Path: utzoo!mnetor!tmsoft!torsqnt!news-server.csri.toronto.edu!cs.utexas.edu!swrinde!zaphod.mps.ohio-state.edu!usc!ucsd!rutgers!mcdchg!ddsw1!karl From: karl@ddsw1.MCS.COM (Karl Denninger) Newsgroups: comp.sys.amiga Subject: Re: Re: A3000UX Seems Fated (Kill file alert!) Summary: None of this matters today; ISA has more bandwidth than disk can use Message-ID: <1990Dec24.220257.12208@ddsw1.MCS.COM> Date: 24 Dec 90 22:02:57 GMT References: <39228@nigel.ee.udel.edu> <1990Dec17.052316.19609@NCoast.ORG> Reply-To: karl@ddsw1.MCS.COM (Karl Denninger) Organization: Macro Computer Solutions, Inc., Wheeling, IL Lines: 78 In article <1990Dec17.052316.19609@NCoast.ORG> davewt@NCoast.ORG (David Wright) writes: >In article <39228@nigel.ee.udel.edu> ST402248@brownvm.brown.edu (F. Scott Porter) writes: >>Unfortunately you are missing out on how the current crop of PC's handle >>High throughput devices. Most of the '386 and '486 machines have private >>memory buses which are not only 32 bits wide but extremely fast since >>they are very specialized. Some of the newer machines also implement > As someone who puts these things togather at least once a week, I >am not missing out on anything. I am quite aware that some *real* 386 >systems have a seperate 32-bit memory bus. NO 386-SX (which are the most >common 386 computers you will find) do. And even on the systems that do, >there is seldom more than 8 megabytes provided for on the motherboard, and >the completely non-standard busses used for the memory (as in the WYSE PC >systems, etc.) means you can't take one mfgr.'s card and use it in another. >Even on the systems I have seen that support up to 16 meg on the motherboard >(remember the 3000 supports 18), there is seldom expansion provided beyond >16 megabytes. And I was not wrong when I said that OS-2 only supports 16 meg >of "real" RAM. As someone who also puts these things together daily, services them to the chip level, and runs both DOS and Unix on these systems, I can assure you that the 386SX is not representative of anything. The 386/25 and /33 caching systems are more representative. And both are CHEAP and FAST. The SX machines are more like an Amiga 500 -- intentionally crippled hardware for a overly price-conscious consumer. Anyone who runs Unix on an SX-based system deserves the slow speed. "Seldom" does not equal "not available" on the RAM expansion. Check with the 486 owners -- most of them can do 64MB on the motherboard, using 4MB SIMMS. No problem; plug and play. >>SCSI devices in the same manner. Thus your argument about slow ISA >>and EISA buses doesn't apply to memory and sometimes doesn't >>apply to hard disk access. These things then become very machine >>specific. I'm not advocating any particular point of view about the >>relative speed/value of PC's versus Amiga's (grown out of that). Just >>trying to point out some mis-information. > This is again true, but even less than the RAM. I have yet to see >ANY PC with SCSI built into the motherboard, although I am sure there >must be one somewhere. I HAVE seen 32-bit EISA HD controllers, so at least a >32-bit controller could be added. But the whole point I was making was that >the 16-bit bus on the Amiga 2000 series blows away (it's not even close) the >16-bit bus on ISA PC's, and the 32-bit bus on the Amiga 3000 series does beat >the EISA bus, even if only by a smaller margin in some speed areas (but by more >in others). This is a non-issue. The ISA PC bus can pass 8MB of data per second. The best SCSI fixed disks we have available today can do 2MB/second. MOST disks cannot sustain that kind of transfer rate for long, even in synchronous mode. SCSI has a maximum transfer rate of 5MB/sec. That is STILL well under the ISA bus machine's bus bandwidth. Since there is little or no reason to put anything ELSE on that bus other than perhaps video, you have 4X the needed processor <> disk bandwidth. Anyone who tries to sell you more bandwidth than you need is a thief -- of your money, that is. Note that "real" controllers for the ISA bus, those which do bus mastering (AHA1542B for example) are here and do work. They take nearly all the load off the processor, do intelligent seek ordering, overlapped command/data requests, and all kinds of other wonderful things. Today EISA is a waste of money, as is MCA. ISA is more bus than you can use for disk I/O. Hell, I can do better with an ISA PC than most workstations in disk performance with a little judicious tuning of disk parameters! The one place where it COULD matter is in frame buffers. But only a fool has their CPU doing display-intensive work -- that's what special chips are for, right? And those chips damn well better be on their own PRIVATE memory bus, or you ARE going to see performance problems. -- Karl Denninger (karl@ddsw1.MCS.COM, !ddsw1!karl) Public Access Data Line: [+1 708 808-7300], Voice: [+1 708 808-7200] Macro Computer Solutions, Inc. "Quality Solutions at a Fair Price"