InfiniBand

InfiniBand (abbreviated IB), a computer-networking communications standard used in high-performance computing, features very high throughput and very low latency. It is used for data interconnect both among and within computers. InfiniBand is also utilized as either a direct, or switched interconnect between servers and storage systems, as well as an interconnect between storage systems.^[1]

As of 2014 it was the most commonly used interconnect in supercomputers. Mellanox and Intel manufacture InfiniBand host bus adapters and network switches, and in February 2016 it was reported^[2] that Oracle Corporation had engineered its own Infiniband switch units and server adapter chips for use in its own product lines and by third parties. Mellanox IB cards are available for Solaris, RHEL, SLES, Windows, HP-UX, VMware ESX,^[3] AIX.^[4] It is designed to be scalable and uses a switched fabric network topology.

As an interconnect, IB competes with Ethernet, Fibre Channel, and proprietary technologies^[5] such as Cray's SeaStar.

The technology is promoted by the InfiniBand Trade Association.

Specification

Performance

Links can be aggregated: most systems use a 4X aggregate. 12X links are typically used for cluster and supercomputer interconnects and for inter-switch connections.

InfiniBand also provides RDMA capabilities for low CPU overhead.

Topology

InfiniBand uses a switched fabric topology, as opposed to early shared medium Ethernet. All transmissions begin or end at a channel adapter. Each processor contains a host channel adapter (HCA) and each peripheral has a target channel adapter (TCA). These adapters can also exchange information for security or quality of service (QoS).

Messages

InfiniBand transmits data in packets of up to 4 KB that are taken together to form a message. A message can be:

• a direct memory access read from or, write to, a remote node (RDMA).
• a channel send or receive
• a transaction-based operation (that can be reversed)
• a multicast transmission.
• an atomic operation

Physical interconnection

InfiniBand switch with CX4/SFF-8470 connectors

In addition to a board form factor connection, it supports both active and passive copper (up to 30 meters) and optical fiber cable (up to 10 km).^[10] QSFP connectors are used.

The Inifiniband Association also specified the CXP copper connector system for speeds up to 120 Gbit/s over copper and active optical cables.

API

InfiniBand has no standard API. The standard only lists a set of verbs like ibv_open_device or ibv_post_send, which are abstract representations of functions or methods that must exist. The syntax of these functions is left to the vendors. The de facto standard software stack is that developed by OpenFabrics Alliance. It is released under two licenses GPL2 or BSD license for GNU/Linux and FreeBSD, and as WinOF under a choice of BSD license for Windows. It has been adopted by most of the InfiniBand vendors, for GNU/Linux, FreeBSD, and Windows.

History

InfiniBand originated in 1999 from the merger of two competing designs: Future I/O and Next Generation I/O. This led to the formation of the InfiniBand Trade Association (IBTA), which included Compaq, Dell, Hewlett-Packard, IBM, Intel, Microsoft, and Sun. At the time it was thought some of the more powerful computers were approaching the interconnect bottleneck of the PCI bus, in spite of upgrades like PCI-X.^[11] Version 1.0 of the InfiniBand Architecture Specification was released in 2000. Initially the IBTA vision for IB was simultaneously a replacement for PCI in I/O, Ethernet in the machine room, cluster interconnect and Fibre Channel. IBTA also envisaged decomposing server hardware on an IB fabric. Following the burst of the dot-com bubble there was hesitation in the industry to invest in such a far-reaching technology jump.^[12]

Timeline

• 2001: Mellanox ships InfiniBridge 10Gbit/s devices and ships over 10,000 InfiniBand ports.^[13]
• 2002: adoption takes a setback when Intel announces that instead of shipping IB chips it would focus on developing PCI Express, and Microsoft discontinues IB development in favor of extending Ethernet, although Sun and Hitachi continue to support IB.^[14]
• 2003: Virginia Tech builds an InfiniBand cluster ranked number three on the Top500 at the time.
• 2004: IB starts to see adoption as a clustering interconnect, beating Ethernet on latency and price.^[12] The OpenFabrics Alliance develops a standardized, Linux-based InfiniBand software stack. The following year Linux adds IB support.^[15]
• 2005: IB begins to be implemented as an interconnect for storage devices.^[16]
• 2009: of the top 500 supercomputers in the world, Gigabit Ethernet is the internal interconnect technology in 259 installations, compared with 181 using InfiniBand.^[17]
• 2010: Market leaders Mellanox and Voltaire merge, leaving just one other IB vendor, QLogic, primarily a Fibre Channel vendor.^[18] Oracle makes a major investment in Mellanox.
• 2011: FDR switches and adapters announced at the International Supercomputing Conference.^[19]
• 2012: Intel acquires QLogic's InfiniBand technology.^[20]
• 2016: Oracle Corporation manufactures its own InfiniBand interconnect chips and switch units.^[21]

See also

• SCSI RDMA Protocol
• iSCSI Extensions for RDMA
• iWARP
• List of device bandwidths
• Optical interconnect
• Optical communication
• Parallel optical interface
• 40/100 Gigabit Ethernet

References

External links

• Dissecting a Small InfiniBand Application Using the Verbs API, arXiv:1105.1827 
• Mellanox Technologies: InfiniBand Performance Metrics

Technical and de facto standards for wired computer buses
General	System bus Front-side bus Back-side bus Daisy chain Control bus Address bus Bus contention Network on a chip Plug and play List of bus bandwidths
Standards	SS-50 bus S-100 bus Unibus VAXBI MBus STD Bus SMBus Q-Bus Europe Card Bus ISA STEbus Zorro II Zorro III CAMAC FASTBUS LPC HP Precision Bus EISA VME VXI VXS NuBus TURBOchannel MCA SBus VLB PCI PXI HP GSC bus InfiniBand UPA PCI Extended (PCI-X) AGP PCI Express (PCIe) Direct Media Interface (DMI) RapidIO Intel QuickPath Interconnect HyperTransport
Storage	ST-506 ESDI SMD Parallel ATA (PATA) SSA DSSI HIPPI Serial ATA (SATA) eSATA eSATAp mSATA SCSI Parallel SCSI SAS Fibre Channel SATA Express M.2
Peripheral	Apple Desktop Bus HIL MIDI Multibus RS-232 RS-422 RS-423 RS-485 DMX512-A IEEE-488 (GPIB) IEEE-1284 (parallel port) UNI/O ACCESS.bus 1-Wire D²B I²C SPI Parallel SCSI Profibus USB IEEE 1394 (FireWire) Camera Link External PCIe Thunderbolt
Audio	ADAT Lightpipe AES3 Intel HD Audio I²S MADI McASP S/PDIF TOSLINK
Portable	PC Card ExpressCard
Embedded	Multidrop bus CoreConnect AMBA Wishbone
Interfaces are listed by their speed in the (roughly) ascending order, so the interface at the end of each section should be the fastest. Category