Retrospective: the Cedar system

A. Veidenbaum, P.-C. Yew, D. J. Kuck, C. D. Polychronopoulos, D. H. Padua, E. S. Davidson, K. Gallivan
1998 25 years of the international symposia on Computer architecture (selected papers) - ISCA '98  
accepted as a way to speed up the execution of a single program. The primary goal of the Cedar project was to "demonstrate that the supercomputers of the future can exhibit the general-purpose behavior and be easy to use" '. We felt that major advances in the state of hardware technology, architecture, compilers, and parallel algorithms made such a demonstration possible. A two-phase approach was advocated: the construction of a 32processor prototype followed by a production system with
more » ... s of processors. We stated that "the prototype design must include the details of scaling the prototype up to a larger, faster production system". Both "architectural and technological upward" scalability was required. Another goal was to have the prototype "achieve Cray-1 speeds for programs written in high-level languages and automatically restructured" by a compiler. Finally, "an integral part of the design... was to allow multiprogramming". 1. The quotes are from the [GKLS83] reference in the 1993 ISCA-20 paper.
doi:10.1145/285930.285965 dblp:conf/isca/VeidenbaumYKPPDG98 fatcat:obv6ipwmffbh7e27pzrhkzaza4