[Posted to the INFO-VAX mailing list] ============================================================================= From: paul@uk.co.laser-scan (Paul Hardy) Date: 14 Oct 93 18:03:02 +0100 Following recent announcements from DEC, I thought it was time I posted a new version of my VMS machines list. As usual, any updates are welcomed. VMS CPU Model Summary (14th October 1993) ----------------------------------------- The following table summarises the whole publicly known VAX and AXP model range by CPU type, divided into processor families, and then by subtype, giving approximate chronological order. The information given has the top byte of the SID in hex (containing the CPU type), subtype (XCPU or SYSTYPE), processor ID, approximate speed (relative to a VAX-11/780, in VUPS for most machines, and SPECmark89 (S) for later workstations and Alphas), main I/O bus type (U=UNIBUS, M=MASSBUS, C=CI, Q=QBUS, B=BI, D=DSSI, X=XMI, T=Turbochannel, F=Futurebus+, S=SCSI, E=EISA), model names, and nickname. For AXPs, the ID is replaced by the clock speed in MHz. Information is from publicly available sources such as DEC brochures and press releases, together with the description of SYS$GETSYI in the VMS documentation, and from $PRDEF, $VAXDEF, and $ALPHADEF in the system macro library. This is supplemented with information from USENET group comp.os.vms. Current models are marked by a leading `*'. This list is not an official publication of Laser-Scan - ask DEC if you want confirmed figures! In the fast changing world of computer hardware, its probably out of date when written. However, please let me know of any inaccuracies or omissions. --- Paul Hardy (PGH), Chief Programmer, Laser-Scan Ltd, Science Park, Milton Rd, CAMBRIDGE, CB4 4FY, England. Tel: (+44) 223 420414; Fax: 420044, Email: paul@lsl.co.uk (via BRITAIN.EU.NET). VAX CPUs -----+---+-----+-------+--------+--------------------------------+-------------- SID | X | Id | Speed | Bus | Model Name | Nickname -----+---+-----+-------+--------+--------------------------------+-------------- ---- 700 series (1977) +--------+--------------------------------+-------------- 01 | - | 780 | 1.0 | U,M,C | VAX-11/780 | Star 01 | - | 780 | 1.8 | U,M,C | VAX-11/782 | Atlas 01 | - | 780 | 3.5 | U,M,C | VAX-11/784 | VAXimus 01 | - | 780 | 1.5 | U,M,C | VAX-11/785 | Superstar 02 | - | 750 | 0.6 | U,M,C | VAX-11/750 | Comet 03 | - | 730 | 0.3 | U | VAX-11/730, 725 | Nebula, LCN 04 | - | 790 | 4.0 | U,M,C | VAX 8600, | Venus 04 | - | 790 | 7.0 | U,M,C | VAX 8650 | Morningstar ---- 8000 series (1986)+--------+--------------------------------+-------------- 05 | - | 8SS | 0.9-2 | B,C | VAX 8200, 8300, 8250, 8350 | Scorpio 05 | - | 8SS | 0.9-2 | B,C | VAXstation 8000 | Lynx 06 | - | 8NN | 3 | B,C | VAX 8500 | Flounder 06 | - | 8NN | 4/6 | B,C | VAX 8530, 8550 | Skipjack 06 | - | 8NN | 6/12 | B,C | VAX 8700, 8800 | Nautilus ---- MicroVAX I (1984) - Decimal SID = 117440512 ----------------+-------------- 07 | - | UV1 | 0.3 | Q | MicroVAX I, VAXstation I | Seahorse ---- MicroVAX II series (1985) - Decimal SID = 134217728 --------+-------------- 08 | 1 | UV2 | 0.9 | Q | MicroVAX II,VAXstation II | Mayflower 08 | 1 | UV2 | 0.9 | Q | VAXstation II/GPX | Caylith 08 | 4 | 410 | 0.9 | none | MicroVAX 2000 | TeamMate 08 | 4 | 410 | 0.9 | none | VAXstation 2000 | VAXstar ---- CVAX chip series (1987) - Decimal SID = 167772160 ----------+-------------- 0A | 1 | 650 | 2.8 | Q | MicroVAX 3500, 3600 | Mayfair 0A | 1 | 65D | 2.8 | Q | VAXstation 3200, 3500 | Mayfair/GPX 0A | 1 | 640 | 2.4 | Q,D | MicroVAX 3300, 3400 | Mayfair II 0A | 1 | 655 | 3.8 | Q | MicroVAX 3800, 3900 | Mayfair III 0A | 2 | 9CC | 2.8 | X,B,C | VAX 6000 model 210 | Calypso/XCP 0A | 2 | 9CC | 3.8 | X,B,C | VAX 6000 model 310 | Calypso/XCP 0A | 3 | 60 | 3-10 | Q | VAXstation 3520, 3540 | Firefox 0A | 4 | 420 | 2.8 | S | VAXstation 3100 models 30, 40 | PVAX 0A | 4 | 420 | 2.4 | S | MicroVAX 3100 models 10, 20 | Teammate II 0A | 4 | 420 | 3.5 | S | MicroVAX 3100 models 10e, 20e | Teammate II 0A | 4 | 420 | 3.8 | S | VAXstation 3100 models 38, 48 | PVAX rev#7 * 0A | 7 | 510 | 2.4 | D | VAXft model 110 | Cirrus 0A | 7 | 520 | 3.8 | D | VAXft model 310 | Cirrus ---- Rigel chip series (1990) - Decimal SID = 184549376 ---------+-------------- 0B | 1 | 670 | 8.0 | Q,D | VAX 4000 model 300 | Pele 0B | 2 | 9RR | 7-36 | X,B,C | VAX 6000 model 410-460 | Calypso/XRP 0B | 4 | 43 | 7.6 | S | VAXstation 3100 model 76 | RigelMAX ---- Aquarius series (1990) - Decimal SID = 234881024 -----------+-------------- 0E | - | 9AR |40-157 | X,B,C | VAX 9000 models 210, 410-440 | Aridus 0E | - | 9AQ |40-157 | X,B | VAX 9000 models 400-800 | Aquarius ---- Polarstar series (1988) - Decimal SID = 285212672 ----------+-------------- 11 | - | 8PS | 6-22 | B,C | VAX 8810 to 8840 | Polarstar ---- Mariah chip series (1991) - Decimal SID = 301989888 --------+------------ 12 | 1 | 690 | 16 | Q,D | VAX 4000 model 400 | Omega/M 12 | 2 | 1202|13-58 | XBCD | VAX 6000 model 510-560 | Calypso/XMP 12 | 4 | 46 | 12 | T,S | VAXstation 4000 model 60 | PMariah * 12 | 4 | 46 | 12 | S | MicroVAX 3100 model 80 | Waverley/M ---- NVAX chip series (1991) - Decimal SID = 318767104 ----------+-------------- * 13 | 1 | 69D | 24 | Q,D | VAX 4000 model 500, 500A | Omega/N * 13 | 1 |1303 | 24 | Q,D | VAX 4000 model 100, 100A | Cheetah-Q * 13 | 1 | 690 | 32 | Q,D | VAX 4000 model 600, 600A | Omega/N+ * 13 | 1 | 690 | 40 | Q,D | VAX 4000 model 700A | Legacy 13 | 2 | 1302|32-150 | XBDC | VAX 6000 models 610-660 | Neptune * 13 | 4 |1303 | 24 | S | MicroVAX 3100 model 90 | Cheetah * 13 | 4 | 49 |32.8 S | T,S | VAXstation 4000 model 90 | Cougar * 13 | 7 | ??? | 30 | D | VAXft model 810 | Jetstream ---- SOC chip series (1991) - Decimal SID = 335544320 -----------+-------------- 14 | 1 | 660 | 5.0 | Q,D | VAX 4000 model 200 | Spitfire 14 | 4 | 440 | 6.2 S | S | VAXstation 4000 VLC (model 30) | PVAX2/VLC * 14 | 4 | 440 | 5.0 | S | MicroVAX 3100 models 30, 40 | Waverley/S 14 | 7 | 550 | 6.0 | D | VAXft model 410, 610 | Cirrus II ---- NVAX+ chip series (1991) - Decimal SID = 385875968 ---------+-------------- * 17 | 3 | 1701|35-120 | X,C,D | VAX 7000 models 610-640 | Laser/Neon * 17 | 3 | 1701|35-120 | X,C,D | VAX 10000 models 610-640 | Blazer -----+---+-----+-------+--------+--------------------------------+-------------- Alpha AXP CPUs -----+---+-----+-------+--------+--------------------------------+-------------- SID | S |Clock| SPECs | Bus | Model Name | Nickname -----+---+-----+-------+--------+--------------------------------+-------------- ---- EV4 AXP chip series (1992) - Decimal SID = -2147483648 -----+-------------- * 80 | 2 | 180 | 135 S | F,D,S | DEC 4000 model 610 | Cobra * 80 | 2 | 190 | 150?S | F,D,S | DEC 4000 model 710 | Fang * 80 | 3 | 180 | 150 S | X,C,D | DEC 7000 model 610 | Laser/Ruby * 80 | 3 | 180 | 160 S | X,C,D | DEC 10000 model 610 | Blazer/Ruby * 80 | 4 | 150 | 126 S | T,S | DEC 3000 model 500W or S | Flamingo * 80 | 4 | 200 | 180?S | T,S | DEC 3000 model 800W or S | Flamingo II * 80 | 4 | 133 | 111 S | T,S | DEC 3000 model 400W or S | Sandpiper * 80 | 4 | 175 | 157 S | T,S | DEC 3000 model 600W or S | Sandpiper+ * 80 | 4 | 200 | 161 S | T,S | DEC 3000 model 500X | Hot Pink * 80 | 4 | 150 | 85 S | T,S | DEC 3000 model 300 | Pelican * 80 | 4 | 100 | 55 S | S | DEC 3000 model 300L | Pelica * 80 | ? | 150 | 100 S | S,E | DEC 2000 model 300, pc AXP/150 | Jensen -----+---+-----+-------+--------+--------------------------------+-------------- ================================================================================ From: ars@com.std.world (Alan R Sieving) Date: Fri, 15 Oct 1993 22:54:59 GMT >pechter@i4got.lakewood.com (Bill Pechter) wrote: >|>> 01 | - | 780 | 3.5 | U,M,C | VAX-11/784 | VAXimus then lionel@quark.enet.dec.com (Steve Lionel) replied: >I've worked at Digital, with VAX systems, continuously since 1978. Though >I believe there was a "one-off" four-way system using the 11/782 technology >(memory shared through an MA780), I never heard it given a code name much >less a marketing designation and it was never sold as a product. It's >possible that such a configuration was built on request for a customer, but >I don't recall ever hearing of such. Also, the VAX architecture committee's >official list of VAX processor IDs (including some for systems never built) >does not mention a "11/784". (No, you can't have the list.) Well, I'm certainly not even close to knowing for certain, but I remember hearing that Purdue had a machine called an 11/784. My faint memory says that it was a custom 4-CPU machine, and that perhaps they at some point offered "DIY" (do it yourself) instructions on how to cobble one together. This was about 1984, probably just before the 8600 (nee 790) came out. -- --al. Alan Sieving, ars@quickware.com or ars@world.std.com Quickware Engineering & Design, 225 Riverview Ave Waltham, MA, 02154-3874 ================================================================================ From: tp@com.mccall (Terry Poot) Date: Fri, 15 Oct 1993 18:01:53 CDT In article <1993Oct15.025640.11352@i4got.lakewood.com>, pechter@i4got.lakewood.com (Bill Pechter) writes: >I never heard of the 11/784... anyone know anything about it... I saw one once, when I was on a job interview. Apparently it was a custom job delivered only to users who really needed it. I never saw it in the catalog. It was a 782, only bigger. 4 780's joined by MA780 multiport memory. Needless to say, it took up a whole room, since each of the 780's was in a 3 bay cabinet, and right in the center you had the MA780. Blew my mind. But there was an real DEC nameplate on it that said it was an 11/784 (i.e. not a hand-written one). The guy giving me the tour grinned and said not to spread around that the thing existed, they had one of the first ones (he may have said _the_ first), so I won't say who the company was, but it was in Dallas, and it wasn't TI. -- Terry Poot The McCall Pattern Company (uucp: ...!rutgers!depot!mccall!tp) 615 McCall Road (800)255-2762, in KS (913)776-4041 Manhattan, KS 66502, USA ================================================================================ From: eugene@gov.nasa.nas.wilbur (Eugene N. Miya) Date: Sat, 16 Oct 1993 00:31:03 GMT In article ars@world.std.com (Alan R Sieving) writes: >>pechter@i4got.lakewood.com (Bill Pechter) wrote: >>|>> 01 | - | 780 | 3.5 | U,M,C | VAX-11/784 | VAXimus >then lionel@quark.enet.dec.com (Steve Lionel) replied: >>I've worked at Digital, with VAX systems, continuously since 1978. Though >>I believe there was a "one-off" four-way system using the 11/782 technology >>(memory shared through an MA780), I never heard it given a code name much >>less a marketing designation and it was never sold as a product. It's >>possible that such a configuration was built on request for a customer, but >>I don't recall ever hearing of such. Also, the VAX architecture committee's >>official list of VAX processor IDs (including some for systems never built) >>does not mention a "11/784". (No, you can't have the list.) Five 784s were built. I believe I have seen four of the five. The code name VAXimus is wrong. The term VAXimus came from the joint Lawrence Livermore, ColoState, DEC dataflow project. The 784 delivered to LLNL was given the network host name Circus VAXimus. The single processor software development machine (still named lll-crg.llnl.gov) is the Gluteus VAXimus (Unix). We had one here starting as a 782 and upgrading to a 784. I saw CMU's 784 on a visit. I saw one at a classified site who will remain unnamed. And there was one in Europe at a DEC site. The person to ask about the 784 is John Sopka who is now with Transarc. Gordon would also know (and he is with SUN). >Well, I'm certainly not even close to knowing for certain, but I >remember hearing that Purdue had a machine called an 11/784. George Goble produced two processor VAXen after reading "It is possible to create a multiprocessor by replacing the SBI with a CPU." He did that after they dropped a 780 off a truck. But it was not a VMS machine. A paper exists by George from a Usenix conference. The only VAX I know missing from your table is the Andromeda (M31). The code name is okay because a DEC Press book is out about it (I would not mind having a copy). Gordon and John would also know about this. Basically a VAX version of the Cm*. --eugene miya, NASA Ames Research Center, eugene@orville.nas.nasa.gov Resident Cynic, Rock of Ages Home for Retired Hackers {uunet,mailrus,other gateways}!ames!eugene Second Favorite email message: 550 Host unknown (Authoritative answer from name server): Address family not supported by protocol family A Ref: Mathematics and Plausible Reasoning, vol. 1, G. Polya ================================================================================ From: pechter@com.lakewood.i4got (Bill Pechter) Date: Fri, 15 Oct 1993 02:56:40 GMT In article <1993Oct14.180302.3830@lsl.co.uk> paul@lsl.co.uk (Paul Hardy) writes: >Following recent announcements from DEC, I thought it was time I posted a >new version of my VMS machines list. As usual, any updates are welcomed. > I worked at DEC from 1981 to 1986 and I worked on 11/780's, 11/785, 11/730's and 86XX's and the MicroVax I and II. > 01 | - | 780 | 3.5 | U,M,C | VAX-11/784 | VAXimus I never heard of the 11/784... anyone know anything about it... > 01 | - | 780 | 1.0 | U,M,C | VAX-11/780 | Star > 01 | - | 780 | 1.8 | U,M,C | VAX-11/782 | Atlas This one was 2 11/780's with a backpanel (SBI) shared between the two. It was asymetrical multiprocessing - one did the crunch and one did the I/O. > 01 | - | 780 | 1.5 | U,M,C | VAX-11/785 | Superstar This was a redone 11/780 done it high speed TTL (or was it Schottky)... the 11/785 ran the CPU with a 3/2 ratio of CPU to SBI backplane transfer. Supposedly the DEC SBI and memory on the 11/780 MS780A/C memory was from an earlier unreleased PDP11 or 32 bit PDP11. Any one know about this. My friend who worked on the first shipping Vaxes saw some docs describing memory -- however the machine named wasn't called the Star. Bill -- ------------------------------------------------------------------------------- Bill Pechter | The postmaster always pings twice. Lakewood MicroSystems | 17 Meredith Drive, 908-389-3592 | Tinton Falls, NJ 07724 ================================================================================ From: lionel@com.dec.enet.quark (Steve Lionel) Date: 15 Oct 1993 22:05:31 GMT In article <1993Oct15.025640.11352@i4got.lakewood.com>, pechter@i4got.lakewood.com (Bill Pechter) writes: >> 01 | - | 780 | 1.8 | U,M,C | VAX-11/782 | Atlas >This one was 2 11/780's with a backpanel (SBI) shared between the two. It >was asymetrical multiprocessing - one did the crunch and one did the I/O. Not quite. The backplanes were independent - the two systems shared memory through an MA780 multiport shared memory box which allowed for a maximum of 4MB memory. You are correct that only one of the processors handled I/O interrupts (as well as a number of other system functions). The ASMP version of VAX/VMS was discontinued for VMS V5.0. |> |>> 01 | - | 780 | 3.5 | U,M,C | VAX-11/784 | VAXimus |>I never heard of the 11/784... anyone know anything about it... |> I've worked at Digital, with VAX systems, continuously since 1978. Though I believe there was a "one-off" four-way system using the 11/782 technology (memory shared through an MA780), I never heard it given a code name much less a marketing designation and it was never sold as a product. It's possible that such a configuration was built on request for a customer, but I don't recall ever hearing of such. Also, the VAX architecture committee's official list of VAX processor IDs (including some for systems never built) does not mention a "11/784". (No, you can't have the list.) Oh, the list is also missing the VAX-11/751, which was a rack-mounted (I think) cabinet variant of the 11/750. There was also a set of systems called something like VAX 8974, which was really a cluster of four "regular" VAX processors (8800, I think, but could be 8600. My memory is a bit fuzzy on this.) This was really just a marketing name for a prepackaged configuration and quickly faded away. Another missing processor is the rtVAX (KA620); this was a KA630 (MicroVAX II) board with modified CPU microcode such that the process address space went through only one level of page table translation instead of two. (This had been the original design of the MicroVAX I.) The intent was to come up with a board that could be sold separately for embedded systems applications (it would run VAXELN), but since it would not run VMS, it would not interfere with systems sales. The LPS40 Printserver was one of the primary users of the KA620. I have two of these sitting in my desk drawer nowadays - not really of much use! -- Steve Lionel lionel@quark.enet.dec.com SDT Languages Group Digital Equipment Corporation 110 Spit Brook Road, ZKO2-3/N30 Nashua, NH 03062 "Free advice is worth every cent" ================================================================================ Date: Sat, 16 Oct 93 09:01:04 EDT From: Jerry Leichter |>> 01 | - | 780 | 3.5 | U,M,C | VAX-11/784 | VAXimus |>I never heard of the 11/784... anyone know anything about it... |> I've worked at Digital, with VAX systems, continuously since 1978. Though I believe there was a "one-off" four-way system using the 11/782 technology (memory shared through an MA780), I never heard it given a code name much less a marketing designation and it was never sold as a product. It's possible that such a configuration was built on request for a customer, but I don't recall ever hearing of such. Also, the VAX architecture committee's official list of VAX processor IDs (including some for systems never built) does not mention a "11/784". (No, you can't have the list.) Steve, it just goes to show how large a company DEC is. At least one 11/784, and I think actually a couple, were built for a university, I think Purdue. The university did a multiprocessor Unix port for the machine. I don't know how successful it was. I believe that the 11/784 designation was actually used - someone probably thought it would be a nice touche to come up with an 11/784 label for the front of the cabinet - though since it was never a product as such and was never supported by any DEC-distributed software, it was never widely known. Oh, the list is also missing the VAX-11/751, which was a rack-mounted (I think) cabinet variant of the 11/750. Yup. There was, as I recall, a difference in the standard configuration as well since the disk drives normally used with a 750 at the time didn't fit in a standard rack. I have no idea where the 751 was sold and used; I didn't see any mention of it until many years later. There was also a set of systems called something like VAX 8974, which was really a cluster of four "regular" VAX processors (8800, I think, but could be 8600. My memory is a bit fuzzy on this.) This was really just a marketing name for a prepackaged configuration and quickly faded away 8700's and 8800's. There was a range of configurations with marketing numbers attached to them: You could get 2 8800's or 4 8700's, for example. The number of sales under these fancy package numbers was tiny. Another missing processor is the rtVAX (KA620); this was a KA630 (MicroVAX II) board with modified CPU microcode such that the process address space went through only one level of page table translation instead of two. (This had been the original design of the MicroVAX I.) The intent was to come up with a board that could be sold separately for embedded systems applications (it would run VAXELN), but since it would not run VMS, it would not interfere with systems sales. The LPS40 Printserver was one of the primary users of the KA620. I have two of these sitting in my desk drawer nowadays - not really of much use! One final VAX configuration that hardly anyone knows about was the M31. This was an experimental large-scale multiprocessor that supported up to 64 uVAX II CPU's off a shared memory. It ran VMS, using a custom configuration until true SMP VMS came along, later "off-the-shelf" VMS V5. However, off-the-shelf VMS only supports up to 32 CPU's, so the machine couldn't reach its full potential - not that it mattered since I'm not certain anyone ever put together a configuration with more than 32 nodes. A couple of these were built; I did some experiments for my dissertation on them - VAX Linda ran quite nicely on 24 nodes, thank you - and they were eventually made available to a few outside experimenters as well. They're long gone now. A paper describing the machine was published as: @inproceedings{reilly:M31, author = "Matthew H. Reilly and John R. Sopka", title = "{M31}: A Large-scale Multiprocessor {VAX} For Parallel Processing Research", booktitle = "Proceedings of the Spring COMPCON", publisher = "{IEEE}", year = 1988, month = mar } Funny story: The official code name of the machine was Andromeda. When the paper above was to be published, it originally called the machine just that, Andromeda. Someone objected to the use of a code name in public. So the references were changed to M31. The objector, who apparently knew no astronomy, was satisfied. -- Jerry ================================================================================ From: don@nz.gen.zl2tnm (Don Stokes) Date: 16 Oct 93 06:41:42 GMT lionel@quark.enet.dec.com (Steve Lionel) writes: > Oh, the list is also missing the VAX-11/751, which was a rack-mounted > (I think) cabinet variant of the 11/750. There was also a set of systems > called something like VAX 8974, which was really a cluster of four "regular" > VAX processors (8800, I think, but could be 8600. My memory is a bit fuzzy > on this.) This was really just a marketing name for a prepackaged > configuration and quickly faded away. Another missing processor is the 8978 and 8974. 8978 was four VAX 8700s, two HSC50s, two SA482s (4xRA82 disk drives in a rack; 2.4GB per SA482), four TA79 tape drives and a MicroVAX II as a console device. 8974 was the same sort of thing, but only four 8700s (and may have scaled down the peripherals as well -- my catalogues are at work). Care to comment on the Firefly? -- Don Stokes, Network Manager, Victoria University of Wellington, New Zealand. don@zl2tnm.gen.nz(home) don@vuw.ac.nz(work) +64 4 495-5052 Fax+64 4 471-5386 ================================================================================ From: pechter@com.lakewood.i4got (Bill Pechter) Date: Sun, 17 Oct 1993 14:46:30 GMT In article <29n6rb$nfm@sousa.ako.dec.com> lionel@quark.enet.dec.com (Steve Lionel) writes: > >In article <1993Oct15.025640.11352@i4got.lakewood.com>, >pechter@i4got.lakewood.com (Bill Pechter) writes: > >>> 01 | - | 780 | 1.8 | U,M,C | VAX-11/782 | Atlas >>This one was 2 11/780's with a backpanel (SBI) shared between the two. It >>was asymetrical multiprocessing - one did the crunch and one did the I/O. > >Not quite. The backplanes were independent - the two systems shared memory >through an MA780 multiport shared memory box which allowed for a maximum >of 4MB memory. You are correct that only one of the processors handled >I/O interrupts (as well as a number of other system functions). The >ASMP version of VAX/VMS was discontinued for VMS V5.0. > Well, my worst nightmare was the 11/782 at RCA in Somerville that wouldn't run backup under some old VMS Rev... (3.2 comes to mind) unless we dropped the system and moved 2 meg of memory from the attached processor to the I/O cpu... So there I was on Sunday morning - moving memory, watching backup, and reinstalling it. I think RCA (now GE if it exists at all) finally stripped this PIG and made 2 11/780's. Bill -- ------------------------------------------------------------------------------- Bill Pechter | The postmaster always pings twice. Lakewood MicroSystems | 17 Meredith Drive, 908-389-3592 | Tinton Falls, NJ 07724 ================================================================================ From: mikel@com.anorad.daytona (Mikel Beck) Date: Sun, 17 Oct 93 15:32:18 GMT Jerry writes in article <9310161314.AA25721@uu3.psi.com>: > Oh, the list is also missing the VAX-11/751, which was a rack-mounted > (I think) cabinet variant of the 11/750. > > Yup. There was, as I recall, a difference in the standard configuration as > well since the disk drives normally used with a 750 at the time didn't fit in > a standard rack. > > I have no idea where the 751 was sold and used; I didn't see any mention of it > until many years later. We had an Intergraph machine which said "751" on the outside of the Intergraph cabinet. On the inside was a sideways-mounted VAX that said "11/751" on it. I don't know the whereabouts of this machine now. -=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-= Mikel Beck E-Mail: mikel@daytona.anorad.com Programmer/Analyst Warnat & Associates, Inc. ================================================================================ From: jfc@edu.mit.athena (John F Carr) Date: 17 Oct 1993 22:03:38 GMT In article <29n6rb$nfm@sousa.ako.dec.com> lionel@quark.enet.dec.com (Steve Lionel) writes: >Oh, the list is also missing the VAX-11/751, which was a rack-mounted >(I think) cabinet variant of the 11/750. MIT used to have several machines we referred to as "hydrovaxes" which I later heard were officially 11/751s. They were VAX 750s in a different cabinet (I never looked inside) with water cooling so they didn't need to be in an air conditioned machine room. They never worked well, especially when MIT physical plant turned off the cooling water or pumped hot water through the system. The RA81s tended to fault when they exceeded 100 degrees. The machine room was never used except to get at the VAXes, so the first warning of failure was typically a machine dropping off the net. There was much joy in the Project Athena operations staff when they were finally turned off forever. (I should correct a statement in the first paragraphs: RA81s tended to fault at any temperature, but 100 degrees would reliably cook one. There was also much rejoicing when we were able to move data off of RA81s.) -- John Carr (jfc@mit.edu) ================================================================================ From: ewilts@ca.bc.gov.vmsmail (Ed Wilts) Date: 17 Oct 93 16:57:16 PST In article <9310161314.AA25721@uu3.psi.com>, Jerry Leichter writes: > Oh, the list is also missing the VAX-11/751, which was a rack-mounted > (I think) cabinet variant of the 11/750. > > Yup. There was, as I recall, a difference in the standard configuration as > well since the disk drives normally used with a 750 at the time didn't fit in > a standard rack. > > I have no idea where the 751 was sold and used; I didn't see any mention of it > until many years later. The 11/751 was widely sold by Intergraph Corporation throughout the world - I helped install many of these myself while working for Intergraph Systems in Canada. Intergraph had built their own I/O adapter for disk and graphic terminal communciations, and bundled a two-rack system consisting of CPU, 9-track tape drive, I/O adapaters, and usually one or two disk drives. I believe the boot ROMs on the 751 were modified to allow booting directly of the Intergraph I/O subsystem. In its peak, Intergraph purchased more Vaxes than anyone else (including the US Government). I actually saw quite a few 751's before I saw my first 750. I rather liked the 751 packaging - you never had to worry about leaning over the system and pushing the little white button... -- Ed Wilts, BC Systems, 4000 Seymour Place, Victoria, B.C., Canada, V8X 4S8 EWilts@Galaxy.Gov.BC.CA Office: (604) 389-3430 Fax: (604) 389-3412 Disclaimer: The opinions and statements contained in this posting are the sole responsibility of the author and have not in any way been reviewed or approved by my employer or any network service. ================================================================================ From: eugene@gov.nasa.nas.wilbur (Eugene N. Miya) Date: Mon, 18 Oct 1993 23:11:41 GMT 1) The Firefly isn't a VAX. It's a RISC based system. A DEC TR is available. It's not a VMS machine either. 2) M31 refs: %A Matthew H. Reilly %A John R. Sopka %T M31: A Large-Scale Multiprocessor VAX for Parallel Processing Research %J Compcon '88 %I IEEE %C San Francisco, CA. %D February -March, 1988 %P 200-206 %K Andromeda, Micro VAX-II, Fast Backplane Interconnect (FBI), VAXcluster %A Ching-Cheng %A Stephen Skedzielewski %A John Feo %Z CRG LLNL %T On the Implementation of Applicative Languages on Shared-Memory MIMD Multiprocessors %J Proceedings ACM/SIGPLAN PPEALS 1988 Parallel Programming: Experience with Applications, Languages and Systems, July 1988, SIGPLAN Notices %V 23 %N 9 %D September 1988 %P 188-197 %K experience with parallel processing systems, sisal, M31, dataflow, Sequent Balance, Cray, Sieve, Simple, first sum loop, %A Matthew Reilly %T Instrumentation for Application Performance Tuning: The M31 System %E Margaret Simmons %E Rebecca Koskela %E Ingrid Bucher %B Instrumentation for Future Parallel Computer Systems %I ACM %C New York %D 1989 %P 143-158 %K DEC, Unfortunately, I didn't enter the book on instrumenting the M31 because I did not get a copy from DEC, but it was advertised in CACM in 1988 when I dropped my ACM membership. Reilly is probably the best person to ask about this. --eugene miya, NASA Ames Research Center, eugene@orville.nas.nasa.gov Associate Editor, Software and Publication Reviews Scientific Programming {uunet,mailrus,other gateways}!ames!eugene Seeking Books to buy: Bongard, Pattern Recognition 3 down 1 to go. ================================================================================ Date: Mon, 18 Oct 93 23:40:24 EDT From: Jerry Leichter 1) The Firefly isn't a VAX. It's a RISC based system. A DEC TR is available. Nope. The Firefly supported up five MicroVAX II CPU's. A later version, whose name I forget, supported 4 CVAX CPU's plus one MicroVAX II. The reason for the funny number of five CPU's in the original was that there were two "compute boards" with two CPU's each, and one with a single CPU and I/O controllers. In the CVAX version, the single MicroVAX II CPU stayed in the design to avoid having to re-do the I/O system. This design made the system asymmetrical, but that wasn't a big bottleneck for the uses the machine was put to. The VAXstation 3520/3540 were essentially commercialized versions of the CVAX-based design; the I/O system got re-done so the lone MicroVAX II could be eliminated. A good reference is: @inproceedings{firefly, author = "Charles P. Thacker and Lawrence C. Stewart", title = "Firefly: a Multiprocessor Workstation", booktitle = "Proceedings of the Second International Conference on Architectural Support of Programming Languages and Operating Systems", year = 1987, month = oct, note = "Published as the joint October 1987 issue of ACM Computer Architecture News, ACM Operating System Review, and ACM SIGPLAN Notices" } Two of my favorite quotes are in this paper. On getting machines out quickly even at the expense of ultimate performance: "Sometimes it's better to have twenty million instructions by Friday than twenty million instructions per second" (Wes Clark). On the performance of the Firefly: "It may not be fast, but it has a lot of torque." (Paul McJones). It's not a VMS machine either. True. The Firefly was built for and at DEC's System Research Labs, and ran a system called Topaz. The 3520/3540 derived from it did, of course, run VMS. -- Jerry ================================================================================ From: oberman@gov.llnl.ptavv Date: Mon, 18 Oct 93 21:25:30 GMT In Article eugene@wilbur.nas.nasa.gov (Eugene N. Miya) writes: >Five 784s were built. I believe I have seen four of the five. >The code name VAXimus is wrong. The term VAXimus came from the >joint Lawrence Livermore, ColoState, DEC dataflow project. >The 784 delivered to LLNL was given the network host name Circus VAXimus. >The single processor software development machine (still named >lll-crg.llnl.gov) is the Gluteus VAXimus (Unix). We had one here starting >as a 782 and upgrading to a 784. I saw CMU's 784 on a visit. I saw one >at a classified site who will remain unnamed. And there was one in Europe >at a DEC site. The person to ask about the 784 is John Sopka who is now >with Transarc. Gordon would also know (and he is with SUN). Just to clarify, CIRCUS ran VMS and the machine which was lll-crg at that time was a 750 running BSD Unix. At the conclusion of the research project the 4 CPUs were split into 4 clustered VMS systems with the imaginative names VAX1, VAX2, VAX3, VAX4. I thought GLUTEUS was a great name, but some people are really boring. At a later date it was decided that the 750 Unix system needed an upgrade. It was LLNL's primary link to the ARPANET at that time using a DL-11 running at 9600 b/s to the ARPANET IMP. So VAX4 was removed from the cluster and took the place of the old 750. While lll-crg is still running, it's on its last legs. It is no longer supported and if it breaks, the oldest remaining LLNL Internet node will bite the dust, leaving ICDC, a vestige of the first Engineering VMS system as the oldest. And, yes, ICDC ran and is still running VMS. But it's been upgraded from a 780 to a 3100. This is just a note for those DEC people who keep saying the the Internet is not used by VMS systems. And, if you work for DEC and wish to deny it, read the section of the DECdts management manual on use of NTP as a time provider first. R. Kevin Oberman Lawrence Livermore National Laboratory Internet: koberman@llnl.gov (510) 422-6955 Disclaimer: Being a know-it-all isn't easy. It's especially tough when you don't know that much. But I'll keep trying. (Both) ================================================================================ From: hansg@se.volvo.vd.risken (Hans Granqvist) Date: Tue, 19 Oct 1993 11:09:25 GMT jfc@athena.mit.edu (John F Carr) writes: >(I should correct a statement in the first paragraphs: RA81s tended to >fault at any temperature, but 100 degrees would reliably cook one. There ^^^^^^^^^^^ At 100 degrees centigrade most anything would cook :-) -- Hans Granqvist, hansg@vd.volvo.se, VOL.VD.HANSG quam maximum credula postero ================================================================================ From: eugene@gov.nasa.nas.wilbur (Eugene N. Miya) Date: Sat, 16 Oct 1993 00:31:03 GMT In article ars@world.std.com (Alan R Sieving) writes: >>pechter@i4got.lakewood.com (Bill Pechter) wrote: >>|>> 01 | - | 780 | 3.5 | U,M,C | VAX-11/784 | VAXimus >then lionel@quark.enet.dec.com (Steve Lionel) replied: >>I've worked at Digital, with VAX systems, continuously since 1978. Though >>I believe there was a "one-off" four-way system using the 11/782 technology >>(memory shared through an MA780), I never heard it given a code name much >>less a marketing designation and it was never sold as a product. It's >>possible that such a configuration was built on request for a customer, but >>I don't recall ever hearing of such. Also, the VAX architecture committee's >>official list of VAX processor IDs (including some for systems never built) >>does not mention a "11/784". (No, you can't have the list.) Five 784s were built. I believe I have seen four of the five. The code name VAXimus is wrong. The term VAXimus came from the joint Lawrence Livermore, ColoState, DEC dataflow project. The 784 delivered to LLNL was given the network host name Circus VAXimus. The single processor software development machine (still named lll-crg.llnl.gov) is the Gluteus VAXimus (Unix). We had one here starting as a 782 and upgrading to a 784. I saw CMU's 784 on a visit. I saw one at a classified site who will remain unnamed. And there was one in Europe at a DEC site. The person to ask about the 784 is John Sopka who is now with Transarc. Gordon would also know (and he is with SUN). >Well, I'm certainly not even close to knowing for certain, but I >remember hearing that Purdue had a machine called an 11/784. George Goble produced two processor VAXen after reading "It is possible to create a multiprocessor by replacing the SBI with a CPU." He did that after they dropped a 780 off a truck. But it was not a VMS machine. A paper exists by George from a Usenix conference. The only VAX I know missing from your table is the Andromeda (M31). The code name is okay because a DEC Press book is out about it (I would not mind having a copy). Gordon and John would also know about this. Basically a VAX version of the Cm*. --eugene miya, NASA Ames Research Center, eugene@orville.nas.nasa.gov Resident Cynic, Rock of Ages Home for Retired Hackers {uunet,mailrus,other gateways}!ames!eugene Second Favorite email message: 550 Host unknown (Authoritative answer from name server): Address family not supported by protocol family A Ref: Mathematics and Plausible Reasoning, vol. 1, G. Polya ================================================================================ From: pechter@com.lakewood.i4got (Bill Pechter) Date: Fri, 15 Oct 1993 02:56:40 GMT In article <1993Oct14.180302.3830@lsl.co.uk> paul@lsl.co.uk (Paul Hardy) writes: >Following recent announcements from DEC, I thought it was time I posted a >new version of my VMS machines list. As usual, any updates are welcomed. > I worked at DEC from 1981 to 1986 and I worked on 11/780's, 11/785, 11/730's and 86XX's and the MicroVax I and II. > 01 | - | 780 | 3.5 | U,M,C | VAX-11/784 | VAXimus I never heard of the 11/784... anyone know anything about it... > 01 | - | 780 | 1.0 | U,M,C | VAX-11/780 | Star > 01 | - | 780 | 1.8 | U,M,C | VAX-11/782 | Atlas This one was 2 11/780's with a backpanel (SBI) shared between the two. It was asymetrical multiprocessing - one did the crunch and one did the I/O. > 01 | - | 780 | 1.5 | U,M,C | VAX-11/785 | Superstar This was a redone 11/780 done it high speed TTL (or was it Schottky)... the 11/785 ran the CPU with a 3/2 ratio of CPU to SBI backplane transfer. Supposedly the DEC SBI and memory on the 11/780 MS780A/C memory was from an earlier unreleased PDP11 or 32 bit PDP11. Any one know about this. My friend who worked on the first shipping Vaxes saw some docs describing memory -- however the machine named wasn't called the Star. Bill -- ------------------------------------------------------------------------------- Bill Pechter | The postmaster always pings twice. Lakewood MicroSystems | 17 Meredith Drive, 908-389-3592 | Tinton Falls, NJ 07724 ================================================================================ From: lionel@com.dec.enet.quark (Steve Lionel) Date: 15 Oct 1993 22:05:31 GMT In article <1993Oct15.025640.11352@i4got.lakewood.com>, pechter@i4got.lakewood.com (Bill Pechter) writes: >> 01 | - | 780 | 1.8 | U,M,C | VAX-11/782 | Atlas >This one was 2 11/780's with a backpanel (SBI) shared between the two. It >was asymetrical multiprocessing - one did the crunch and one did the I/O. Not quite. The backplanes were independent - the two systems shared memory through an MA780 multiport shared memory box which allowed for a maximum of 4MB memory. You are correct that only one of the processors handled I/O interrupts (as well as a number of other system functions). The ASMP version of VAX/VMS was discontinued for VMS V5.0. |> |>> 01 | - | 780 | 3.5 | U,M,C | VAX-11/784 | VAXimus |>I never heard of the 11/784... anyone know anything about it... |> I've worked at Digital, with VAX systems, continuously since 1978. Though I believe there was a "one-off" four-way system using the 11/782 technology (memory shared through an MA780), I never heard it given a code name much less a marketing designation and it was never sold as a product. It's possible that such a configuration was built on request for a customer, but I don't recall ever hearing of such. Also, the VAX architecture committee's official list of VAX processor IDs (including some for systems never built) does not mention a "11/784". (No, you can't have the list.) Oh, the list is also missing the VAX-11/751, which was a rack-mounted (I think) cabinet variant of the 11/750. There was also a set of systems called something like VAX 8974, which was really a cluster of four "regular" VAX processors (8800, I think, but could be 8600. My memory is a bit fuzzy on this.) This was really just a marketing name for a prepackaged configuration and quickly faded away. Another missing processor is the rtVAX (KA620); this was a KA630 (MicroVAX II) board with modified CPU microcode such that the process address space went through only one level of page table translation instead of two. (This had been the original design of the MicroVAX I.) The intent was to come up with a board that could be sold separately for embedded systems applications (it would run VAXELN), but since it would not run VMS, it would not interfere with systems sales. The LPS40 Printserver was one of the primary users of the KA620. I have two of these sitting in my desk drawer nowadays - not really of much use! -- Steve Lionel lionel@quark.enet.dec.com SDT Languages Group Digital Equipment Corporation 110 Spit Brook Road, ZKO2-3/N30 Nashua, NH 03062 "Free advice is worth every cent" ================================================================================ Date: Sat, 16 Oct 93 09:01:04 EDT From: Jerry Leichter |>> 01 | - | 780 | 3.5 | U,M,C | VAX-11/784 | VAXimus |>I never heard of the 11/784... anyone know anything about it... |> I've worked at Digital, with VAX systems, continuously since 1978. Though I believe there was a "one-off" four-way system using the 11/782 technology (memory shared through an MA780), I never heard it given a code name much less a marketing designation and it was never sold as a product. It's possible that such a configuration was built on request for a customer, but I don't recall ever hearing of such. Also, the VAX architecture committee's official list of VAX processor IDs (including some for systems never built) does not mention a "11/784". (No, you can't have the list.) Steve, it just goes to show how large a company DEC is. At least one 11/784, and I think actually a couple, were built for a university, I think Purdue. The university did a multiprocessor Unix port for the machine. I don't know how successful it was. I believe that the 11/784 designation was actually used - someone probably thought it would be a nice touche to come up with an 11/784 label for the front of the cabinet - though since it was never a product as such and was never supported by any DEC-distributed software, it was never widely known. Oh, the list is also missing the VAX-11/751, which was a rack-mounted (I think) cabinet variant of the 11/750. Yup. There was, as I recall, a difference in the standard configuration as well since the disk drives normally used with a 750 at the time didn't fit in a standard rack. I have no idea where the 751 was sold and used; I didn't see any mention of it until many years later. There was also a set of systems called something like VAX 8974, which was really a cluster of four "regular" VAX processors (8800, I think, but could be 8600. My memory is a bit fuzzy on this.) This was really just a marketing name for a prepackaged configuration and quickly faded away 8700's and 8800's. There was a range of configurations with marketing numbers attached to them: You could get 2 8800's or 4 8700's, for example. The number of sales under these fancy package numbers was tiny. Another missing processor is the rtVAX (KA620); this was a KA630 (MicroVAX II) board with modified CPU microcode such that the process address space went through only one level of page table translation instead of two. (This had been the original design of the MicroVAX I.) The intent was to come up with a board that could be sold separately for embedded systems applications (it would run VAXELN), but since it would not run VMS, it would not interfere with systems sales. The LPS40 Printserver was one of the primary users of the KA620. I have two of these sitting in my desk drawer nowadays - not really of much use! One final VAX configuration that hardly anyone knows about was the M31. This was an experimental large-scale multiprocessor that supported up to 64 uVAX II CPU's off a shared memory. It ran VMS, using a custom configuration until true SMP VMS came along, later "off-the-shelf" VMS V5. However, off-the-shelf VMS only supports up to 32 CPU's, so the machine couldn't reach its full potential - not that it mattered since I'm not certain anyone ever put together a configuration with more than 32 nodes. A couple of these were built; I did some experiments for my dissertation on them - VAX Linda ran quite nicely on 24 nodes, thank you - and they were eventually made available to a few outside experimenters as well. They're long gone now. A paper describing the machine was published as: @inproceedings{reilly:M31, author = "Matthew H. Reilly and John R. Sopka", title = "{M31}: A Large-scale Multiprocessor {VAX} For Parallel Processing Research", booktitle = "Proceedings of the Spring COMPCON", publisher = "{IEEE}", year = 1988, month = mar } Funny story: The official code name of the machine was Andromeda. When the paper above was to be published, it originally called the machine just that, Andromeda. Someone objected to the use of a code name in public. So the references were changed to M31. The objector, who apparently knew no astronomy, was satisfied. -- Jerry ================================================================================ From: buda@com.dec.enet.star (Mark A. Buda) Date: 19 Oct 1993 18:15:56 GMT In article , ars@world.std.com (Alan R Sieving) writes: >Well, I'm certainly not even close to knowing for certain, but I >remember hearing that Purdue had a machine called an 11/784. My faint Could that have been an 11/74? There were some PDP-11's in a quad setup. >memory says that it was a custom 4-CPU machine, and that perhaps they >at some point offered "DIY" (do it yourself) instructions on how to >cobble one together. This was about 1984, probably just before the >8600 (nee 790) came out. ================================================================================ From: ghg@edu.purdue.ecn.en (George Goble) Date: Tue, 19 Oct 93 22:06:27 GMT In article , eugene@wilbur.nas.nasa.gov (Eugene N. Miya) writes: > > George Goble produced two processor VAXen after reading > "It is possible to create a multiprocessor by replacing the SBI with a CPU." > He did that after they dropped a 780 off a truck. But it was not a VMS > machine. A paper exists by George from a Usenix conference. We did not drop a 780 off a truck, but we picked one up approx 1 year after the first dualcpu was up from a surplus dealer.. Most of the credit for the Purdue Dualcpu 780 goes to Mike Marsh, Around June 1981, he noticed (in the prints) about something about clock jumpers which could be removed for "extra cpu" on the SBI termination. He quickly figured out that the SBI terminator could be removed, and replaced with a CPU at a different TR level.. The SBI cables needed to be special made, with hot and ground reversed for this.. We made the first set under a microscope, and later got the cable supplier to make them up for us. Mike and I instrumented an 11/780, then the "ve" machine in the Purdue School of Electrical Engineering, room 338. I figured out, that most of the time, about only 1/3 of memory/SBI bus bandwidtth was being used, and it might support a 2nd processor.. There was a Usenix conference near the end of June, 1981, I think it was in Austin?? Mike and I gave talks on Unix Kernel changes and general problems with DEC Unibus Boxes, and covered the rewiring of the grant lines on the DD blocks to get rid of buss reflections, etc.. At the close of that talk, I spent 30 sec or so, about how we might try to build a Dual 780, by removing the SBI terminator and replacing it with a cpu. Over the July 4 weekend, after returning from Usenix, we tried that.. It didn't work at first.. no clocks. It turned out that the "extra cpu" jumpers were incorrect in the prints, and that termination was incorrect on the six clock lines when these jumpers where changed. Mike next constructed a termination pack of 12 resistors to go on the 6 clock lines, and lo and behold it worked.. I had a crude master-slave version of Unix up in about 3 weeks... We had about 10 crashes/day for those 3 weeks.. but it paid off. Armando Stettner (then aps@dec.com?) and I worked on getting that Unix to run on the 782, same as the Purdue dual 780 but it had MA-780 shared memory controllers (each only 1 or 2 MB), so one could easily have a 1$ Million+ config just from the mem controllers. I went out to DEC for a few days and helped APS to get it running.. it worked on the 782 as well... I dunno what, if anything DEC did with it then. The 780 dropped off a truck was not dropped by us. Curt Freeland located one with a bent frame at some junk dealer.. At the time SBI cables were notoriously flakey. Curt went up to the junk dealer, with a set of boards, new SBI cables, etc, to run diags on the suspect 780.. It actually worked, even with a bent frame, but had lots of bad SBI cables.. Curt marked the bad cables "good", and the good ones "bad", and the dishonest dealer, then later removed all the marked "good" ones (he had no way of testing them) and put them on other systems, and put other unknown cables in their place.. He screwed himself.. and ended up with a whole bunch of bad ones, and we ended up with only 1 or two bad! The 780 cpu dropped of the truck, after a frame straightning, became the slave cpu on ef.ecn.purdue.edu which still runs today. Purdue built 10-15 dual 780's (there are even two still running here today e[af].ecn.purdue.edu). Around 2500 copies of the Tech Report were given out by the EE dept, and it even included the parts list to build your own dual 780.. I understand that around 30ish were built by local DEC FS's on T & M basis for various customers.. The original dual 780 was finally turned off and cut up for scrap around 3 weeks ago..it had been renamed to ec.ecn.purdue.edu. This dualcpu 780 model & kernel code was used by SEL (which became Gould), Sequent, Amdahl, and others as a starting point for their multiprocessor Unix machines. --ghg (George Goble) ghg@purdue.edu ================================================================================ From: erc@com.sim114 (Eric R. Crane) Date: 20 Oct 93 20:42:54 GMT In article <2a1ass$3cp@jac.zko.dec.com> buda@star.enet.dec.com (Mark A. Buda) writes: In article , ars@world.std.com (Alan R Sieving) writes: >Well, I'm certainly not even close to knowing for certain, but I >remember hearing that Purdue had a machine called an 11/784. My faint Could that have been an 11/74? There were some PDP-11's in a quad setup. >memory says that it was a custom 4-CPU machine, and that perhaps they >at some point offered "DIY" (do it yourself) instructions on how to >cobble one together. This was about 1984, probably just before the >8600 (nee 790) came out. There was a 784, it consisted of 4 11/780s with a common memory. I remember seeing one while I was at Carnegie Mellon. I also remember seeing a similar machine that was made of 8600's. - Eric R. Crane Westinghouse Electric Corp Simulators Division I am only a consultant here, my opinions are my own and do not reflect the views of Westinghouse. ================================================================================ From: farsef@net.jvnc.tigger (Dan Shoop) Date: Mon, 8 Nov 1993 18:04:43 GMT In Article <29n6rb$nfm@sousa.ako.dec.com>, lionel@quark.enet.dec.com (Steve Lionel) wrote: >|> >|>> 01 | - | 780 | 3.5 | U,M,C | VAX-11/784 | VAXimus >|>I never heard of the 11/784... anyone know anything about it... >|> > >I've worked at Digital, with VAX systems, continuously since 1978. Though >I believe there was a "one-off" four-way system using the 11/782 technology >(memory shared through an MA780), I never heard it given a code name much >less a marketing designation and it was never sold as a product. It's >possible that such a configuration was built on request for a customer, but >I don't recall ever hearing of such. Also, the VAX architecture committee's >official list of VAX processor IDs (including some for systems never built) >does not mention a "11/784". (No, you can't have the list.) Seems to me that while I was at a major bank in the "city" which never slept, that we had a beast that was three (or was it four) cpus in an asmp configuration that after the field test was unsupported and reverted to three 11/78-'s. One still kept the nameplate. -dhan FARSEF | The Dan Shoop | Far Side Internet: shoop@horton.farsef.com | Expeditionary AT&Tnet: 201.612.0895 | Force USmail: 127 East Prospect Street Waldwick, NJ 07463 - He who dies with the most toys... can't collect any more... This message is brought to you as shareware. If you like what was said, please send me a check.