix.zhtml?c=98390&p=irol newsArticle_Print &ID=1083780 &highlight=. retrieved 08/03/05

“Cray XT3™ Supercomputer: Scalable by Design”, www.cray.com/downloads/ Cray_XT3_ Datasheet.pdf. retrieved 08/03/05

Joyce

9:55 PM  
Anonymous Anonymous said...

Cray designs and develops HPC systems for governement/classified operationgs, scientific research, weather/environmental research and automootice and aerospace markets. Products include the X1E supercomputer that ranges from 16 to 8192 processors and can deliver up to 147 teraflops.

http://67.79.90.147:2196/ehost/pdf?vid=7&hid=101&sid=0dd0102e-3784-470f-b7a3-ab1177968cc1%40sessionmgr109

Daniel Brooks

11:54 PM  
Anonymous Anonymous said...

Parallel processing is the ability to use more then one central processing unit simultaneously.

http://en.wikipedia.org/wiki/Parallel_processing

One great choice would be the XPS 720 desktop from dell. Its primary function is gaming. It includes a NVIDIA® 's nForceTM 680i SLI chipset which is longhand for "A really powerful chipset" and operates at 800MHz and can max out at 8GB of dual-channel memory (on a 64bit operating system) for higher speeds.

Thomas Kelley

http://www.dell.com/content/products/productdetails.aspx/xpsdt_720?c=us&l=en&s=biz&cs=555

9:47 PM  
Anonymous Anonymous said...

distributed processing software is needed for a single cpu computer to even attempt parallel processing , which i can do as long as its connected to a network of computers. in most cases a computer now adays has at least 2 cpu's though the more powerful supercomputers can have more than a 1000 granting its parallel processing a great deal of power and speed.

http://en.wikipedia.org/wiki/Parallel_Processing

Jessie

11:52 AM  
Anonymous Anonymous said...

Parallel processing allowed us to do things we never thought imaginable in terms of PC power and even console gaming. Parallel processing is basically two or more processors running the same task at the same time. So it's basically dividing the information between the processors for exponentially faster power from any processor. The Xbox 3560 is a great example with three 3.3ghz processors running parallel, it is a force to be reckoned with!

Jerod Finney

8:47 AM  

Post a Comment

<< Home