Path: utzoo!utgpu!news-server.csri.toronto.edu!cs.utexas.edu!sdd.hp.com!wuarchive!uunet!zephyr.ens.tek.com!tektronix!percy!m2xenix!quagga!proxima!olsa99!tabbs!tabbs!aris From: aris@tabbs.UUCP (Aris Stathakis) Newsgroups: comp.sys.ibm.pc.hardware Subject: Re: MIPS on 386 Message-ID: Date: 27 May 91 16:40:20 GMT References: <1991May23.105137.294@jarvis.csri.toronto.edu> <1991May24.125642.13818@rathe.cs.umn.edu> Organization: TABBS - Totally Awesome BBS Lines: 24 In <1991May24.125642.13818@rathe.cs.umn.edu> ian@rathe.cs.umn.edu (Ian Hogg) writes: >In article <1991May23.105137.294@jarvis.csri.toronto.edu> byu@csri.toronto.edu (Benjamin Yu) writes: >>I want to find out how many mips are the 386's running at. A number of >>dealers told me their 33 Mz machine runs at about 7 to 8 mips. When I go >>to the stores and run the mips program from Chips and Technology, it only >>shows actual MIPS to be around 4.7. Does anyone have a clue who is lying: >>the dealer or the program?? > I see this on my 33Mhz (supposedly 8 MIPS) 386. What I suspect is happening >is the MIPS test gives a value of 7-8 MIPS for register to register operations >(I think that's the test anyways). What it appears to me is the classic case >of vendors reporting "peak" performance. What I think the problem is that PC dealers use "Power Meter" instead of the Chips and Technologies mips program. Power meter always seems to give a more favorable reading :-) Aris -- Aris Stathakis | Bang: ..!uunet!ddsw1!olsa99!tabbs!aris or aris@tabbs.UUCP - - ------------------------- Sex, dope, UNIX! -------------------------------