black@par1.cs.umass.edu (David K. Black) (04/03/91)
Assuming that this aparently moribund file is concerned with the Motorola 88100 and and 88200 RISC Chips, would anyone care to post or send a list of currently available machines that employ them? The only one I know about is the BBN TC2000. Thanks, David Black black@cs.umass.edu
martin@adpplz.UUCP (Martin Golding) (04/05/91)
In <28747@dime.cs.umass.edu> black@par1.cs.umass.edu (David K. Black) writes: >Assuming that this aparently moribund file is concerned with the >Motorola 88100 and and 88200 RISC Chips, would anyone care to >post or send a list of currently available machines that employ them? Motorola makes some. Their customer support is great (for VAR's, anyway). A naive domestic computer without any breeding, but I think you'll admire its pretensions. Martin Golding | sync, sync, sync, sank ... sunk: Dod #0236 | He who steals my code steals trash. A Poor old decrepit Pick(tm) programmer ... Sympathize at: {mcspdx,pdxgate}!adpplz!martin or martin@adpplz.uucp
jay@metran.UUCP (Jay Ts) (04/06/91)
In <28747@dime.cs.umass.edu> black@par1.cs.umass.edu (David K. Black) writes: >Assuming that this aparently moribund file is concerned with the >Motorola 88100 and and 88200 RISC Chips, would anyone care to >post or send a list of currently available machines that employ them? Here is the list of 88open Certified Platforms, from the March 1991 88open Report: Data General Aviions Dolphin Triton 88 Harris Night Hawk 4400 Motorola Delta 8000 Opus Series 400 & 8000 Personal Mainframe Sanyo/Icon 3080, 3380 & 8000 Personal note: considering that the 88000 is by far the best microprocessor architecture on the market, and the pioneering work of 88open into the planning of Open Systems, I find the brevity of this list to be very depressing. Jay Ts, Director Metran Technology uunet!pdn!tscs!metran!jay (813) 979-9169
kpt@ibism.UUCP (Kevin Tyson) (04/08/91)
In article <5@metran.UUCP>, jay@metran.UUCP (Jay Ts) writes: |> |> Personal note: considering that the 88000 is by far the best microprocessor |> architecture on the market, and the pioneering work of 88open into the planning |> of Open Systems, I find the brevity of this list to be very depressing. |> I agree. Although I'm a neophyte when it comes to microprocessor architecture I think this one has a future. I've tried to interest my clients in 88K based systems with the following results: Data General based systems rejected out of hand. My clients have been burned so badly in the past they would gladly eviscerate my and any DG representative I dragged in even if it was the best machine made and was being given away for free. Tektronics is preceived as over priced for the commercial, as opposed to the scientific marketplace. Motorola has not been very agressive in their marketing. It took quite an effort the get any information out of their 800 number and what we got was underwhelming. No one seems to be moving in the OSF direction with 88K based systems which regardless of how I feel about OSF is a drawback with my clients. If anyone is aware of commercial software, i.e. relational databases, C++ compilers, DEC connectivity, etc, from reputable vendors for 88k based systems I'd love to hear about it. Thanks in advance, -- Kevin P. Tyson Phone: 212-657-5928 Fax: 212-825-8607 IISA c/o Citibank E-Mail: uunet!ibism!kpt 111 Wall Street New York, NY 10043
jcallen@Encore.COM (Jerry Callen) (04/09/91)
In article <5@metran.UUCP> jay@metran.UUCP (Jay Ts) writes: >Here is the list of 88open Certified Platforms, from the March 1991 88open >Report: > > Data General Aviions > Dolphin Triton 88 > Harris Night Hawk 4400 > Motorola Delta 8000 > Opus Series 400 & 8000 Personal Mainframe > Sanyo/Icon 3080, 3380 & 8000 > >Personal note: considering that the 88000 is by far the best microprocessor >architecture on the market, and the pioneering work of 88open into the planning >of Open Systems, I find the brevity of this list to be very depressing. A few comments: - I think that the list of 88K-based machines is MUCH longer than the list of machines currently certified as conforming to the 88K BCS and OCS. Some 88K-based systems may NEVER be certified. Consider, for instance, single-board computers, made by companies like Force and Tadpole, that run real-time executives, not Unix. [self-interest mode on] Encore makes 88K-based systems (the Encore 91 Series), too. [self-interest mode off] - I like the 88K, but I'd be pretty reluctant to assert that it is "by far the best microprocessor architecture on the market." -- Jerry Callen jcallen@encore.com
jat@xavax.com (John Tamplin) (04/09/91)
In article <5@metran.UUCP> jay@metran.UUCP (Jay Ts) writes: >Here is the list of 88open Certified Platforms, from the March 1991 88open >Report: > > Data General Aviions > Dolphin Triton 88 > Harris Night Hawk 4400 > Motorola Delta 8000 > Opus Series 400 & 8000 Personal Mainframe > Sanyo/Icon 3080, 3380 & 8000 > >Personal note: considering that the 88000 is by far the best microprocessor >architecture on the market, and the pioneering work of 88open into the planning >of Open Systems, I find the brevity of this list to be very depressing. > > Jay Ts, Director > Metran Technology > uunet!pdn!tscs!metran!jay > (813) 979-9169 IBM proved with the PC that you don't have to have the best product or even a good one to make a lot of money. Profit, not technical merit, is motivation for companies. Sun had already spent a lot of money on Sparc before the 88k came along, and MIPS had some design wins (DEC, Stardent, etc) before the 88k existed. I think that future generations of the respective chips will widen the performance difference between Sparc and 88k, and may provide some inroads there. MIPS is currently comparable (based on technical merit), although I feel the 88k has a slight edge by not having the internals of the pipeline visible to the compiler. It seems that Motorola and MIPS are taking different roads for the future -- MIPS jumping early onto the 64 bit bandwagon and Motorola aiming for superscalar speed. I guess we will see which one wins in a few years. -- John Tamplin Xavax jat@xavax.COM 2104 West Ferry Way ...!uunet!xavax!jat Huntsville, AL 35801
smithr@ast.dsd.northrop.com (Dick Smith) (04/12/91)
>In <28747@dime.cs.umass.edu> black@par1.cs.umass.edu (David K. Black) writes: >>Assuming that this aparently moribund file is concerned with the >>Motorola 88100 and and 88200 RISC Chips, would anyone care to >>post or send a list of currently available machines that employ them? In article <5@metran.UUCP> jay@metran.UUCP (Jay Ts) replies: > >Here is the list of 88open Certified Platforms, from the March 1991 88open >Report: > > Data General Aviions > Dolphin Triton 88 > Harris Night Hawk 4400 > Motorola Delta 8000 > Opus Series 400 & 8000 Personal Mainframe > Sanyo/Icon 3080, 3380 & 8000 > Do not forget that there are many board vendors offering 88K products such as VMEbus boards that are not bundled into a system. Here is a sampling of such vendors (taken from Dec 90 issue of VMEbus Systems magazine): Tadpole Technology 800-232-6656 Motorola 800-624-8999 Force Computers 408-370-6300 Aitech 408-720-9400 Imp 408-429-1338 Eltec Eletronik 818-449-1558 I currently intend to use a board from one of the above listed, along with pSOS (Software Components Group) real time operating system. Pete Salerno, c/o Dick Smith Northrop ESD-RMS smith@ast.dsd.northrop.com
meissner@osf.org (Michael Meissner) (04/12/91)
In article <5@metran.UUCP> jay@metran.UUCP (Jay Ts) writes: | Personal note: considering that the 88000 is by far the best microprocessor | architecture on the market, and the pioneering work of 88open into the planning | of Open Systems, I find the brevity of this list to be very depressing. I probably shouldn't say anything, but that never stopped me before...... I agree with Hennesey and Patterson, that the current crop of RISC's are more similar than they are different. The m88k does have a few warts: * A signed divide instruction that traps if either number is negative. This was the single worst feature of the machine when I was doing GCC development IMHO. * No multiply with overflow checking. * Memory load latency of 3 cycles instead of 2 cycles. * FP registers in the general register pool. I used to think this was a feature, but now I'm convinced it's a bug. The biggest problem is you run out of registers when unrolling heavy FP loops. Another problem is that it probably limits how fast the next generation of chips can be. To the people that think it's neat so that you can do bit flipping and such, I had done some of that in GCC, and I and Tom Wood removed it because it violates the IEEE floating point spec. * 64-bit FP paths seem to have lots of 32-bit knotholes that limit performance (true of most 1st generation RISC systems). * Standard doesn't include a small data area, which allows one instruction memory references to small static/global items. It was in at one time, and then removed. * Passing structures on the stack. This makes varargs real awkward. The original calling sequence had the first 8 arguments passed in registers, even if a structure was split between the stack and registers. This allowed a varargs function to just store the 8 registers into the homing area, and use a char * pointer to bop through the argument list. Now, you have to store the 8 registers elsewhere, and use ?: to determine if an argument was in the first 8 words or passed on the stack (as if printf wasn't slow enough as is). This was because a particular compiler vendor bulldozed the 88open committee. * Time to market on the original 88100 was real late. I suspect the same problem will occur with the 88110. * No remainder instruction. Things that I see as features as compared to the MIPS include: * Double indexed addressing, and scaling by 2, 4, or 8. * The extract bits stuff, though it can cause some code to break that does shift by 32. * Hardware interlocks, which allows code meant for different implementations to work (though possibily not work at peak speed). * {,f}cmp giving you <, =, and > status all at the same time. * 13 saved registers (as compared to 9 integer regs) on the MIPS. -- Michael Meissner email: meissner@osf.org phone: 617-621-8861 Open Software Foundation, 11 Cambridge Center, Cambridge, MA, 02142 Considering the flames and intolerance, shouldn't USENET be spelled ABUSENET?
tom@ssd.csd.harris.com (Tom Horsley) (04/12/91)
meissner> * Standard doesn't include a small data area, which allows one
meissner> instruction memory references to small static/global items.
meissner> It was in at one time, and then removed.
But the standard does include 4 reserved registers for the linker to use as
it sees fit. Our (Harris Computer Systems Division) compiler tools include a
post-linker optimizer that uses these 4 registers to hold the 4 most common
values appearing in 'or.u' instructions, and then squeezes out the or.u
instructions.
Statistics we have gathered on a very wide range of programs show that we
almost always get the majority of the memory references this way (some
fortran programs with heavy common block usage speed up by 15-20%). In fact,
for most programs, using only 2 base registers (rather than the 4 available)
covers most of the memory references.
A "small data" area would require an omniscient compiler that could predict
ahead of time how much data any given compilation unit could be allowed to
allocate to the small data area so that it doesn't overflow once the program
is linked with all the other compilation units that allocate small data
space. If you overflow the small data area, you then have to go back and
recompile something.
meissner> * Passing structures on the stack. This makes varargs real
meissner> awkward.
Yep. This is the stupidest bonehead idea in the whole OCS standard, but note
that it doesn't have anything to do with the hardware architecture (of
course we are still stuck with it if we want to be standard conforming).
--
======================================================================
domain: tahorsley@csd.harris.com USMail: Tom Horsley
uucp: ...!uunet!hcx1!tahorsley 511 Kingbird Circle
Delray Beach, FL 33444
+==== Censorship is the only form of Obscenity ======================+
| (Wait, I forgot government tobacco subsidies...) |
+====================================================================+rcg@lpi.liant.com (Rick Gorton) (04/12/91)
In article <14518@encore.Encore.COM> jcallen@encore.Com (Jerry Callen) writes: >In article <5@metran.UUCP> jay@metran.UUCP (Jay Ts) writes: >>Here is the list of 88open Certified Platforms, from the March 1991 88open >>Report: >> >> Data General Aviions >> Dolphin Triton 88 >> Harris Night Hawk 4400 >> Motorola Delta 8000 >> Opus Series 400 & 8000 Personal Mainframe >> Sanyo/Icon 3080, 3380 & 8000 >> > Encore makes 88K-based systems (the Encore 91 Series), too. > >-- Jerry Callen > jcallen@encore.com Are the 91 Series machines currently in production? (Or can you say?) I haven't heard anything at all or seen anything in the trade press. Personally, I think that a shared memory multiprocessor 88100 box would be ideal for heavy-duty engineering/scientific computing, and with proper tools/compilers, it could very easily compete in the mini-super market. -- Richard Gorton rcg@lpi.liant.com (508) 626-0006 Language Processors, Inc. Framingham, MA 01760 Hey! This is MY opinion. Opinions have little to do with corporate policy.
jcallen@Encore.COM (Jerry Callen) (04/17/91)
In article <1991Apr12.164153.396@lpi.liant.com> rcg@lpi.liant.com (Rick Gorton) writes: >Are the [Encore] 91 Series machines currently in production? Yes. I use one daily. Production is just ramping up, and I _think_ all shipments thus far are to beta sites. I'm a techie, so I don't have sales info. I also don't have hard performance numbers, but it's subjectively very fast. How's THAT for vague? :-) -- Jerry Callen jcallen@encore.com
scottl@convergent.com (Scott Lurndal) (04/19/91)
In article <1991Apr8.155753.14742@decvax.dec.com>, kenton@abyss.zk3.dec.com (Jeff Kenton OSG/UEG) writes: |> In article <12356@ibism.uucp>, kpt@ibism.UUCP (Kevin Tyson) writes: |> |> |> |> If anyone is aware of commercial software, i.e. relational databases, |> C++ compilers, |> |> DEC connectivity, etc, from reputable vendors for 88k based systems |> |> I'd love to hear about it. |> |> |> |> Try Encore and BBN. Any others out there? |> Obtain a copy of the 88open Sourcebook. It lists available software packages (many of which have been certified to be Binary Compatible on 88k systems, the rest are in process of certification, or have promised to be certified). Obtain from: 88open Consortium Ltd. 100 Homeland Court, Suite 800 San Jose, Ca 95112 Tel: +1 408 436-6600 Fax: +1 408 436-0725 -------------------------------------------------------------------- Scott Lurndal UNISYS Network Computing Group
brian@king.csd.mot.com (04/20/91)
In article <12356@ibism.uucp>, kpt@ibism.UUCP (Kevin Tyson) writes: > > If anyone is aware of commercial software, i.e. relational databases, C++ compilers, > DEC connectivity, etc, from reputable vendors for 88k based systems > I'd love to hear about it. > Try Motorola Computer Group! Depending on your need, either the Commercial Systems Division or the Technical Systems Division should be able to help. CSD's phone number is (408)255-0900 and TSD's phone number is (602)438-3418. I have no connection with Motorola other than that it's my job :-).