Dolphin Interconnect Solutions

From Wikipedia, the free encyclopedia
Dolphin Interconnect Solutions
OSE: DOLP
Founded1989; 35 years ago (1989)
HeadquartersOslo, Norway
Websitewww.dolphinics.com

Dolphin Interconnect Solutions is a privately held manufacturer of high-speed data communication systems headquartered in Oslo, Norway[1][2] and Woodsville, New Hampshire, USA.

The technology of Dolphin was based on development work at Norsk Data during the late 1980s. Dolphin Interconnect Solutions was founded in 1992 as a spin-off from Dolphin Server Technology which was, in turn, a spin-off from Norsk Data in 1989.[3][4] Dolphin Interconnect Solutions develops technology for low latency and high-speed communication between servers and/or embedded computer systems.

History[edit]

Dolphin Server Technology emerged from Norsk Data, "a formerly flourishing Norwegian minicomputer maker", with the aim of building a business developing systems based on the Motorola 88000 architecture, these being adopted by Norsk Data as the new company's initial customer, with the intention of gradually reducing Norsk Data's stake to less than 50 percent and thus gradually increasing the new company's independence.[5]

Following an initial product announcement in late 1989,[6] by April 1990, Dolphin Server Technology had started shipping products in its Triton 88 series, based on the Motorola 88000 processor family, with these systems supporting up to four processors. Compliant with the 88open Consortium's standards, the Triton 88 series ran a Unix product developed by UniSoft, providing binary compatibility with contemporary 88000-based systems. Dolphin offered these products through value-added resellers in European, North American, and South American markets, also cultivating business with original equipment manufacturers, resulting in the Triton 88 models appearing "under several different brand names" worldwide.[7]

Having announced plans for an emitter-coupled logic (ECL) version of the Motorola 88000, projected to run at 125 MHz, executing up to eight instructions in parallel, and delivering a peak performance of 1000 MIPS,[8] Dolphin Server Technology participated in the development and standardization of Scalable Coherent Interface (SCI) technology, delivering the first prototype in 1992 for an implementation of the base SCI standard as a gate array fabricated by Vitesse Semiconductor. A CMOS implementation was demonstrated in 1994 in association with LSI Logic.[9]

The company had announced its plans for the ECL variant of the 88000, named Orion and developed in conjunction with Motorola, in December 1989. This processor, employing a technique called "instruction folding" originating from research done within Norsk Data, involved "a mutual exchange of patented technology" between the companies. It was hoped that Orion would ship in the first half of 1992.[7]

In 1993, Dolphin, described as a vendor of "RISC-based UNIX multiprocessor servers" specializing in solutions for the government and banking, announced a deal with NeXT to resell NeXT computer products and to license NeXT's software technology.[10] Ultimately, Dolphin "abandoned the server market entirely".[4]: 472

Products[edit]

Dolphin started out continuing the development of a line of SCI products[11] from Norsk Data, by implementing customer-specific technology, as well as providing Peripheral Component Interconnect (PCI) and later PCIe boards for commodity and high-performance computing (HPC) systems. Sun Microsystems agreed to re-sell Dolphin's SCI interfaces for the SBus in 1996.[12] Dolphin SCI products are available under the Dolphin Express SCI label.

The StarFabric product line was added through the acquisition of StarGen Inc. in early 2007.[13] StarGen shareholders received about 22% of the combined company. StarGen, which became the US subsidiary of Dolphin, had been based in Marlborough, Massachusetts, and led by Tim Miller.[14] StarFabric provides a PCI-based interconnect running over standard Ethernet Category 5 cables. Similarly, the Dolphin Express DX product line introduced in 2006 was also acquired from StarGen. DX was based on the Advanced Switching Interconnect (ASI) standard and implements a PCI Express Gen1 switched-topology technology supporting both host to host communication and host to IO expansion over an individual cable connection.[15] A company called Numascale was spun out of Dolphin in 2008, referring to the concept of non-uniform memory access (NUMA).[16]

The Dolphin Express IX product line introduced in 2010 is based on PCIe Gen2 and Gen3 integrated circuits ("chips") from Integrated Device Technology. The Dolphin Express PX product line, introduced in 2016, is based on PCI Express Gen3 chipsets from Broadcom. IX and PX implements a PCIe-native switched-topology technology.

The SISCI application programming interface (API) was developed for the shared memory SCI hardware. With the introduction of the PX, IX, and DX-line of products, the API was expanded to support features like reflective memory,[17] multicast and PCIe peer-to-peer communication.

SuperSockets is a software platform for Dolphin Express providing a low latency, high throughput implementation of the Berkeley sockets and Winsock APIs.[18] It was introduced in 2007.[19]

SmartIO has been used to share GPUs, NVMe drives, and other devices in a PCIe network.[20][21][22][23]

References[edit]

  1. ^ Wagner, N., Tiffany, P., Peterson, S. D. (2013). Business Plans For Canadians For Dummies. United States: Wiley.
  2. ^ Tveito, A., Bruaset, A. M., Lysne, O. (2009). Simula Research Laboratory: By Thinking Constantly about it. Germany: Springer Berlin Heidelberg.
  3. ^ "Dolphin Interconnect is on its Way". Tech Monitor. Retrieved October 25, 2021.
  4. ^ a b Gustavson, David B. (1999). SCI - Scalable coherent interface : architecture and software for high-performance compute clusters. Springer. p. 472. ISBN 3-540-66696-6. ISSN 0302-9743. Retrieved 24 February 2023.
  5. ^ Faden, Michael (February 1990). "Industry Report: RISC on the Rise in Europe". UNIX Review. pp. 14, 16, 19, 21, 23, 25–26. Retrieved 24 February 2023.
  6. ^ "Nordic Nereus". UNIX Review. December 1989. p. 117. Retrieved 26 February 2023.
  7. ^ a b Wilson, David (July 1991). "Tested Mettle: The Dolphin Server Technology Triton 88". UNIX Review. pp. 38, 40, 43–44, 46, 48. Retrieved 24 February 2023.
  8. ^ "Microbytes". Byte. February 1990. p. 17. Retrieved 24 February 2023.
  9. ^ Lundstrom, Stephen F. (1994). Defining the Global Information Infrastructure: Infrastructure, Systems, and Services. SPIE–The International Society for Optical Engineering. pp. 157–158. ISBN 0-8194-1680-0.
  10. ^ Bergson, Eliot (January 1993). "NeXT hooks into European server". NeXTWORLD. p. 4. Retrieved 24 February 2023.
  11. ^ Liaaen M.C., Kohmann H. (1999) Dolphin SCI Adapter Cards. In: Hellwagner H., Reinefeld A. (eds) SCI: Scalable Coherent Interface. Lecture Notes in Computer Science, vol 1734. Springer, Berlin, Heidelberg. https://doi.org/10.1007/10704208_5
  12. ^ "Sun Microsystems and Dolphin Sign OEM Agreement". EE Times. October 10, 1996. Retrieved October 25, 2021.
  13. ^ Rick Merritt (January 26, 2007). "Dolphin, Stargen merge to ride Express". EE Times. Retrieved October 25, 2021.
  14. ^ Rick Merritt (February 12, 2007). "Merger to yield I/O, clustering products based on PCI Express". EE Times. Retrieved October 25, 2021.
  15. ^ Venkata Krishnan; Tim Miller; Herman Paraison (September 17, 2007). "Dolphin express: A transparent approach to enhancing PCI Express". 2007 IEEE International Conference on Cluster Computing. pp. 464–467. doi:10.1109/CLUSTR.2007.4629266. ISBN 978-1-4244-1387-4. S2CID 14004892.
  16. ^ Timothy Prickett Morgan (November 24, 2010). "Numascale brings big iron SMP to the masses". EThe Register. Retrieved October 25, 2021.
  17. ^ "Dolphin Launches Low Latency Networking Solution". Wall Street & Technology.
  18. ^ Ryan, Stein Jørgen; Bryhni, Haakon (March 30 – April 3, 1998). "Eliminating the protocol stack for socket based communication in shared memory interconnects". In José Rolim (ed.). Lecture Notes in Computer Science. 10th International Parallel and Distributed Processing, held in conjunction with the 12th International Parallel Processing Symposium and 9th Symposium on Parallel and Distributed Processing. Vol. 1388. Orlando, Florida, USA: Springer. doi:10.1007/3-540-64359-1_724.
  19. ^ Rick Merritt (April 16, 2007). "Dolphin, Stargen Swims After InfiniBand in Clusters". EE Times. Retrieved October 25, 2021.
  20. ^ "GTC Silicon Valley-2019: Dynamic Sharing of GPUs and IO in a PCIe Network". NVIDIA Developer. April 28, 2019.
  21. ^ Markussen, Jonas; Kristiansen, Lars Bjørlykke; Halvorsen, Pål; Kielland-Gyrud, Halvor; Stensland, Håkon Kvale; Griwodz, Carsten (July 8, 2021). "SmartIO: Zero-overhead Device Sharing through PCIe Networking". ACM Transactions on Computer Systems. 38 (1–2): 2:1–2:78. doi:10.1145/3462545. hdl:10852/86684.
  22. ^ "PCIe with low cost and low latency, ideal for sharing resources". www.microcontrollertips.com.
  23. ^ "Automotive Industry Eyes Low-Cost, Low-Latency PCIe for Sharing Resources – Lynnette Reese".

External links[edit]