wjc@mit-eddie.UUCP (Bill Chiarchiaro) (12/04/85)
Does anyone know what ever happened to the IBM 801 Simplified Instruction Set minicomputer?
noman@gatech.CSNET (Jeffrey L. Grover) (12/09/85)
In article <632@mit-eddie.UUCP>, wjc@mit-eddie.UUCP (Bill Chiarchiaro) writes: > Does anyone know what ever happened to the IBM 801 Simplified Instruction > Set minicomputer? if you dig into the recent announcemnets about the IBM workstation you'll find something to the effect: 1. The 801 project was an experiment 2. The findings of that experiment were implemented in the newly announced workstation 3. The ~801 architecture is being emulated via microcode on a 68000 ( <<== ?? ) 4. The workstation is an AT chassis with the above engine -- jeffg ( aka noman ) Dept : GTRI/CTAD Office: ERB rm 34 Phone : 894-3456 GTRI/CTAD ERB rm 34 894-3456
bruceb@amiga.UUCP (Bruce Barrett) (12/10/85)
In article <2191@gatech.CSNET> noman@gatech.CSNET (Jeffrey L. Grover) writes: > 3. The ~801 architecture is being emulated via > microcode on a 68000 ( <<== ?? ) Well, IBM has had practice with this sort of thing...The IBM XT/370 emulated a 370 by re-microcoding 1 (or 2??) 68000's and an 8087 (for floating point). --Bruce Barrett
noman@gatech.CSNET (Jeffrey L. Grover) (12/10/85)
In article <373@amiga.amiga.UUCP>, bruceb@amiga.UUCP (Bruce Barrett) writes: > In article <2191@gatech.CSNET> noman@gatech.CSNET (Jeffrey L. Grover) writes: > > 3. The ~801 architecture is being emulated via > > microcode on a 68000 ( <<== ?? ) > > Well, IBM has had practice with this sort of thing...The IBM > XT/370 emulated a 370 by re-microcoding 1 (or 2??) 68000's and an 8087 > (for floating point). > > --Bruce Barrett yep, IBM put 2 68000's in the XT/360 1. microcoded to execute as a 360 sans floating point operations 2. microcoded as a floating point co-processor BTW, there is an 8088 in there too ... it's an I/O processor -- jeffg ( aka noman ) Dept : GTRI/CTAD Office: ERB rm 34 Phone : 894-3456 GTRI/CTAD ERB rm 34 894-3456
stubbs@ncr-sd.UUCP (Jan Stubbs) (12/11/85)
In article <632@mit-eddie.UUCP> wjc@mit-eddie.UUCP (Bill Chiarchiaro) writes: >Does anyone know what ever happened to the IBM 801 Simplified Instruction >Set minicomputer? Rumour has it that it will appear shortly as a high-performance engineering workstation, probably running Unix. Jan Stubbs ...sdcsvax!ncr-sd!stubbs
bobbyo@celerity.UUCP (Bob Ollerton) (12/11/85)
Workstation? What workstation? Rumors don't equal an announcement. Maybe IBM will have better luck in April, Well thats what the LATEST rumors say. -- Bob Ollerton; Celerity Computing; 9692 Via Excelencia; San Diego, Ca 92126; (619) 271 9940 {decvax || ucbvax || ihnp4}!sdcsvax!celerity!bobbyo akgua!celerity!bobbyo
kim@mips.UUCP (Kim DeVaughn) (12/11/85)
> In article <632@mit-eddie.UUCP> wjc@mit-eddie.UUCP (Bill Chiarchiaro) writes: > >Does anyone know what ever happened to the IBM 801 Simplified Instruction > >Set minicomputer? > > Rumour has it that it will appear shortly as a high-performance engineering > workstation, probably running Unix. When I was at Amdahl, I seem to recall that it (or a close variation) was being used inside the Channel Director of the 308x and/or 3090-x00 machines. /kim -- UUCP: {decvax,ucbvax,ihnp4}!decwrl!mips!kim DDD: 415-960-1200 USPS: MIPS Computer Systems Inc, 1330 Charleston Rd, Mt View, CA 94043
doug@terak.UUCP (Doug Pardee) (12/18/85)
> When I was at Amdahl, I seem to recall that it (or a close variation) was > being used inside the Channel Director of the 308x and/or 3090-x00 machines. Strange, a fellow I knew who used to fix 'em said that they're just good-ol' 158's. -- Doug Pardee -- CalComp -- {hardy,savax,seismo,decvax,ihnp4}!terak!doug
mat@amdahl.UUCP (Mike Taylor) (12/23/85)
> > When I was at Amdahl, I seem to recall that it (or a close variation) was > > being used inside the Channel Director of the 308x and/or 3090-x00 machines. > > Strange, a fellow I knew who used to fix 'em said that they're just > good-ol' 158's. The 3033 "Channel Directors" appeared to be recycled 158's. This predated the TCM packaging that IBM used in the 308X and 3090-x00. The 308X was TCM packaged and therefore unlikely to be derived from 158 MST technology. There is a rumor (as yet unverified) that the 3090-x00 EXDC is an 801. -- Mike Taylor ...!{ihnp4,hplabs,amd,sun}!amdahl!mat [ This may not reflect my opinion, let alone anyone else's. ]
darrell@sdcsvax.UUCP (Darrell Long) (01/20/86)
Alright, enough of this shift nonsense... Let's see, I suppose that I should try to start something new... How's this: does anyone know the why IBM could not release the news of their 801 project until just recently? I understand it has something to do with lawsuits and Reagan. Or, better yet, has anyone yet seen one of the Fairchild CLIPPER machines? From the marketing cruft I got from Fairchild, it would appear that they have done just about everything right. -- Darrell Long Department of Electrical Engineering and Computer Science University of California, San Diego UUCP: sdcsvax!darrell ARPA: darrell@sdcsvax
henry@utzoo.UUCP (Henry Spencer) (01/22/86)
> ...does anyone know the > why IBM could not release the news of their 801 project until just > recently?... Huh? The 801 was not exactly accompanied by a blaze of publicity, but the first paper describing it was in the ASPLOS [?] proceedings some years ago. There hasn't been any secret about it for a long time. You haven't seen any IBM marketing hype because it was not a product, just an internal experiment and then a research tool. -- Henry Spencer @ U of Toronto Zoology {allegra,ihnp4,linus,decvax}!utzoo!henry
aglew@ccvaxa.UUCP (01/25/86)
Why did IBM not release news about the 801 until just about now? Paranoid answer: because the 801 RISC approach was valid when VLSI was young (just how long has Patterson's RISC group been going on) but is no longer applicable because of increasing density (perhaps the argument that microcoded control takes up too much space is no longer valid if you can cram as much parallel execution hardware as you can afford, to 1 cycle most simple instructions, plus as much microcode as you need to sequence complex ones. Microcode was a lump that lay across the chip boundary - RISC placed this lump outside because it couldn't all be fitted inside - maybe IBM can now squeeze it all onto the chip?) Just paranoid - but replace IBM with Fujitsu or Hitachi or NEC and start sweating... Andy "Krazy" Glew