Path: utzoo!attcan!telly!lethe!torsqnt!news-server.csri.toronto.edu!rutgers!apple!agate!darkstar!ucscb.UCSC.EDU!unknown From: unknown@ucscb.UCSC.EDU (The Unknown User) Newsgroups: comp.sys.apple2 Subject: Re: Stellar 7 re-release Message-ID: <10127@darkstar.ucsc.edu> Date: 15 Dec 90 02:42:07 GMT References: <9012120353.AA26625@apple.com> <3137.27692c59@miavx1.acs.muohio.edu> Sender: usenet@darkstar.ucsc.edu Organization: University of California, Santa Cruz; Open Access Computing Lines: 41 In article <3137.27692c59@miavx1.acs.muohio.edu> rlcollins@miavx1.acs.muohio.edu (Ryan 'Gozar' Collins) writes: >I've heard discussion after discussion on the uselessness of MIPS as a >speed comparison. There are too many other factors that are involved. And you don't seen to know a lot of them. God, is there an "ignore" command in rn like there are in forum programs I see? >A 1Mhz GS faster than a 4.77MHz IBM, this I find hard to believe. If it is While that is true also, the commonly accepted statistic is that the original Apple // (that is, 1 Mhz) is faster than a 4.77 Mhz IBM PC. I will admit that I do not have any references or statistics to back up this claim, although I am virtually certain someone else does. (This is so well known that it's like a "the sky is blue" or "the Earth is round" statement). Another claim, that seems like it's on a little shakier ground, is that the standard 2.8 Mhz GS is as fast as an X Mhz '286. I don't recall the value of the '286 that was used in this comparison though. Someone else will most likely be able to come through with the facts on this one too. >true, it could just be the fact that the original IBM was produced in 1981, >and was probably very inefficient. I would like to see a speed test though. >Anyone got the source code in C for any of the standard tests? (Sieve of >Erostones (sp?), and a few others I can't think of right now.) We could put >together a collection of these and run them on all the machines we have >access to, which would include about every machine concievable! Talk about not knowing what other factors are involved! This guy is trying to compare computers based on their C compilers! While I do not doubt that C source for these types of tests (Are you referring to the "Drhystones" that are mentioned a lot?), I think that speed tests for a computer should be written directly in assembly. This takes out the possibility (probability!) of a compiler not being as efficient as possible. -- /Apple II(GS) Forever! unknown@ucscb.ucsc.edu MAIL ME FOR INFO ABOUT CHEAP CDs\ |WRITE TO ORIGIN ABOUT ULTIMA VI //e and IIGS! Mail me for addresses, & info. | \ "Dammit Bev, is it you inside or is it the clown?" -IT by Stephen King /