doon@sdcrdcf.UUCP (05/11/86)
Hi, a few months ago it was announced that the 32332 was here. My question is "what's happened to the 32332?" I haven't heard or seen a word about it in months. Does anybody know what's going on?
kludge@gitpyr.UUCP (Scott Dorsey) (05/12/86)
In article <2793@sdcrdcf.UUCP> doon@sdcrdcf.UUCP (Harry W. Reed) writes: > >Hi, a few months ago it was announced that the 32332 was here. My question >is "what's happened to the 32332?" I haven't heard or seen a word about it in >months. Does anybody know what's going on? I have seen one. It exists. It is very, very fast. -- ------- Disclaimer: Everything I say is probably a trademark of someone. But don't worry, I probably don't know what I'm talking about. Scott Dorsey " If value corrupts kaptain_kludge then absolute value corrupts absolutely" ICS Programming Lab (Where old terminals go to die), Rich 110, Georgia Institute of Technology, Box 36681, Atlanta, Georgia 30332 ...!{akgua,allegra,amd,hplabs,ihnp4,seismo,ut-ngp}!gatech!gitpyr!kludge
mdr@reed.UUCP (05/14/86)
>>> "what's happened to the 32332?" <<<
I hate to be sarcastic, but unless National has really cleaned up their
act since they came out with this family of processors (what a
nightmare NS was in 82/83!), the stage which comes after the press
release is to sit down and well..., kind-of..., design the part.
Is there any indication that things are getting better?
Mike
Hmmm... Maybe I shouldn't bother people with this, but I wouldn't advise
anyone to plan a product on the new processor if things are the same.
seifert@hammer.UUCP (Snoopy) (05/15/86)
In article <1768@gitpyr.UUCP> kludge@gitpyr.UUCP (Scott Dorsey) writes: >In article <2793@sdcrdcf.UUCP> doon@sdcrdcf.UUCP (Harry W. Reed) writes: >> >>Hi, a few months ago it was announced that the 32332 was here. My question >>is "what's happened to the 32332?" I haven't heard or seen a word about it in >>months. Does anybody know what's going on? > >I have seen one. It exists. It is very, very fast. I know someone who did benchmarks comparing the 32332 to the 68020, with all else being identical (RAM, etc). A 15MHz 32332 is faster than a 16MHz 68020. Snoopy tektronix!tekecs!doghouse.TEK!snoopy [My other workstation only has 2 32016s. Drat! a workstation gap! Oh well, I bet I have more color planes than he does! :-) ]
joemu@nsc-pdc.UUCP (Joe Mueller) (05/16/86)
> > >>> "what's happened to the 32332?" <<< > > I hate to be sarcastic, but unless National has really cleaned up their > act since they came out with this family of processors (what a > nightmare NS was in 82/83!), the stage which comes after the press > release is to sit down and well..., kind-of..., design the part. > > Is there any indication that things are getting better? > > Mike > > Hmmm... Maybe I shouldn't bother people with this, but I wouldn't advise > anyone to plan a product on the new processor if things are the same. National demonstrated working 32332's during the Uniforum Confrerence February of 1986. I've personally seen equipment running unix on this chip. What else can I say? Joe Mueller ...!nsc!nsc-pdc!joemu
kludge@gitpyr.UUCP (05/19/86)
In article <2020@hammer.UUCP> tekecs!doghouse.TEK!snoopy (Snoopy) writes: >I know someone who did benchmarks comparing the 32332 to the 68020, >with all else being identical (RAM, etc). A 15MHz 32332 is faster >than a 16MHz 68020. I would like to see these benchmarks. I have been trying to get some more recent ones, after having run a few on a demo machine at a trade show. I am writing a paper on 32-bit microprocessor design, and the 332 is a good example of something that I would give my eyeteeth for. -- ------- Disclaimer: Everything I say is probably a trademark of someone. But don't worry, I probably don't know what I'm talking about. Scott Dorsey " If value corrupts kaptain_kludge then absolute value corrupts absolutely" ICS Programming Lab (Where old terminals go to die), Rich 110, Georgia Institute of Technology, Box 36681, Atlanta, Georgia 30332 ...!{akgua,allegra,amd,hplabs,ihnp4,seismo,ut-ngp}!gatech!gitpyr!kludge
larry@geowhiz.UUCP (Larry McVoy) (05/22/86)
In article <1796@gitpyr.UUCP> kludge@gitpyr.UUCP (Scott Dorsey) writes: >In article <2020@hammer.UUCP> tekecs!doghouse.TEK!snoopy (Snoopy) writes: >>I know someone who did benchmarks comparing the 32332 to the 68020, >>with all else being identical (RAM, etc). A 15MHz 32332 is faster >>than a 16MHz 68020. > > I would like to see these benchmarks. I have been trying to get I have a few comments & questions. 1) The story I have heard (albeit from sources that I don't view as gospel) is that the 32016 (in the symmetrics box) is s*l*o*w, about 1/4 a 68010. Is that true? 2) Another story I hear a lot is that people *claim* that the 32xxx chips are fast, but independant tests show that the claims are consistantly false. Can anyone comment on this? I'd prefer to hear from people who: A) are not associated with National Semiconductor B) are using a unix workstation based on a 32xxx chip set. 3) I've heard that the 32xxx series of CPU's are binary compatible. If this is true, are they pin compatible? The real question is: can I buy a symmetrics box, pull the 32016 and replace it with a 32032 or 32332? -- Larry McVoy ----------- Arpa: mcvoy@rsch.wisc.edu Uucp: {seismo, ihnp4}!uwvax!geowhiz!geophiz!larry "Just remember, wherever you go -- there you are." -Buckaroo Banzai
kjm@motsj1.UUCP (Kevin Meyer) (05/22/86)
> > I know someone who did benchmarks comparing the 32332 to the 68020, > with all else being identical (RAM, etc). A 15MHz 32332 is faster > than a 16MHz 68020. > Shouldn't this be posted to net.rumor?
doon@sdcrdcf.UUCP (05/24/86)
In article <216@motsj1.UUCP> kjm@motsj1.UUCP (Kevin Meyer) writes: >> >> I know someone who did benchmarks comparing the 32332 to the 68020, >> with all else being identical (RAM, etc). A 15MHz 32332 is faster >> than a 16MHz 68020. >> >Shouldn't this be posted to net.rumor? No, net.fact!
henry@utzoo.UUCP (Henry Spencer) (05/25/86)
> 1) The story I have heard (albeit from sources that I don't view as gospel) > is that the 32016 (in the symmetrics box) is s*l*o*w, about 1/4 a 68010. > Is that true? It ain't fast. 0.25*68010 sounds a bit low, but as I recall the 32032 isn't lots faster than the 68000, so it makes sense that the 016 is slower. It also depends on how fast one runs the clock (Symmetric has been around for quite a while -- maybe they are running with a slow clock because of an old design for old buggy chips) and on how fast the memory is. And on how much branching the code does; the 32016/32 *hates* to branch. > 3) I've heard that the 32xxx series of CPU's are binary compatible... Should be, from the specs I've seen. I don't recall anything new in the 332 in the way of instructions, and the 016 and 032 are two peas from the same pod. > If this is true, are they pin compatible? No. Not even the same package: the 016 is in a 48-pin DIP, the 32032 is a chip carrier, and the 32332 is either a chip carrier or a pin-grid array (I forget). The 16-vs-32 difference of the 016 and the 032 is not as bad as you would think, however; since the MMU needs a 16-bit bus either way, a careful design can accommodate either a 32016 or a 32032 with a change of socket and one PAL. The 32332 might be 32032-compatible, again with a different socket, if the design doesn't exploit some of the 332's goodies. Not sure about that last, I didn't study the 332 very carefully. In any case, there's no telling whether Symmetric has actually built their box to permit such an upgrade. Again, it's been around a long time; I suspect not. -- Join STRAW: the Society To Henry Spencer @ U of Toronto Zoology Revile Ada Wholeheartedly {allegra,ihnp4,decvax,pyramid}!utzoo!henry
jsgray@watdragon.UUCP (Jan Gray) (05/25/86)
In article <2815@sdcrdcf.UUCP> doon@sdcrdcf.UUCP (Harry W. Reed) writes: >In article <216@motsj1.UUCP> kjm@motsj1.UUCP (Kevin Meyer) writes: >>> >>> I know someone who did benchmarks comparing the 32332 to the 68020, >>> with all else being identical (RAM, etc). A 15MHz 32332 is faster >>> than a 16MHz 68020. >>> >>Shouldn't this be posted to net.rumor? > >No, net.fact! Could you tell us why the 332 is so fast, what the benchmarks test, schedule for general availability of the 15 MHz version, etc. Motorola announced 20 MHz fully debugged 68020s a while ago. Are they selling 24 MHz versions yet? How does the {best generally available or best internal sample} 68020 compare with the 32332? Cheering for another commercially viable 32 bit family, trying to stir up the 68K vs 32K debate yet again, and fickle as hell (I used to *love* the NS family, but the bugs and the 68020 changed my mind), Jan Gray jsgray@watdragon University of Waterloo 519-885-1211 x3870
davet@oakhill.UUCP (05/27/86)
In article <1018@watdragon.UUCP> jsgray@watdragon.UUCP (Jan Gray) writes: >Motorola announced 20 MHz fully debugged 68020s a while ago. Are they >selling 24 MHz versions yet? How does the {best generally available or >best internal sample} 68020 compare with the 32332? We hope to be in standard production of 25 Mhz units by the end of this year. -- Dave Trissel Motorola Semiconductor, Austin, Texas {ihnp4,seismo}!ut-sally!im4u!oakhill!davet
seifert@hammer.UUCP (05/27/86)
In article <438@geowhiz.UUCP> larry@geowhiz.UUCP (Larry McVoy) writes: >In article <1796@gitpyr.UUCP> kludge@gitpyr.UUCP (Scott Dorsey) writes: >>In article <2020@hammer.UUCP> tekecs!doghouse.TEK!snoopy (Snoopy) writes: >>>I know someone who did benchmarks comparing the 32332 to the 68020, >>>with all else being identical (RAM, etc). A 15MHz 32332 is faster >>>than a 16MHz 68020. >> >> I would like to see these benchmarks. When the gentleman who did them gets back from his honeymoon I'll ask him for more details. (assuming that the results are considered public domain, which they may not be) >I have a few comments & questions. > >1) The story I have heard (albeit from sources that I don't view as gospel) > is that the 32016 (in the symmetrics box) is s*l*o*w, about 1/4 a 68010. > Is that true? I don't know about the symmetrics box, but I've heard that our customers have found the Tek 6130 (32016 @ 10MHz) to be faster than the Sun-2. >2) Another story I hear a lot is that people *claim* that the 32xxx chips are > fast, but independant tests show that the claims are consistantly false. > Can anyone comment on this? I'd prefer to hear from people who: > A) are not associated with National Semiconductor > B) are using a unix workstation based on a 32xxx chip set. I work for Tektronix, not NSC. My current task is doing bugfixes and enhancements on UTek (UNIX) utilities for the 6130. I do as much of my work as possible on doghouse (6130) because it's so much faster than hammer (Vax780). (Unless there are only 1-2 people on hammer, which is pretty rare) >3) I've heard that the 32xxx series of CPU's are binary compatible. If this > is true, are they pin compatible? The real question is: can I buy a > symmetrics box, pull the 32016 and replace it with a 32032 or 32332? No, the 32016 is a 48 pin dip, the 32032 is a 68 pin leadless chip carrier. The Tek 6200 series had sockets for both. Conversion was simple, just pull out the 32016 and put in a 32032, and *presto* it runs faster. Unfortunately, the 6200 series was cancelled for political reasons. Snoopy tektronix!tekecs!doghouse.TEK!snoopy
jans@tekecs.UUCP (Jan Steinman) (05/27/86)
In article <6732@utzoo.UUCP> henry@utzoo.UUCP (Henry Spencer) writes: >... The 16-vs-32 difference of the 016 and the 032 is not as bad >as you would think, however; since the MMU needs a 16-bit bus either way, >a careful design can accommodate either a 32016 or a 32032 with a change >of socket and one PAL... This reply is coming to you from a box that has both sockets on the CPU board -- to change from 32016 to 32032, simply pull out one chip, insert the other. (Too bad we didn't get a chance to sell it.) -- :::::: Artificial Intelligence Machines --- Smalltalk Project :::::: :::::: Jan Steinman Box 1000, MS 60-405 (w)503/685-2956 :::::: :::::: tektronix!tekecs!jans Wilsonville, OR 97070 (h)503/657-7703 ::::::
david@ukma.UUCP (David Herron, NPR Lover) (05/28/86)
In article <216@motsj1.UUCP> kjm@motsj1.UUCP (Kevin Meyer) writes: >> >> I know someone who did benchmarks comparing the 32332 to the 68020, >> with all else being identical (RAM, etc). A 15MHz 32332 is faster >> than a 16MHz 68020. >> >Shouldn't this be posted to net.rumor? Or maybe net.jokes? -- David Herron, cbosgd!ukma!david, david@UKMA.BITNET, david@uky.csnet
patch@nsc-pdc.UUCP (Pat Chewning) (05/28/86)
> 3) I've heard that the 32xxx series of CPU's are binary compatible. If this > is true, are they pin compatible? The real question is: can I buy a > symmetrics box, pull the 32016 and replace it with a 32032 or 32332? > > -- > Larry McVoy > ----------- After laying out boards using 32016 32032 and 32332, I can claim that they are definently NOT pin compatible: 32016 40 pin DIP 32032 68 pin leadless ceramic chip carrier 32332 84 (plus one locating pin) = 85 pin PGA (pin grid array) However, the same code for the 32016 does indeed run on 32032 and 32332. Pat Chewning NSC Portland Development Center 15201 NW Greenbriar Pkwy Beaverton, OR 97006 (503) 629-9090
patch@nsc-pdc.UUCP (Pat Chewning) (05/28/86)
Oops, that should have been: 32016 48 pin DIP (not 40 pin DIP)
bjorn@alberta.UUCP (Bjorn R. Bjornsson) (05/29/86)
In <438@geowhiz.UUCP> larry@geowhiz.UUCP (Larry McVoy) writes: > I have a few comments & questions. > > 1) The story I have heard (albeit from sources that I don't view as gospel) > is that the 32016 (in the symmetrics box) is s*l*o*w, about 1/4 a 68010. > Is that true? You would be well advised to put even less faith in your "sources", for even though I cannot answer for the Symmetrics box, the Dhrystone results speak (with the usual truck load of salt) for themselves: |*----------------DHRYSTONE VERSION 1.0 RESULTS BEGIN-------------------------- |* |* MACHINE MICROPROCESSOR OPERATING COMPILER DHRYSTONES/SEC. |* TYPE SYSTEM NO REG REGS |* -------------------------- ------------ ----------- --------------- |* Colex DM-6 68010-8Mhz Unisoft SYSV cc 378 410 |* Apollo DN550 68010-?Mhz AegisSR9/IX cc 3.12 666 666 |* Cadmus 9000 68010-10Mhz UNIX cc 714 735 |* Cadmus 9790 68010-10Mhz 1MB SVR0,Cadmus3.7 cc 720 747 |* Burroughs XE550 68010-10Mhz Centix 2.10 cc 769 769 CT1 |* ATT 3B2/300 WE32000-?Mhz UNIX 5.0.2 cc 735 806 |* Apollo DN320 68010-?Mhz AegisSR9/IX cc 3.12 806 806 |* IRIS-2400 68010-10Mhz UNIX System V cc 772 829 |* IRIS-1400 68010-10Mhz UNIX System V cc 909 1000 |* NSC ICM-3216 NSC 32016-10Mhz UNIX SVR2 cc 1041 1084 | ------------- |* ATT PC7300 68010-10Mhz UNIX 5.0.2 cc 1041 1111 |* Sun2/120 68010-10Mhz Sun 4.2BSD cc 1136 1219 |* MASSCOMP 500 68010-10MHz RTU V3.0 cc (V3.2) 1156 1238 |* Cyb DataMate 68010-12.5Mhz Uniplus 5.0 Unisoft cc 1162 1250 |* Sun2/120 68010-10Mhz Standalone cc 1219 1315 |* Sequent Balance 8000 NS32032-10MHz Dynix 2.0 cc 1250 1315 N12 | ------------- |* IBM PC/DSI-32 32032-10Mhz MSDOS 3.1 GreenHills 2.14 1282 1315 C3 | ------------- |* Cyb DataMate 68010-12.5Mhz Uniplus 5.0 Unisoft cc 1470 1562 S > 2) Another story I hear a lot is that people *claim* that the 32xxx chips are > fast, but independant tests show that the claims are consistantly false. > Can anyone comment on this? I'd prefer to hear from people who: > A) are not associated with National Semiconductor > B) are using a unix workstation based on a 32xxx chip set. See Dhrystones above. People with access to 32000 based workstations from Tektronix, Intergraph & Whitechapel, etc., would be ideal candidates for expanding on this questions. For floating point fans, it's probably a save bet that the 32k based systems outperform most existing (ie. excluding 68020/68881) 68k systems. Some concrete figures on this would be of interest. > 3) I've heard that the 32xxx series of CPU's are binary compatible. If this > is true, are they pin compatible? The real question is: can I buy a > symmetrics box, pull the 32016 and replace it with a 32032 or 32332? I'm not sure what you mean by "pin compatible". If you mean signal and electrical compatibility, the answer is basically yes. There would however, be absolutely no point in replacing the 32016 with a 32032, as they are identical save for the CPU bus interface. You would need a modest amount of logic to make a 16 bit data bus look like a 32 bit bus (with possible degradation in performance). The 32332 is a different story. Since it has dynamic bus sizing, it could indeed easily replace a 32016, with an increase in performance due to the deeper prefetch queue and separate ALU/Shifter in the address path. A small adapter board containing the 32332, could be plugged into the 32016 socket, although you might need to bring an auxiliary power source onto the board, to satisfy the 32332s greater power requirements. P.S. You can find some benchmark results for 32032 IBM-PC add-on board in a recent issue of UNIX/WORLD. Bjorn R. Bjornsson Department of Computing Science University of Alberta
hsu@eneevax.UUCP (Dave Hsu) (05/30/86)
In article <921@alberta.UUCP> bjorn@alberta.UUCP (Bjorn R. Bjornsson) writes: >In <438@geowhiz.UUCP> larry@geowhiz.UUCP (Larry McVoy) writes: >> I have a few comments & questions. >> >> 1) The story I have heard (albeit from sources that I don't view as gospel) >> is that the 32016 (in the symmetrics box) is s*l*o*w, about 1/4 a 68010. >> Is that true? > >You would be well advised to put even less faith in your "sources", for >even though I cannot answer for the Symmetrics box, the Dhrystone results >speak (with the usual truck load of salt) for themselves: > >|*----------------DHRYSTONE VERSION 1.0 RESULTS BEGIN------------------------- >|* NSC ICM-3216 NSC 32016-10Mhz UNIX SVR2 cc 1041 1084 >| ------------- Actually, we had a Symmetrics rep over back in December or January and we did get a chance to dhrystone their unit. Although the figure escapes me now, I believe that it was in the 7-800 range. One major stumbling block we did notice was that the compile times were enormous, certainly several times as long as a Sun-2, and about as slow as my antiquated Callan. The line from the rep was that at the time, Symmetrics was still shipping an old compiler based on some silly theoreticians papers, and that the code it was generating was being threaded this way and that, generating subroutine calls here and there with all the nasty activation record stuff, etc etc etc. I was rather interested, though, by his claim that Symmetrics was on the verge of releasing their 32032 version, soon to be followed by higher- performance NS parts. Also, he mentioned that a new compiler was in the works. Perhaps its time to hit them for fresh literature again. Although this is completely incidental to the architecture, I probably should add that somebody at Symmetrics was eating their Wheaties when they arranged for the 4.2 port...it looked quite complete and happy, and was the first machine that I saw anyway that included a variant on Chris Torek's ^T hack. -dave -- David Hsu (301)454-1433 || -8798 "It was Dave, not me...honest!" -eneevax Communication & Signal Processing Lab / Engineering Computer Facility The University of Maryland -~- College Park, MD 20742 ARPA:hsu@eneevax.umd.edu UUCP:[seismo,allegra,rlgvax]!umcp-cs!eneevax!hsu "Filmed on location in space"
seifert@hammer.UUCP (Snoopy) (05/31/86)
In article <699@oakhill.UUCP> davet@oakhill.UUCP (Dave Trissel) writes: >We hope to be in standard production of 25 Mhz units by the end of this year. > > -- Dave Trissel Motorola Semiconductor, Austin, Texas > {ihnp4,seismo}!ut-sally!im4u!oakhill!davet When will MMUs for these be available in quantity? (really! I'm sure the 440x group would like to know!) Snoopy tektronix!tekecs!doghouse.TEK!snoopy