Home > Articles > Operating Systems, Server

  • Print
  • + Share This
Like this article? We recommend

Like this article? We recommend

A Taxonomy: Naming the Beasts

Not that long ago, everything inside the computer came to a halt while a line of text was printed on the operator's console. The government's need for speed provided funding for some very creative ideas in the early 1960s, and the key to faster processing speeds was overlap: doing more than one thing at a time. Experimental prototypes with multiple central processing units (CPUs), partitioned physical memories, and some innovative hardware and software developments brought about some new and exciting ideas.

The Illiac computer (at the University of Illinois, in Champaign-Urbana, Illinois) was a vector processor with a novel architecture. Each of a string of worker computers was given an instruction to execute on its own portion of the data. One important benefit was that 2 lists of 10 numbers, for example, were multiplied by 10 processors in a single instruction cycle! Mathematicians refer to a list of numbers as a vector, so these types of computers are commonly called vector processors. This was overlap in the extreme, provided that the software could exploit it.

Michael J. Flynn (in his paper titled "Very High-Speed Computing Systems," in Proceedings of the IEEE, December 1966) gave us a way to categorize and name these new machines. His taxonomy focused on the number of instruction and data pathways that the architecture provided.

A uniprocessor was distinct from a multiprocessor (MP) because it could execute only a single instruction at a time: SI stood for single instruction. Similarly, if only a single item of data could be extracted from memory at a time, it was designated SD, for single data. The typical desktop computer is a uniprocessor, designated SISD. An MP with two or more CPUs and a single shared memory could simultaneously execute as many instructions as it had CPUs. Each of these instructions could access memory data simultaneously, so these kinds of machines were designated MIMD.

From here it gets a little trickier. Remember the Illiac? Technically, it executed only one instruction at a time. (Although there are many CPUs executing that instruction, only one instruction is taken from program memory, so it counts as only one.) Because each slave computer has its own local memory, multiple pieces of data can be accessed at a time. This is called SIMD, for single instruction, multiple data. The last possible combination of instruction and data pathways is MISD. Many (including Flynn) say there is no such architecture. Some speculate on how such a machine might operate, but the classification is dubious, at best.

Two popular types of multiprocessor emerged in the 1970s: loosely coupled and tightly coupled. Loose meant that two or more computers shared a job (input) queue and a print (output) queue; tight that meant two or more CPUs shared the same physical memory. A loosely coupled multiprocessor could improve a commercial data center's throughput in terms of jobs per day. A tightly coupled MP ran parallel programs that let scientists predict tomorrow's weather before tomorrow came, and let soldiers complete a battlefield simulation before the battle ended! Parallel processing became an important asset to the scientific and military communities, but it was very expensive, costing millions of dollars.

In the 1980s, a doctoral student at Yale named Kai Li proposed a network of workstations that could emulate a tightly coupled MP. (Search http://www.yale.edu for the IVY system. Yale is rightly still buzzing about his groundbreaking work today!) Each PC maintained a portion of the virtual memory space, and software interrupts handled page faults by sending the requested pages of virtual memory over the network. Parallel programs ran more slowly, but at a fraction of the cost. An immediate benefit was being able to debug parallel algorithms without tying up the real parallel processor's time.

This new distributed computing architecture became a modern version of the loosely coupled MP. Computer science research was flooded with extensions to this model for more than a decade. IVY (which doesn't stand for anything—Yale just uses that word a lot) even had a major influence on the early Beowulf project at NASA, discussed later in this article. And Beowulf, some say, put Linux on the map. (The January 1998 issue of Linux Journal has half a dozen articles about the first Beowulf systems. The August 2002 issue has a recap and an update on Beowulf II projects.)

The distributed MP became so popular with computer architects that it warranted its own taxonomy. Modern computer architecture texts refer to tightly coupled multiprocessors as UMA, which stands for uniform memory access. This is because each CPU experiences the same amount of delay time when it accesses data from anywhere in physical memory space.

High-speed communications systems and other stream-data processors are often constructed from multiple computer boards, each of which is plugged into a backplane in a common chassis. Specialized operating systems let you organize the memory on each CPU board into a single memory space. The first board might represent the first 16MB of physical memory, the second board's memory can be mapped right behind that, and so on. When an instruction executed on a board's CPU accesses data in its local memory, access time is short. When it accesses data from some remote board's local memory, hardware retrieves the data from the remote board's memory and sends it over the high-speed backplane's data bus, placing it in the requesting CPU's memory data register, just as if it came from its own local memory. But memory access time is much longer from a remote board, due to all that hardware intervention. Textbooks call these systems NUMA, for their nonuniform memory access time properties.

The IVY system from Yale has a considerably longer memory access time for data from a remote machine. Remote data access is handled through software communications over the local area network, which is considerably slower than a backplane's data bus. Some texts call these systems NUMA, and others distinguish IVY's nonhardware approach as NORMA, for no remote memory access. We might all agree that there is certainly support for remote memory access, but the no here refers to the lack of hardware support. This is computer architecture, after all, and software architecture doesn't quite get the distinction it deserves, in my opinion. But hopefully, that's all about to change.

In the 1990s, a project team at NASA was tasked to develop a (cheap) solution to the problem of data access. NASA's databases were huge, and way too much time was being spent moving the same data to the various workstations for individual processing, sometimes repeatedly to the same workstation. The team was asked to look into a way to reduce the data transmission time by designing a "Gigaflops Scientific Workstation." (Gigaflops is shorthand for a billion floating-point operations per second, a common scientific measure of computer performance.) The team accomplished its task by developing a cluster system, a supercomputer called Beowulf.

A Beowulf system, according to Donald Becker, comprises only commercial, off-the-shelf components; costs less than $50,000; and uses freely available software and tools, with the express goal of returning the design and improvements back to the community. (See his paper titled "Beowulf: Harnessing the Power of Parallelism in a Pile-of-PCs" at http://www.beowulf.org for further details.) Later versions of Beowulf relaxed some of the off-the-shelf requirements, but their scientific computing benchmark results were no less than stunning: Becker's team won the prestigious Gordon Bell award in 1996. The cost-performance ratio of a cluster of Pentium Pros achieved 2.1 billion floating-point operations per second, or 2.1Gflops, based on measurements from a commonly available and long-trusted benchmark.

Cluster systems are not without their problems. Whether such a system is configured as a supercomputer or a high-volume server, you should consider carefully two ratios. Tuning a system's performance requires a balance between the amount of time it takes to transfer a message from one node machine in the cluster to another and the amount of time that the receiving node spends processing the data in that message. The message might be a query packet in a cluster server. In a supercomputer, it might be a block of data to be processed, or a block of program instructions to be executed by the receiving node. How much time does it take to process a typical query or a block of data, and how much time does it take to execute a typical block of instructions? Compare these to the time it takes to get the message from one node to another, including communications support software processing time on both the sending and the receiving nodes.

If the processing time is dramatically shorter than the transmission time, as it most often is, the master node in a cluster server might be able to process all incoming queries faster by itself, rather than by sending it to an available worker node. And a supercomputer will not benefit from any inherent parallelism if sending the data to a remote processor takes longer than the processing itself.

While we're on the subject of parallelism, consider Amdahl's Law before you consider using a supercomputer. If your application doesn't have enough inherent parallelism to warrant the use of a parallel machine, you probably shouldn't bother acquiring one.

  • + Share This
  • 🔖 Save To Your Account

InformIT Promotional Mailings & Special Offers

I would like to receive exclusive offers and hear about products from InformIT and its family of brands. I can unsubscribe at any time.

Overview


Pearson Education, Inc., 221 River Street, Hoboken, New Jersey 07030, (Pearson) presents this site to provide information about products and services that can be purchased through this site.

This privacy notice provides an overview of our commitment to privacy and describes how we collect, protect, use and share personal information collected through this site. Please note that other Pearson websites and online products and services have their own separate privacy policies.

Collection and Use of Information


To conduct business and deliver products and services, Pearson collects and uses personal information in several ways in connection with this site, including:

Questions and Inquiries

For inquiries and questions, we collect the inquiry or question, together with name, contact details (email address, phone number and mailing address) and any other additional information voluntarily submitted to us through a Contact Us form or an email. We use this information to address the inquiry and respond to the question.

Online Store

For orders and purchases placed through our online store on this site, we collect order details, name, institution name and address (if applicable), email address, phone number, shipping and billing addresses, credit/debit card information, shipping options and any instructions. We use this information to complete transactions, fulfill orders, communicate with individuals placing orders or visiting the online store, and for related purposes.

Surveys

Pearson may offer opportunities to provide feedback or participate in surveys, including surveys evaluating Pearson products, services or sites. Participation is voluntary. Pearson collects information requested in the survey questions and uses the information to evaluate, support, maintain and improve products, services or sites, develop new products and services, conduct educational research and for other purposes specified in the survey.

Contests and Drawings

Occasionally, we may sponsor a contest or drawing. Participation is optional. Pearson collects name, contact information and other information specified on the entry form for the contest or drawing to conduct the contest or drawing. Pearson may collect additional personal information from the winners of a contest or drawing in order to award the prize and for tax reporting purposes, as required by law.

Newsletters

If you have elected to receive email newsletters or promotional mailings and special offers but want to unsubscribe, simply email information@informit.com.

Service Announcements

On rare occasions it is necessary to send out a strictly service related announcement. For instance, if our service is temporarily suspended for maintenance we might send users an email. Generally, users may not opt-out of these communications, though they can deactivate their account information. However, these communications are not promotional in nature.

Customer Service

We communicate with users on a regular basis to provide requested services and in regard to issues relating to their account we reply via email or phone in accordance with the users' wishes when a user submits their information through our Contact Us form.

Other Collection and Use of Information


Application and System Logs

Pearson automatically collects log data to help ensure the delivery, availability and security of this site. Log data may include technical information about how a user or visitor connected to this site, such as browser type, type of computer/device, operating system, internet service provider and IP address. We use this information for support purposes and to monitor the health of the site, identify problems, improve service, detect unauthorized access and fraudulent activity, prevent and respond to security incidents and appropriately scale computing resources.

Web Analytics

Pearson may use third party web trend analytical services, including Google Analytics, to collect visitor information, such as IP addresses, browser types, referring pages, pages visited and time spent on a particular site. While these analytical services collect and report information on an anonymous basis, they may use cookies to gather web trend information. The information gathered may enable Pearson (but not the third party web trend services) to link information with application and system log data. Pearson uses this information for system administration and to identify problems, improve service, detect unauthorized access and fraudulent activity, prevent and respond to security incidents, appropriately scale computing resources and otherwise support and deliver this site and its services.

Cookies and Related Technologies

This site uses cookies and similar technologies to personalize content, measure traffic patterns, control security, track use and access of information on this site, and provide interest-based messages and advertising. Users can manage and block the use of cookies through their browser. Disabling or blocking certain cookies may limit the functionality of this site.

Do Not Track

This site currently does not respond to Do Not Track signals.

Security


Pearson uses appropriate physical, administrative and technical security measures to protect personal information from unauthorized access, use and disclosure.

Children


This site is not directed to children under the age of 13.

Marketing


Pearson may send or direct marketing communications to users, provided that

  • Pearson will not use personal information collected or processed as a K-12 school service provider for the purpose of directed or targeted advertising.
  • Such marketing is consistent with applicable law and Pearson's legal obligations.
  • Pearson will not knowingly direct or send marketing communications to an individual who has expressed a preference not to receive marketing.
  • Where required by applicable law, express or implied consent to marketing exists and has not been withdrawn.

Pearson may provide personal information to a third party service provider on a restricted basis to provide marketing solely on behalf of Pearson or an affiliate or customer for whom Pearson is a service provider. Marketing preferences may be changed at any time.

Correcting/Updating Personal Information


If a user's personally identifiable information changes (such as your postal address or email address), we provide a way to correct or update that user's personal data provided to us. This can be done on the Account page. If a user no longer desires our service and desires to delete his or her account, please contact us at customer-service@informit.com and we will process the deletion of a user's account.

Choice/Opt-out


Users can always make an informed choice as to whether they should proceed with certain services offered by InformIT. If you choose to remove yourself from our mailing list(s) simply visit the following page and uncheck any communication you no longer want to receive: www.informit.com/u.aspx.

Sale of Personal Information


Pearson does not rent or sell personal information in exchange for any payment of money.

While Pearson does not sell personal information, as defined in Nevada law, Nevada residents may email a request for no sale of their personal information to NevadaDesignatedRequest@pearson.com.

Supplemental Privacy Statement for California Residents


California residents should read our Supplemental privacy statement for California residents in conjunction with this Privacy Notice. The Supplemental privacy statement for California residents explains Pearson's commitment to comply with California law and applies to personal information of California residents collected in connection with this site and the Services.

Sharing and Disclosure


Pearson may disclose personal information, as follows:

  • As required by law.
  • With the consent of the individual (or their parent, if the individual is a minor)
  • In response to a subpoena, court order or legal process, to the extent permitted or required by law
  • To protect the security and safety of individuals, data, assets and systems, consistent with applicable law
  • In connection the sale, joint venture or other transfer of some or all of its company or assets, subject to the provisions of this Privacy Notice
  • To investigate or address actual or suspected fraud or other illegal activities
  • To exercise its legal rights, including enforcement of the Terms of Use for this site or another contract
  • To affiliated Pearson companies and other companies and organizations who perform work for Pearson and are obligated to protect the privacy of personal information consistent with this Privacy Notice
  • To a school, organization, company or government agency, where Pearson collects or processes the personal information in a school setting or on behalf of such organization, company or government agency.

Links


This web site contains links to other sites. Please be aware that we are not responsible for the privacy practices of such other sites. We encourage our users to be aware when they leave our site and to read the privacy statements of each and every web site that collects Personal Information. This privacy statement applies solely to information collected by this web site.

Requests and Contact


Please contact us about this Privacy Notice or if you have any requests or questions relating to the privacy of your personal information.

Changes to this Privacy Notice


We may revise this Privacy Notice through an updated posting. We will identify the effective date of the revision in the posting. Often, updates are made to provide greater clarity or to comply with changes in regulatory requirements. If the updates involve material changes to the collection, protection, use or disclosure of Personal Information, Pearson will provide notice of the change through a conspicuous notice on this site or other appropriate way. Continued use of the site after the effective date of a posted revision evidences acceptance. Please contact us if you have questions or concerns about the Privacy Notice or any objection to any revisions.

Last Update: November 17, 2020