TL;DR: The Myrinet local area network employs the same technology used for packet communication and switching within massively parallel processors, but with the highest performance per unit cost of any current LAN.
Abstract: The Myrinet local area network employs the same technology used for packet communication and switching within massively parallel processors. In realizing this distributed MPP network, we developed specialized communication channels, cut-through switches, host interfaces, and software. To our knowledge, Myrinet demonstrates the highest performance per unit cost of any current LAN. >
TL;DR: An apparatus, system and method for providing multiple logical partitions in a system area network are provided in this paper, which allows multiple operating systems to share the resources of a single physical host channel adapter (HCA).
Abstract: An apparatus, system and method for providing multiple logical partitions in a system area network are provided Logical partitioning support is provided for host channel adapters which allows multiple operating systems to share the resources of a single physical host channel adapter (HCA). The apparatus, system and method ensures that each operating system is unaware that the HCA hardware resources are being shared with other operating systems and further guarantees that the individual operating systems are prevented from accessing HCA hardware resources which are associated with other operating systems.
TL;DR: Adaptive sets of lanes are configured between routers in a system area network as discussed by the authors, where source nodes determine whether packets may be adaptively routed between the lanes by encoding adaptive control bits in the packet header.
Abstract: Adaptive sets of lanes are configured between routers in a system area network. Source nodes determine whether packets may be adaptively routed between the lanes by encoding adaptive control bits in the packet header. The adaptive control bits also facilitate the flushing of all lanes of the adaptive set. Adaptive sets may also be used in uplinks between levels of a fat tree.
TL;DR: In this paper, a Transparent Network Computing extension to a highly available version of UNIX System V Release 4.2 is presented to provide a higher degree of availability to I/O devices by providing for the takeover of their controlling entity.
Abstract: A system area network computer system architecture is structured as a single system image cluster operating system to offer an opportunity to increase the availability to I/O devices in the system. The computing system comprises a number of processor units coupled to a plurality of input/output (I/O) elements by a routing fabric that provides each of the processor elements with access to any one of the I/O elements. Using a Transparent Network Computing extension to a highly available version of UNIX System V Release 4.2, the system provides a higher degree of availability to I/O devices by providing for the takeover of their controlling entity.
TL;DR: A new fault-Tolerant architecture that combines the best attributes of the software fault-tolerant Tandem NonStop systems with the hardware fault- tolerant integrity systems is introduced, based on the ServerNet System Area Network.
Abstract: The paper introduces a new fault-tolerant architecture that combines the best attributes of the software fault-tolerant Tandem NonStop systems with the hardware fault-tolerant integrity systems. This architecture is based on the ServerNet System Area Network (SAN). ServerNet, formerly called TNet, is a packetized byte-serial multistage network that supports both I/O and interprocessor traffic in fault-tolerant systems. Dual-ported CPUs and VO controllers connect to independent subnetworks in a variety of different network topologies. Systems can expand either through shared or distributed memory multiprocessing. A separate maintenance system controls system initialization, online configuration changes, and error reporting. The architecture's flexibility makes it suitable for a wide range of environments with varying requirements for performance, fault tolerance, and software compatibility. >