This article needs additional citations for verification. (August 2007) (Learn how and when to remove this template message)
In a tree data structure, every branch has the same thickness, regardless of their place in the hierarchy—they are all "skinny" (skinny in this context means low-bandwidth). In a fat tree, branches nearer the top of the hierarchy are "fatter" (thicker) than branches further down the hierarchy. In a telecommunications network, the branches are data links; the varied thickness (bandwidth) of the data links allows for more efficient and technology-specific use.
Applications in supercomputers
Supercomputers that use a fat tree network include the two fastest as of late 2018, Summit and Sierra, as well as Tianhe-2, the Meiko Scientific CS-2, Yellowstone, the Earth Simulator, the Cray X2, the Connection Machine CM-5, and various Altix supercomputers.
Mercury Computer Systems applied a variant of the fat tree topology—the hypertree network—to their multicomputers. In this architecture, 2 to 360 compute nodes are arranged in a circuit-switched fat tree network. Each node has local memory that can be mapped by any other node.[vague] Each node in this heterogeneous system could be an Intel i860, a PowerPC, or a group of three SHARC digital signal processors.
In August 2008, a team of computer scientists at UCSD published a scalable design for network architecture that uses a topology inspired by the fat tree topology to realize networks that scale better than those of previous hierarchical networks. The architecture uses commodity switches that are cheaper and more power-efficient than high-end modular data center switches.
This topology is actually a special instance of a Clos network, rather than a fat-tree as described above. That is because the edges near the root are emulated by many links to separate parents instead of a single high-capacity link to a single parent. However, many authors continue to use the term in this way.
- Leiserson, Charles E (October 1985). "Fat-trees: universal networks for hardware-efficient supercomputing" (PDF). IEEE Transactions on Computers. 34 (10): 892–901. doi:10.1109/TC.1985.6312192.
- Leiserson, Charles E.; Abuhamdeh, Zahi S.; Douglas, David C.; Feynman, Carl R.; Ganmukhi, Mahesh N.; Hill, Jeffrey V.; Daniel Hillis, W.; Kuszmaul, Bradley C.; St. Pierre, Margaret A.; Wells, David S.; Wong, Monica C.; Yang, Shaw-Wen; Zak, Robert (1992). "The Network Architecture of the Connection Machine CM-5". SPAA '92 Proceedings of the fourth annual ACM symposium on Parallel algorithms and architectures. ACM. pp. 272–285. doi:10.1145/140901.141883. ISBN 978-0-89791-483-3.
- Yuefan Deng (2013). "3.2.1 Hardware systems: Network Interconnections: Topology". Applied Parallel Computing. World Scientific. p. 25. ISBN 978-981-4307-60-4.
- "November 2018 TOP500". TOP500. November 2018. Retrieved 2019-02-11.
- "Summit - Oak Ridge National Laboratory's next High Performance Supercomputer". Oak Ridge Leadership Computing Facility. Retrieved 2019-02-11.
- Barney, Blaise (2019-01-18). "Using LC's Sierra Systems - Hardware - Mellanox EDR InfiniBand Network - Topology and LC Sierra Configuration". Lawrence Livermore National Laboratory. Retrieved 2019-02-11.
- Dongarra, Jack (2013-06-03). "Visit to the National University for Defense Technology Changsha, China" (PDF). Netlib. Retrieved 2013-06-17.
- Al-Fares, Mohammad; Loukissas, Alexander; Vahdat, Amin (2008). "A scalable, commodity data center network architecture" (PDF). Proceedings of the ACM SIGCOMM 2008 conference on Data communication. ACM. pp. 63–74. doi:10.1145/1402958.1402967. ISBN 978-1-60558-175-0.