Ultra Network Technologies

Last updated

Ultra Network Technologies (previously called Ultra Corporation) was a networking company. It offered high-speed network products for the scientific computing market as well as some commercial companies. It was founded in 1986 by James N. Perdue (formerly of NASA, Ames Research Center), Drew Berding, and Wes Meador (of Control Data Corporation) to provide higher speed connectivity and networking for supercomputers and their peripherals and workstations. At the time, the only other companies offering high speed networking and connectivity for the supercomputer and high-end workstation market was Network Systems Corporation (NSC) and Computer Network Technology Corporation (CNT). They both offered 50 megabytes per second (MB/s) bandwidth between controllers but at that time, their architecture was not implemented using standard networking protocols and their applications were generally focused on supporting connectivity at high speed between large mainframes and peripherals, often only implementing only point-to-point connections. Ethernet was available in 1986 and was used by most computer centers for general networking purposes. Its bandwidth was not high enough to manage the high data rate required by the 100 MB/s supercomputer channels and 4 MB/s VMEbus channels on workstations.[ citation needed ]

Ultra's first customer, Apple Computer, purchased a system to connect their Cray 1 supercomputer to a high speed graphics framebuffer so that Apple could simulate new personal computers on the Cray Research computer (at the hardware level) and use the framebuffer as the simulated computer display device. Although not a networking application, this first contract allowed Ultra to demonstrate the basic technologies and gave them capital to continue development on a true networking processor.

In 1988, Ultra introduced ISO TP4 (level 4 networking protocol) as part of their controllers and implemented a type of star configuration network using coax and fiber optic connections. They called this product, UltraNet. They later offered a fast version of TCP/IP in their controllers, as this protocol was most frequently encountered in an actual computer center network environment. The clock rates on the Ultra network processors provided 250 Mbit/s transfer rates and four of these could be connected together to achieve one gigabit per second transfer rates for a single logical connection. Effective transfer rates between Silicon Graphics and Sun Microsystems workstations exceeded 4 MB/s using one 250 Mbit/s physical connection, a factor of over 10 to 12 greater than then current Ethernet connections and often exceeded the effective transfer rates of the competing NSC and CNT connections in similar applications. Customers with dual Cray computers measured the connections between Cray processors over the UltraNet that exceeded 80 MB/s effective transfer rates. Ultra Network Technologies products included network cards for workstations and mini-supercomputers using VMEbus connectors and fiber optic cable for the network physical connections, host network cards which resided in the network hub for Cray Supercomputers, IBM mainframes, mini-supercomputers from Convex Computer, HIPPI standard channel, and others. There were two sizes of high speed network hubs that contained the mainframe host cards plus the fiber optic network hub to network hub cards. The network topology was in the form of connected hubs. Engineers at the Stuttgart University computer center demonstrated long distance connections using German PTT provided fiber optics of effective transfer rates over 4 MB/s up to an 800 km distance. Later products incorporated TCP/IP network protocols in their processors.

A typical network configuration of several workstations and a single mainframe host could cost $250,000. A configuration with many workstations and two or three mainframe computers could reach $1 Million.

The company grew to about 140 employees at its high point. Its headquarters was located at 101 Daggett Drive, San Jose, CA with other offices in Dallas, Los Angeles, Seattle, Washington DC, Düsseldorf, Germany, and Paris, France. In 1992, the company was abandoned by its investors and sold due to an inability to become profitable and the advent of less expensive network technologies, mainly created by the advent of the higher speed personal computers and lower cost workstations used in the scientific labs; the buyer was Computer Network Technology Corporation of Plymouth, Minnesota (NASDAQ: CMNT). The company's Chairman of the Board was M. Kenneth Oshman, formally chairman of ROLM Corporation, and President was Stan Tenold, previously the president of ROLM's Military Products division. The company's various customers included many high-end computer centers, including, several NASA sites, NSA, US Air Force, US Navy, Aramco, France's EDF, Pittsburg Supercomputer Center, University of Stuttgart, Leibniz University Hannover, Apple Computer, Houston Chronicle, and many other such high end computer users.

Citations

Related Research Articles

<span class="mw-page-title-main">Local area network</span> Computer network that connects devices over a limited area

A local area network (LAN) is a computer network that interconnects computers within a limited area such as a residence, school, laboratory, university campus or office building. By contrast, a wide area network (WAN) not only covers a larger geographic distance, but also generally involves leased telecommunication circuits.

Myrinet, ANSI/VITA 26-1998, is a high-speed local area networking system designed by the company Myricom to be used as an interconnect between multiple machines to form computer clusters.

<span class="mw-page-title-main">Mainframe computer</span> Large computer

A mainframe computer, informally called a mainframe or big iron, is a computer used primarily by large organizations for critical applications like bulk data processing for tasks such as censuses, industry and consumer statistics, enterprise resource planning, and large-scale transaction processing. A mainframe computer is large but not as large as a supercomputer and has more processing power than some other classes of computers, such as minicomputers, servers, workstations, and personal computers. Most large-scale computer-system architectures were established in the 1960s, but they continue to evolve. Mainframe computers are often used as servers.

<span class="mw-page-title-main">Silicon Graphics</span> Former American computing company

Silicon Graphics, Inc. was an American high-performance computing manufacturer, producing computer hardware and software. Founded in Mountain View, California in November 1981 by Jim Clark, its initial market was 3D graphics computer workstations, but its products, strategies and market positions developed significantly over time.

<span class="mw-page-title-main">Fiber Distributed Data Interface</span> Standard for data transmission in a local area network

Fiber Distributed Data Interface (FDDI) is a standard for data transmission in a local area network. It uses optical fiber as its standard underlying physical medium, although it was also later specified to use copper cable, in which case it may be called CDDI, standardized as TP-PMD, also referred to as TP-DDI.

<span class="mw-page-title-main">Metropolitan area network</span> Computer network serving a populated area

A metropolitan area network (MAN) is a computer network that interconnects users with computer resources in a geographic region of the size of a metropolitan area. The term MAN is applied to the interconnection of local area networks (LANs) in a city into a single larger network which may then also offer efficient connection to a wide area network. The term is also used to describe the interconnection of several LANs in a metropolitan area through the use of point-to-point connections between them.

Systems Network Architecture (SNA) is IBM's proprietary networking architecture, created in 1974. It is a complete protocol stack for interconnecting computers and their resources. SNA describes formats and protocols but, in itself, is not a piece of software. The implementation of SNA takes the form of various communications packages, most notably Virtual Telecommunications Access Method (VTAM), the mainframe software package for SNA communications.

<span class="mw-page-title-main">HIPPI</span>

HIPPI, short for High Performance Parallel Interface, is a computer bus for the attachment of high speed storage devices to supercomputers, in a point-to-point link. It was popular in the late 1980s and into the mid-to-late 1990s, but has since been replaced by ever-faster standard interfaces like Fibre Channel and 10 Gigabit Ethernet.

<span class="mw-page-title-main">Cray X-MP</span> Supercomputer manufactured by Cray Research

The Cray X-MP was a supercomputer designed, built and sold by Cray Research. It was announced in 1982 as the "cleaned up" successor to the 1975 Cray-1, and was the world's fastest computer from 1983 to 1985 with a quad-processor system performance of 800 MFLOPS. The principal designer was Steve Chen.

Minisupercomputers constituted a short-lived class of computers that emerged in the mid-1980s, characterized by the combination of vector processing and small-scale multiprocessing. As scientific computing using vector processors became more popular, the need for lower-cost systems that might be used at the departmental level instead of the corporate level created an opportunity for new computer vendors to enter the market. As a generalization, the price targets for these smaller computers were one-tenth of the larger supercomputers.

FICON is the IBM proprietary name for the ANSI FC-SB-3 Single-Byte Command Code Sets-3 Mapping Protocol for Fibre Channel (FC) protocol. It is a FC layer 4 protocol used to map both IBM's antecedent channel-to-control-unit cabling infrastructure and protocol onto standard FC services and infrastructure. The topology is fabric utilizing FC switches or directors. Valid rates include 1, 2, 4, 8 and 16 Gigabit per second data rates at distances up to 100 km.

<span class="mw-page-title-main">MBus (SPARC)</span>

MBus is a computer bus designed and implemented by Sun Microsystems for communication between high speed computer system components, such as the central processing unit, motherboard and main memory. SBus is used in the same machines to connect add-on cards to the motherboard.

Fiber to the <i>x</i> Broadband network architecture term

Fiber to the x or fiber in the loop is a generic term for any broadband network architecture using optical fiber to provide all or part of the local loop used for last mile telecommunications. As fiber optic cables are able to carry much more data than copper cables, especially over long distances, copper telephone networks built in the 20th century are being replaced by fiber.

A fully switched network is a computer network which uses only network switches rather than Ethernet hubs on Ethernet networks. The switches provide a dedicated connection to each workstation. A switch allows for many conversations to occur simultaneously. Before switches, networks based on hubs data could only allow transmission in one direction at a time, this was called half-duplex. By using a switch this restriction is removed; full-duplex communication is maintained and the network is collision free. This means that data can now be transmitted in both directions at the same time. Fully switched networks employ either twisted-pair or fiber-optic cabling, both of which use separate conductors for sending and receiving data. In this type of environment, Ethernet nodes can forgo the collision detection process and transmit at will, since they are the only potential devices that can access the medium. This means that a fully switched network is a collision-free environment.

Network Systems Corporation (NSC) was an early manufacturer of high-performance computer networking products. Founded in 1974, NSC produced hardware products that connected IBM and Control Data Corporation (CDC) mainframe computers to peripherals at remote locations. NSC also developed and commercialized the HYPERchannel networking system and protocol standards, adopted by Cray Research, Tektronix and others. In the late 1980s, NSC extended HYPERchannel to support the TCP/IP networking protocol and released a product allowing HYPERchannel devices to connect to the emerging Internet.

<span class="mw-page-title-main">Merit Network</span> Global LTE

Merit Network, Inc., is a nonprofit member-governed organization providing high-performance computer networking and related services to educational, government, health care, and nonprofit organizations, primarily in Michigan. Created in 1966, Merit operates the longest running regional computer network in the United States.

The Ohio Academic Resources Network (OARnet) is a state-funded IT organization that provides member organizations with intrastate networking, virtualization and cloud computing solutions, advanced videoconferencing, connections to regional and international research networks and the commodity Internet, colocation services and emergency web-hosting.

HYPERchannel, sometimes rendered Hyperchannel, was a local area networking system for mainframe computers, especially supercomputers, introduced by Network Systems Corporation in the 1970s. It ran at the then-fast speed of 50 Mbits/second, performance that would not be matched by commodity hardware until the introduction of Fast Ethernet in 1995. HYPERchannel ran over very thick coax cable or fibre optic extensions and required adaptor hardware the size of a minicomputer. The networking protocol was entirely proprietary. Solutions for Control Data, IBM and Cray computers were their primary products, but a wide variety of support emerged in the 1980s, including DEC VAX and similar superminicomputers.

<span class="mw-page-title-main">Bus and Tag</span> IBM peripheral interface

Bus and Tag is an "IBM standard for a computer peripheral interface", and was commonly used to connect their mainframe computers to peripheral devices such as line printers, disk storage, magnetic tape drives and IBM 3270 display controllers. The technology uses two sets of thick, multi-connector copper cables, one set, carrying data, called the bus, and the other set, carrying control information, called the tag.