Xref: utzoo comp.sys.mac:46319 comp.protocols.appletalk:2902 Path: utzoo!utgpu!jarvis.csri.toronto.edu!mailrus!cs.utexas.edu!wuarchive!udel!rochester!rutgers!att!dptg!mtuno!rjk From: rjk@mtuno.ATT.COM (Roberto Kohler) Newsgroups: comp.sys.mac,comp.protocols.appletalk Subject: Re: MIP rating for the Mac II Keywords: performance Message-ID: <2788@mtuno.ATT.COM> Date: 15 Jan 90 15:45:10 GMT Followup-To: comp.sys.mac Organization: AT&T BL Middletown/Lincroft NJ USA Lines: 115 Thanks to all those that had something useful to say. -------------- Roberto Kohler, rjk@mtung.att.com The question was: >>Does anyone out there know how the Mac II, Max IIx, and Mac II CX compare >>in performance with the 80386 based machines? I'm trying to find out the >>MIP rating of the Macs and how they compare with 386 based machines. >>Would the Mac IIx be equivalent to a 20 MHz 386 machine, etc. The responses I received included: ----------------------------------------------------------------------- ----------------------------------------------------------------------- >> Is the Mac II as fast as a 20 Mhz 386 This is great, the guy asks a simple question and 10k of absolute noise is generated no one answering him! Now it is true no 1 benchmark can indicate much, but in my experience the Mac II and Mac IIx both perform slightly better than an 80386 clone running a dos extender (20Mhz) The 80387 at 20mhz is somewhat faster than the 68882 running at 15+ Mhz, in my experience, except for some transcendental functions. Some Benchmarks: sieve (100 iterations) - 5 secs (386 20 Mhz) 4 secs (mac II and IIx) qsort (byte benchmark) - 18 secs (386 20 Mhz) 9 secs (mac II) 6 secs (mac iix) using Turbo C 2.0 for the 386 and MPW C for the Mac (using -mc68020 option) I do not have fp figures handy but the 387 was faster than the 68882 on the mac iix in most cases. They were fairly comparable though. In day to day use, mac applications on a Mac II or IIx tend to perform slightly faster than the MS-DOS applications running on 386's. If the MS-DOS application is text only, sometimes it feels faster. ----------------------------------------------------------------------- ----------------------------------------------------------------------- > >I would reply via Email, but this is a VERY bad comparison. The idea >of the mythical "MIP" is an idead propagated by computer sales(wo)men. >A MIP is ONLY useful when comparing proccessors with the same instruction >set. For example, in my Mac, I have a 16mhz 68020/68881 which can put I have one friend who told me that a machines MIPS is usually pro-rated to a VAX MIPS. For example, if a RISC chip can execute 30 millions instrucion per second but it takes on average 3 RISC instructions to equal that of one VAX, then the the chip is rated at 10 MIPS (not 30). I do not know how true this is. Most people I know, however, say MIPS stands for: Meaningless Index of Processor Speed ----------------------------------------------------------------------- ----------------------------------------------------------------------- My experience has been that, because they use their MIPs in different ways, it's not very useful to compare things like that. Byte ran such a benchmark a year or so ago, though: fastest 80386 vs. fastest 68030. Your library should have it. ----------------------------------------------------------------------- ----------------------------------------------------------------------- I don't believe that any of the 3 machines you mentioned are in the same ballpark as the 386 machines (especially @ 25MHz). They are all 16MHz machines, for one thing. I recall seeing the Mac II as being in the 2-3 MIP range; this would make the other two in the 2+ to 4 MIP range most likely. (probably near the middle of those ranges). The Mac IIci might approach 5 or so... -- ----------------------------------------------------------------------- ----------------------------------------------------------------------- Sorry I have no info, but do post a summary or let me personally know of any results you get. My friend and I always debate the issue. (I have an SE/30 and he has a 386 machine.) ----------------------------------------------------------------------- ----------------------------------------------------------------------- One thing to keep in mind - the newer Macs come with a math coprocessor, but very few (or no) '386 machines come with a coprocessor. The 8387 costs about $400. Of course, if you don't do much "math" you won't care. This complicates "MIPS" ratings, since for floating point and transcendentals, at least, what you get out of the box is not "equal". I find the older macs Plus, SE slow. The newer ones (SE/30, IIcx, IIci) are pretty fast. ----------------------------------------------------------------------- ----------------------------------------------------------------------- The original MAC II is about 1/4 to 1/3 the speed of a current generation 386 machine. This is by my own very extensive tests. I have read that the latest MAC II systems are about twice as fast as the original Mac II. In any case, the fastest 68030 systems are not as fast as the fastest 386 PC clones, so it is extremely safe to say that the latest 386 will be faster than the latest Mac. They are no longer four times as fast, though. The latest Mac II would not be as fast as a good 20 MHz PC clone. ----------------------------------------------------------------------- ----------------------------------------------------------------------- A straight MIPS comparison between Mac II machines and 80386 machines is somewhat problematic-- the Mac has practically zero overhead from its windowing environment where DOS & OS/2 machines lose a lot of performance to their windowing interfaces. ----------------------------------------------------------------------- -----------------------------------------------------------------------