The Community for Technology Leaders
Green Image
<p>The design of the Sparcle chip, which incorporates mechanisms required for massively parallel systems in a Sparc RISC core, is described. Coupled with a communications and memory management chip (CMMU) Sparcle allows a fast, 14-cycle context switch, an 8-cycle user-level message send, and fine-grain full/empty-bit synchronization. Sparcle's fine-grain computation, memory latency tolerance, and efficient message interface are discussed. The implementation of Sparcle as a CPU for the Alewife machine is described.</p>
Anant Agarwal, David Kranz, Godfrey D'Souza, Mike Parkin, John Kubiatowicz, Donald Yeung, Beng-Hong Lim, "Sparcle: An Evolutionary Processor Design for Large-Scale Multiprocessors", IEEE Micro, vol. 13, no. , pp. 48-61, May/June 1993, doi:10.1109/40.216748
93 ms
(Ver 3.3 (11022016))