SIMD machines

Behrooz Parhami
1995 SIGARCH Computer Architecture News  
About This Report I volunteered m write this report during the SIMD panel session held on 2/9/95 at Frontiers '95. All panelists cooperated by sending me their transparency masters. A draft report was prepared based on these transparency masters, position statements published in the Frontiers '95 proceedings on pp. 466-469, and my own notes. The draft was e-marled on 3/17/95 to the panel organizer/moderator and the panelists for their comments. This final version of the report is based on
more » ... ts and markups received through 3/31/95. I have drawn from the panelists' ideas freely, using quotation marks only when including their statements verbatim. The panel consisted of both academic and industry experts in the field of massively parallel system.~ (see the table below). All but Tim Bridges, who is currently involved in a large-scale software development project for the MasPar MP-2 SIMD architecture, have built working SIMD machines. The vast practical experience of the panel was quite evident in the insightful presentations and interactions. It is indeed a privilege for me to have worked on this report. * Panel organizer and moderator. #+ STARAN and Massively Parallel .P!oce.sso~" S IMD m,3chines by Goodyear Aerospace. ~.t~ce.ssmK-m-Memory crop, o es~. Deq. m ~ection ? or_ .t~.'s report. ~ LqSU'tOu[eo Array rrocessor, aescnDeo m ~ection 4 ot mis report. PAnitionable Sirh .d/Mired machine, pro totyRe reconfigm'able parallel system. trnage unaerstanding Architecture, design~:! for integrated reid-time v~sion tasks. What is SIMD? The first massively parallel machines had single-instruction-stream multiple-data-stream or SIMD (Sim-Dee) designs. SIMD implies that a central unit fetches and interprets the instructions and then broadcasts appropriate control signals to a number of processors operating in lock step. This initial interest in SIMD resulted both from characteristics of early parallel applications and economic necessity. Some of the earliest applications, such as air traffic control, are what several panelists characterized as "embarrassingly parallel" ('H.J. Siegel and I prefer the more positive terms "parallel= machine=friendly" and "pleasantly parallcr'). Such applications tend to be much easier to program in SIMD languages and lead to more cost-effective SIMD hardware. On the economics side, fullfledged processors with reasonable speed were quite expensive in those days, thus limiting any massively parallel system (one having > 1000 processors, say) to the SIMD variety. m 19 m
doi:10.1145/218864.218868 fatcat:zvaf7cbs55gjrhf6eajthnetiq