 | This article has multiple issues. Please helpimprove it or discuss these issues on thetalk page.(Learn how and when to remove these messages) (Learn how and when to remove this message)
|
_built_at_Caltech_-_Computer_History_Museum_(2007-11-10_22.57.36_by_Carlo_Nardone).jpg)
_-_Computer_History_Museum_(2007-11-10_22.57.18_by_Carlo_Nardone).jpg)
TheIntel Paragon is a discontinued series ofmassively parallelsupercomputers that was produced byIntel in the 1990s. TheParagon XP/S is a productized version of the experimentalTouchstone Delta system that was built atCaltech, launched in 1992. The Paragon superseded Intel's earlieriPSC/860 system, to which it is closely related.
The Paragon series is based on theIntel i860RISCmicroprocessor. Up to 2048 (later, up to 4096) i860s are connected in a 2D grid. In 1993, an entry-levelParagon XP/E variant was announced with up to 32 compute nodes.
The system architecture is a partitioned system, with the majority of the system comprising diskless compute nodes and a small number of I/O nodes interactive service nodes. Since the bulk of the nodes have no permanent storage, it is possible to "Red/Black switch" the compute partition from classified to unclassified by disconnecting one set of I/O nodes with classified disks and then connecting an unclassified I/O partition.
Intel intended the Paragon to run theOSF/1 ADdistributed operating system on all processors. However, this was found to be inefficient in practice, and alight-weight kernel calledSUNMOS was developed atSandia National Laboratories to replace OSF/1 AD on the Paragon's compute processors.
Oak Ridge National Laboratory operated aParagon XP/S 150 MP, one of the largest Paragon systems, for several years.
The prototype for the Intel Paragon was the Intel Delta, built by Intel with funding fromDARPA and installed operationally at theCalifornia Institute of Technology in the late 1980s with funding from theNational Science Foundation. The Delta was one of the few computers to sit significantly above the curve ofMoore's Law.
The computer boards was produced in two variants: the GP16 with 16 MB of memory and two CPUs, and the MP16 with three CPUs. Each node has a B-NIC interface that connects to the mesh routers on the backplane. The compute nodes are diskless and performed all I/O over the mesh. During system software development, a light-pen was duct-taped to the status LED on one board and a timer interrupt was used tobit bang aserial port[citation needed].
The B-NICASIC is the square chip with the circular heat-sink.
The IO boards have eitherSCSI drive interfaces orHiPPI network connections and are used to provide data to the compute nodes. They do not run any user applications. The MP64 I/O node has three i860 CPUs and ani960 CPU used in the disk controller.
| Records | ||
|---|---|---|
| Preceded by Numerical Wind Tunnel 124.0 gigaflops | World's most powerful supercomputer June 1994 | Succeeded by Numerical Wind Tunnel 170.0 gigaflops |
