imacbeath@crocus.waterloo.edu (Ian MacBeath, Conrad Grebel College) (12/06/88)
In article <45900175@uxe.cso.uiuc.edu> mcdonald@uxe.cso.uiuc.edu writes: >Rahul Dhesi writes: >>Apocalypse approaches rapidly. From 8086 we derived 80286, and then >>things became more orderly as we went to 80386, 80486, and now 80586. >>When we reach 80986, what will happen? > >Use hex of course: 80a86, 80b86 ... 80f86. Then go to base 36 - >80g86,... 80z86. Rumor has it that that is exactly what Boeing is going to do: >7a7, 7b7 ... Too late. There's already an 80C86. The CMOS version which gets primarily used in laptops.
bcw@rti.UUCP (Bruce Wright) (12/09/88)
> In article <45900175@uxe.cso.uiuc.edu> mcdonald@uxe.cso.uiuc.edu writes: > >Rahul Dhesi writes: > >>Apocalypse approaches rapidly. From 8086 we derived 80286, and then > >>things became more orderly as we went to 80386, 80486, and now 80586. > >>When we reach 80986, what will happen? > > > >Use hex of course: 80a86, 80b86 ... 80f86. Then go to base 36 - > >80g86,... 80z86. There is, of course an 80186 (and an 80188) - this was a chip used briefly before the 80286 came out. It was never very popular, but it was used by a few clones (like the Radio Shack Model 2000 I believe). It was really just an 8086/8088 which had some of the microcode optimizations used by the 80286 - which means it runs about the speed of a '286 at a similar MHz rating, but without protected memory. The *88 chips ended at that point, I think - I've never heard of an 80288. What do you do with the architecture after the 80386 - outside of speedups like more on-chip cache and higher MHz? The architecture has pretty much reached its limit ... look at '386 native mode: a complete revamping of the instruction set! Seems to me that after '386 native mode there's no good place to take the architecture, it's already pretty much maxed out. So you either make it faster or you go to a new chip design. Why then is there all this hype about a '486? It'll probably only be a fast '386 (like the 80186 to an 8086). Bruce C. Wright
zu@ethz.UUCP (Urs Zurbuchen) (12/13/88)
In article <2618@rti.UUCP> bcw@rti.UUCP (Bruce Wright) writes: >What do you do with the architecture after the 80386 - outside of speedups >like more on-chip cache and higher MHz? The architecture has pretty much >reached its limit ... look at '386 native mode: a complete revamping of >the instruction set! Seems to me that after '386 native mode there's no >good place to take the architecture, it's already pretty much maxed out. >So you either make it faster or you go to a new chip design. Why then is >there all this hype about a '486? It'll probably only be a fast '386 >(like the 80186 to an 8086). The 80486 is rumored to have a virtual 80286 mode as the 80386 has a virtual 8086 mode. That's all we waited for, isn't it. So we can run multiple OS/2's on one computer :-) (If you run two OS/2's does this make it a complete Operating System ?) By the way, this virtual 80286 mode caused Intel a lot of problems. It seems to be the main reason why the chip is that late. ...urs uucp: ...!seismo!mcvax!cernvax!ethz!zu
Ralf.Brown@B.GP.CS.CMU.EDU (12/14/88)
In article <715@ethz.UUCP>, zu@ethz.UUCP (Urs Zurbuchen) writes: }The 80486 is rumored to have a virtual 80286 mode as the 80386 has a }virtual 8086 mode. That's all we waited for, isn't it. I suppose this means the 80586 will have a virtual 386 mode. I can see it now: run Windows/386, VM/386, and DESQview 386 simultaneously, each using multiple virtual 86 tasks.... -- UUCP: {ucbvax,harvard}!cs.cmu.edu!ralf -=-=-=- Voice: (412) 268-3053 (school) ARPA: ralf@cs.cmu.edu BIT: ralf%cs.cmu.edu@CMUCCVMA FIDO: Ralf Brown 1:129/31 Disclaimer? I |Ducharm's Axiom: If you view your problem closely enough claimed something?| you will recognize yourself as part of the problem.
allbery@ncoast.UUCP (Brandon S. Allbery) (12/16/88)
As quoted from <2618@rti.UUCP> by bcw@rti.UUCP (Bruce Wright): +--------------- | What do you do with the architecture after the 80386 - outside of speedups | like more on-chip cache and higher MHz? The architecture has pretty much | reached its limit ... look at '386 native mode: a complete revamping of | the instruction set! Seems to me that after '386 native mode there's no | good place to take the architecture, it's already pretty much maxed out. | So you either make it faster or you go to a new chip design. Why then is | there all this hype about a '486? It'll probably only be a fast '386 | (like the 80186 to an 8086). +--------------- From what I have heard (I don't know how reliable it is), the 80486 will come out in two versions: a native one and an 80486/32632 (!) hybrid... after which the iAPX86 line will be discontinued, folded into the iAPX32 line. So the question becomes, what follows the 32932? ++Brandon -- Brandon S. Allbery, comp.sources.misc moderator and one admin of ncoast PA UN*X uunet!hal.cwru.edu!ncoast!allbery ncoast!allbery@hal.cwru.edu comp.sources.misc is moving off ncoast -- please do NOT send submissions direct Send comp.sources.misc submissions to comp-sources-misc@<backbone>.
rob@conexch.UUCP (Robert Collins) (12/17/88)
In article <715@ethz.UUCP> zu@bernina.UUCP (Urs Zurbuchen) writes: -In article <2618@rti.UUCP> bcw@rti.UUCP (Bruce Wright) writes: ->What do you do with the architecture after the 80386 - outside of speedups ->like more on-chip cache and higher MHz? The architecture has pretty much ->reached its limit ... look at '386 native mode: a complete revamping of ->the instruction set! Seems to me that after '386 native mode there's no ->good place to take the architecture, it's already pretty much maxed out. ->So you either make it faster or you go to a new chip design. Why then is ->there all this hype about a '486? It'll probably only be a fast '386 ->(like the 80186 to an 8086). - -The 80486 is rumored to have a virtual 80286 mode as the 80386 has a -virtual 8086 mode. That's all we waited for, isn't it. So we can run -multiple OS/2's on one computer :-) (If you run two OS/2's does this -make it a complete Operating System ?) - -By the way, this virtual 80286 mode caused Intel a lot of problems. It -seems to be the main reason why the chip is that late. - In the latest (or one of the latest) issues of Microprocessor Report, says the '486 will have downloadable micro code, and a 6 instruction prefetch queue. As for the bigger prefetch queue, that means that relative jumps can be done in 0 clock cycles. But as to your assertion of disbelief that much can be done other than speedups, I think downloadable microcode is lightyears more advanced than the '386. For copies of Microprocessor report, you must pay $250/year for a subscription, but I find it well worth it. -- "Worship the Lord your God, and serve him only." Mat. 4:10 Robert Collins UUCP: ucbvax!ucivax!icnvax!conexch!rob HOMENET: (805) 523-3205 UUCP: uunet!ccicpg!turnkey!conexch!rob WORKNET: (805) 371-5081
allbery@ncoast.UUCP (Brandon S. Allbery) (12/18/88)
In article <13258@ncoast.UUCP>, allbery@ncoast.UUCP (Brandon S. Allbery) writes: +--------------- | From what I have heard (I don't know how reliable it is), the 80486 will | come out in two versions: a native one and an 80486/32632 (!) hybrid... +------------------------------------------------------^^^^^ OOPS!!! My apologies, people, I managed to confuse Intel and NS numbering schemes. I was trying for the "common form" number of the iAPX432 and related processors. Shows how familiar I am with *either*. Sigh.... ++Brandon -- Brandon S. Allbery, comp.sources.misc moderator and one admin of ncoast PA UN*X uunet!hal.cwru.edu!ncoast!allbery ncoast!allbery@hal.cwru.edu comp.sources.misc is moving off ncoast -- please do NOT send submissions direct Send comp.sources.misc submissions to comp-sources-misc@<backbone>.
bobmon@iuvax.cs.indiana.edu (RAMontante) (12/19/88)
rob@conexch.UUCP (Robert Collins) writes:
-In the latest (or one of the latest) issues of Microprocessor Report,
-says the '486 will have downloadable micro code, [...]
-of disbelief that much can be done other than speedups, I think
-downloadable microcode is lightyears more advanced than the '386.
^^^^^^^^^^
You mean it's physically remote, or aimed at starry-eyed people? :-)
IBM made big bucks with downloadable microcode in their mainframes;
they kept the S/360 architecture alive for years after they got better
hardware, by emulating a 360 whenever a customer wanted to run an old
program. Maybe not so fast, except for the fact the the new iron would
run so much faster than an original 360 anyway.
If the '486 can be re-microprogrammed, perhaps the 8080 will ride again!
(Or a 4004? 32-to-64 bit bus, 4-bit words, riiiiggghhhhttttttt.)
Or more radically, Intel can make a generic engine that it can program
as an 80x86 (for the obsolescence freaks), a 680x0 (for the
addressing-mode freaks), another S/360 (for the IBM freaks) . . .bcw@rti.UUCP (Bruce Wright) (12/19/88)
In article <16716@conexch.UUCP>, rob@conexch.UUCP (Robert Collins) writes: > In article <715@ethz.UUCP> zu@bernina.UUCP (Urs Zurbuchen) writes: > -The 80486 is rumored to have a virtual 80286 mode as the 80386 has a > -virtual 8086 mode. That's all we waited for, isn't it. So we can run > -multiple OS/2's on one computer :-) (If you run two OS/2's does this > -make it a complete Operating System ?) > - > -By the way, this virtual 80286 mode caused Intel a lot of problems. It > -seems to be the main reason why the chip is that late. > - > In the latest (or one of the latest) issues of Microprocessor Report, > says the '486 will have downloadable micro code, and a 6 instruction > prefetch queue. As for the bigger prefetch queue, that means that > relative jumps can be done in 0 clock cycles. But as to your assertion > of disbelief that much can be done other than speedups, I think > downloadable microcode is lightyears more advanced than the '386. Umm, well, I am by no means entranced with the '386 (for various reasons ...). My original posting was more along the lines that the '386 has become too much of a muchness, and that in order to do anything else with it it seems that there is little choice but to go with something like virtual 80286 and virtual 80386 modes. This is hardly an improvement!!! The architecture is too complex by half already, there is very little percentage in piling kludge upon kludge. As for downloadable microcode, well, I have used a number of machines that had downloadable microcode; and although we always thought we would try to take advantage of it we never found it to be cost-effective. I know of other installations which had the same reactions - it's something which sounds really neat, and it may even be useful so that the Field Service Engineers can update the microcode on the machine to correct bugs, but _VERY_ few ever really used it. Seems likely to me that its only real use on a 486 will be just that - correcting bugs (assuming that the bugs are fixable in microcode and aren't embedded in the microengine .....). It might be _SOLD_ as being something that had broader utility but in my experience this would be mostly marketing hype rather than solid value. I also don't quite understand why it is considered so horrible that it might be a good idea to call a halt to the continual reorganization of the 80x86 machine architecture and just concentrate on speedups. As it is now there is very little software which really takes advantage of the 80386 native mode ... after all, in the real world what matters is how much work you can get done for how many $. If you are going to increase the complexity of the architecture (and hence the difficulty of using the architecture) then that complexity will have to produce significant returns. My concern is that the 80386 with all of its different operating modes is already complex enough, and provides a reasonable functionality. Why complicate things further for little additional gain? If you are really running into architectural limits I would submit that the time has arrived to junk the architecture and look at going with a cleaner design. Bruce C. Wright
bcw@rti.UUCP (Bruce Wright) (12/19/88)
In article <15892@iuvax.cs.indiana.edu>, bobmon@iuvax.cs.indiana.edu (RAMontante) writes: > IBM made big bucks with downloadable microcode in their mainframes; > they kept the S/360 architecture alive for years after they got better > hardware, by emulating a 360 whenever a customer wanted to run an old > program. Maybe not so fast, except for the fact the the new iron would > run so much faster than an original 360 anyway. IBM mainframes are still running an architecture extremely similar to the S/360. A few additional instructions, and the entire 32 bits of a base register can be used as a memory address (instead of only 24 as on the S/360), but close enough so that most well-written assembler programs (or even binaries) would run in native mode on the latest machines. You are almost certainly thinking about 1401 emulation mode. The early S/360 and S/370 machines could emulate an old IBM 1401 machine; I think this emulation mode has been removed from the latest machines (but I haven't had any reason to keep track so I don't know this for certain). > If the '486 can be re-microprogrammed, perhaps the 8080 will ride again! > (Or a 4004? 32-to-64 bit bus, 4-bit words, riiiiggghhhhttttttt.) > Or more radically, Intel can make a generic engine that it can program > as an 80x86 (for the obsolescence freaks), a 680x0 (for the > addressing-mode freaks), another S/360 (for the IBM freaks) . . . This has of course always been possible - you just have to remask the ROM for the microcode. IBM has a chipset for the S/360 based I think on the 68k. One point (which you may be trying to make) is that it is not clear that changing the personality of the processor has much utility unless you have old programs to run. Most of the users running 1401 emulation mode were doing so because they hadn't rewritten all their code to run in S/360 native mode (sometimes they no longer HAD the source!!) - in fact there were several companies that made a very nice living converting 1401 binaries to S/360 COBOL code. Anyway, after experiences like that I don't think that there are very many companies that take such a cavalier attitude towards their critical program sources. If it is really interesting to be able to run, say, S/360 code on your PC, why didn't the XT/370 and similar products go anywhere? (this machine could run both PC and S/360 applications on the same machine). Would making the chip dynamically reconfigurable really make that much difference? I can see that there would be a few selected applications where it would be nice (I can even think of a couple of times it might have some marginal utility in some of the off-the-wall type projects I sometimes get involved in), but for the VAST run of PC-type and minicomputer applications I just don't see where the percentage is. Maybe I'm just getting old. Bruce C. Wright
bcw@rti.UUCP (Bruce Wright) (12/19/88)
In article <16716@conexch.UUCP>, rob@conexch.UUCP (Robert Collins) writes: > [...] I think > downloadable microcode is lightyears more advanced than the '386. The 80*86 family reminds me of something I once heard said about an entirely different type of hardware (that floated rather than computed): "Beauty is only skin deep but ugly goes clean to the bone" Bruce C. Wright
prc@maxim.ERBE.SE (Robert Claeson) (12/20/88)
In article <13258@ncoast.UUCP>, allbery@ncoast.UUCP (Brandon S. Allbery) writes: > From what I have heard (I don't know how reliable it is), the 80486 will > come out in two versions: a native one and an 80486/32632 (!) hybrid... > after which the iAPX86 line will be discontinued, folded into the iAPX32 > line. This will be confusing, since National Semiconductor uses the 32x32 numbering scheme now. I think their latest CPU is the 32532.. -- Robert Claeson, ERBE DATA AB, P.O. Box 77, S-175 22 Jarfalla, Sweden "No problems." -- Alf Tel: +46 758-202 50 EUnet: rclaeson@ERBE.SE uucp: uunet!erbe.se!rclaeson Fax: +46 758-197 20 Internet: rclaeson@ERBE.SE BITNET: rclaeson@ERBE.SE
jhunt@omews3.intel.com (Jim Hunt) (12/22/88)
In article <2618@rti.UUCP> bcw@rti.UUCP (Bruce Wright) writes: >There is, of course an 80186 (and an 80188) - this was a chip used briefly >before the 80286 came out. It was never very popular, but it was used by >a few clones (like the Radio Shack Model 2000 I believe). It was really >just an 8086/8088 which had some of the microcode optimizations used by >the 80286 - which means it runs about the speed of a '286 at a similar >MHz rating, but without protected memory. > Actually, the 80186/80188's main features were on board peripherals, such as DMA, timers, interrupt controller, chip select logic, etc. It didn't sell well in the PC market because it wasn't as fast as a 80286 and the on board peripherals were not PC compatible. It does have a substantial market niche in the 16 bit embedded control arena, however. A CMOS version of the component, with some feature upgrades, was recently released. Jim Standard disclaimer: Intel is not responsible for anything I say here.