Path: utzoo!attcan!uunet!lll-winken!lll-tis!ames!amdahl!chuck From: chuck@amdahl.uts.amdahl.com (Charles Simmons) Newsgroups: comp.arch Subject: Re: NSIEVE C Source File (long) Message-ID: Date: 2 Sep 88 08:31:10 GMT References: <1070@marlin.NOSC.MIL> <1073@marlin.NOSC.MIL> <2899@winchester.mips.COM> <1076@marlin.NOSC.MIL> Reply-To: chuck@amdahl.uts.amdahl.com (Charles Simmons) Distribution: comp.arch Organization: Amdahl Corporation, Sunnyvale CA Lines: 26 In article <1076@marlin.NOSC.MIL> aburto@marlin.nosc.mil.UUCP (Alfred A. Aburto) writes: >For example, the Amdahl 5890 Dhyrstone/sec is I believe about 30,000. Well, >on the Amiga with 68020 at 14.32 Mhz and Manx Aztec C (with no 'optimizer') >the best Dhrystones/sec figure I've seen is 3034. So the Amdahl 5890 has a >performance gain of 30000/3034 = 9.9 (roughly) over the Amiga/020. 45,000 would be a better approxamation for the dhrystone/sec figure on a 5890. 45000/3034 = 14.8 (roughly). [30,000 is in the ballpark of a 5880.] >Thanks to Chuck Simmons of Amdahl, I also have the nsieve results. The >Amdahl 5890 ran nsieve (for the 8191 sized array) in 0.05 seconds. An >average of 5 runs on the Amiga/020 yielded a run time of 0.48+/-0.02 seconds. >These results indicate the Amdahl 5890 has a performance gain of >0.48 / 0.05 = 9.6 over the Amiga/020. That is (in this one isolated case) >both the Dhrystone and the nsieve are yielding pretty much the same >information within about a 4% error. I would like to investigate these >relationships in more detail, but (right now) there is not sufficient data. For all you GNU fans out there, the current version of GCC produces a binary that runs in 0.033 seconds for the 8191 sized array. >Al Aburto >aburto@marlin.nosc.mil.UUCP -- Chuck