Myrinet

Last updated

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.

Contents

Description

Myrinet was promoted as having lower protocol overhead than standards such as Ethernet, and therefore better throughput, less interference, and lower latency while using the host CPU. Although it can be used as a traditional networking system, Myrinet is often used directly by programs that "know" about it, thereby bypassing a call into the operating system.

Earlier versions of Myrinet used a variety of media and connectors: [1]

The later versions of Myrinet physically consist of two fibre optic cables, upstream and downstream, connected to the host computers with a single connector. Machines are connected via low-overhead routers and switches, as opposed to connecting one machine directly to another. Myrinet includes a number of fault-tolerance features, mostly backed by the switches. These include flow control, error control, and "heartbeat" monitoring on every link. The "fourth-generation" Myrinet, called Myri-10G, supported a 10 Gbit/s data rate and can use 10 Gigabit Ethernet on PHY, the physical layer (cables, connectors, distances, signaling). Myri-10G started shipping at the end of 2005.

Myrinet was approved in 1998 by the American National Standards Institute for use on the VMEbus as ANSI/VITA 26-1998. [2] One of the earliest publications on Myrinet is a 1995 IEEE article. [3]

Performance

GenerationYear [4] BandwidthNotes
1Myrinet19940.64 Gbit/s PECL PHY
2Myrinet-LAN19961.28 Gbit/sBackwards compatible with original Myrinet.
LVDS PHY for 1.28 Gbit/s operation. [5]
Myrinet-SANSystem-Area Network, shorter reach (3m) but lower cost [6]
3Myrinet-200020002 Gbit/sBackwards-compatible with Gigabit Ethernet
4Myri-10G200510 Gbit/sBackwards-compatible with 10 Gigabit Ethernet

Myrinet is a lightweight protocol with little overhead that allows it to operate with throughput close to the basic signaling speed of the physical layer. For supercomputing, the low latency of Myrinet is even more important than its throughput performance, since, according to Amdahl's law, a high-performance parallel system tends to be bottlenecked by its slowest sequential process, which in all but the most embarrassingly parallel supercomputer workloads is often the latency of message transmission across the network.

Deployment

According to Myricom, 141 (28.2%) of the June 2005 TOP500 supercomputers used Myrinet technology. In the November 2005 TOP500, the number of supercomputers using Myrinet was down to 101 computers, or 20.2%, in November 2006, 79 (15.8%), and by November 2007, 18 (3.6%), a long way behind gigabit Ethernet at 54% and InfiniBand at 24.2%.

In the June 2014 TOP500 list, the number of supercomputers using Myrinet interconnect was 1 (0.2%). [7] [8]

In November, 2013, the assets of Myricom (including the Myrinet technology) were acquired by CSP Inc. [9] In 2016, it was reported that Google had also offered to buy the company. [10]

See also

Related Research Articles

<span class="mw-page-title-main">Ethernet</span> Computer networking technology

Ethernet is a family of wired computer networking technologies commonly used in local area networks (LAN), metropolitan area networks (MAN) and wide area networks (WAN). It was commercially introduced in 1980 and first standardized in 1983 as IEEE 802.3. Ethernet has since been refined to support higher bit rates, a greater number of nodes, and longer link distances, but retains much backward compatibility. Over time, Ethernet has largely replaced competing wired LAN technologies such as Token Ring, FDDI and ARCNET.

A network switch is networking hardware that connects devices on a computer network by using packet switching to receive and forward data to the destination device.

<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.

<span class="mw-page-title-main">InfiniBand</span> Network standard

InfiniBand (IB) is a computer networking communications standard used in high-performance computing that features very high throughput and very low latency. It is used for data interconnect both among and within computers. InfiniBand is also used as either a direct or switched interconnect between servers and storage systems, as well as an interconnect between storage systems. It is designed to be scalable and uses a switched fabric network topology. Between 2014 and June 2016, it was the most commonly used interconnect in the TOP500 list of supercomputers.

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

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">VMEbus</span> Computer bus standard physically based on Eurocard sizes

VMEbus is a computer bus standard physically based on Eurocard sizes.

<span class="mw-page-title-main">Network interface controller</span> Hardware component that connects a computer to a network

A network interface controller is a computer hardware component that connects a computer to a computer network.

<span class="mw-page-title-main">Quadrics (company)</span>

Quadrics was a supercomputer company formed in 1996 as a joint venture between Alenia Spazio and the technical team from Meiko Scientific. They produced hardware and software for clustering commodity computer systems into massively parallel systems. Their highpoint was in June 2003 when six out of the ten fastest supercomputers in the world were based on Quadrics' interconnect. They officially closed on June 29, 2009.

In computing, remote direct memory access (RDMA) is a direct memory access from the memory of one computer into that of another without involving either one's operating system. This permits high-throughput, low-latency networking, which is especially useful in massively parallel computer clusters.

In computer networking, jumbo frames are Ethernet frames with more than 1500 bytes of payload, the limit set by the IEEE 802.3 standard. The payload limit for jumbo frames is variable: while 9000 bytes is the most commonly used limit, smaller and larger limits exist. Many Gigabit Ethernet switches and Gigabit Ethernet network interface controllers and some Fast Ethernet switches and Fast Ethernet network interface cards can support jumbo frames.

<span class="mw-page-title-main">IBM BladeCenter</span> Blade server architecture by IBM

The IBM BladeCenter was IBM's blade server architecture, until it was replaced by Flex System in 2012. The x86 division was later sold to Lenovo in 2014.

In audio and broadcast engineering, audio over Ethernet (AoE) is the use of an Ethernet-based network to distribute real-time digital audio. AoE replaces bulky snake cables or audio-specific installed low-voltage wiring with standard network structured cabling in a facility. AoE provides a reliable backbone for any audio application, such as for large-scale sound reinforcement in stadiums, airports and convention centers, multiple studios or stages.

<span class="mw-page-title-main">VPX</span> Standards for connecting components of a computer

VPX, also known as VITA 46, is a set of standards for connecting components of a computer, commonly used by defense contractors. Some are ANSI standards such as ANSI/VITA 46.0–2019. VPX provides VMEbus-based systems with support for switched fabrics over a new high speed connector. Defined by the VMEbus International Trade Association (VITA) working group starting in 2003, it was first demonstrated in 2004, and became an ANSI standard in 2007.

<span class="mw-page-title-main">Magerit</span> Supercomputer in Madrid, Spain

Magerit is one of the most powerful supercomputers in Spain. It also reached the second best Spanish position in the TOP500 list of supercomputers. It is installed in CeSViMa, a research center of the Technical University of Madrid.

QPACE is a massively parallel and scalable supercomputer designed for applications in lattice quantum chromodynamics.

<span class="mw-page-title-main">10 Gigabit Ethernet</span> Standards for Ethernet at ten times the speed of Gigabit Ethernet

10 Gigabit Ethernet is a group of computer networking technologies for transmitting Ethernet frames at a rate of 10 gigabits per second. It was first defined by the IEEE 802.3ae-2002 standard. Unlike previous Ethernet standards, 10GbE defines only full-duplex point-to-point links which are generally connected by network switches; shared-medium CSMA/CD operation has not been carried over from the previous generations of Ethernet standards so half-duplex operation and repeater hubs do not exist in 10GbE. The first standard for faster 100 Gigabit Ethernet links was approved in 2010.

<span class="mw-page-title-main">LIO (SCSI target)</span> Open-source version of SCSI target

The Linux-IOTarget (LIO) is an open-source Small Computer System Interface (SCSI) target implementation included with the Linux kernel.

<span class="mw-page-title-main">Mellanox Technologies</span> Israeli-American multinational supplier of computer networking products

Mellanox Technologies Ltd. was an Israeli-American multinational supplier of computer networking products based on InfiniBand and Ethernet technology. Mellanox offered adapters, switches, software, cables and silicon for markets including high-performance computing, data centers, cloud computing, computer data storage and financial services.

<span class="mw-page-title-main">QPACE2</span> Massively parallel and scalable supercomputer

QPACE 2 is a massively parallel and scalable supercomputer. It was designed for applications in lattice quantum chromodynamics but is also suitable for a wider range of applications..

References

  1. Guide to Myrinet/PCI Host Interfaces, Myricom, Inc., 18 February 2002
  2. American National Standard for Myrinet-on-VME Protocol Specification (PDF). VMEbus International Trade Association. November 2, 1998. ISBN   1-885731-15-9. Archived (PDF) from the original on November 11, 2014. Retrieved September 1, 2016.
  3. Boden, N.J.; Cohen, D.; Felderman, R.E.; Kulawik, A.E.; Seitz, C.L.; Seizovic, J.N.; Wen-King Su (1995). "Myrinet: A gigabit-per-second local area network". IEEE Micro. 15: 29–36. doi:10.1109/40.342015.
  4. Padua, David, ed. (2011). Encyclopedia of Parallel Computing. IEEE. pp. 1239–1247. doi:10.1007/978-0-387-09766-4. ISBN   978-0-387-09765-7.
  5. "M2M-M2F description". 1997-01-17. Archived from the original on 1997-01-17. Retrieved 2023-11-11.
  6. "Myrinet - A Brief, Technical Overview". 1997-01-17. Archived from the original on 1997-01-17. Retrieved 2023-11-11.
  7. "List Statistics". Archived from the original on 2018-07-18. Retrieved 2014-01-13.
  8. "Deployment Time Series Chart". Archived from the original on 2014-02-01. Retrieved 2014-01-16.
  9. "CSP, Inc. Broadens MultiComputer Business Opportunities With Asset Purchase of Myricom, Inc". Press Release. November 6, 2013. Archived from the original on September 11, 2016. Retrieved September 1, 2016.
  10. Chris Williams (February 9, 2016). "Google crafts custom networking CPU with parallel computing links". The Register. Archived from the original on August 11, 2016. Retrieved September 1, 2016.