mccalpin@perelandra.cms.udel.edu (John D. McCalpin) (02/02/91)
Aren't there any more SPEC results out there? I only have 66-67 systems in the table and there are a number of duplicates. It sure would be nice to be able to include machines like the Cray Y/MP, the SGI 4D/35, and the new Sun Sparc 2 machines. By the way, the newest table is set up to show: (1) Total SPECmark (2) Integer SPECmark (3) FP SPECmark (4) FP/Int (5) Best/Worst (6) Best of 10 (7) Worst of 10 It is interesting to note, for example, that the *slowest* ratio for the IBM RS/6000 Model 320 (13.72) is faster than the *fastest* ratio of the Sun Sparc I+ (12.78). It is also interesting to note that only *1* machine has any individual results more than 100x as fast as the VAX 11/780! (The machine is the Stardent 3010 at 107x. The IBM RS/6000 Model 540 is close at 91x). As usual, the table in 'sc' format is available by anonymous ftp from perelandra.cms.udel.edu, in the file pub/bench/spec.sc. If you don't have the 'sc' spreadsheet program, it is available in pub/sc, and should compile OK on most UNIX machines. DISCLAIMER: There ain't nothing official about this.... -- John D. McCalpin mccalpin@perelandra.cms.udel.edu Assistant Professor mccalpin@brahms.udel.edu College of Marine Studies, U. Del. J.MCCALPIN/OMNET