Market research for new PowerPC system
  • Acolyte of the Butterfly
    Acolyte of the Butterfly
    feanor
    Posts: 104 from 2009/3/20
    Quote:


    metalmac wrote:
    Nice initiative! But I think what the Amiga/Haiku/PPC market realy needs is a portable laptop, And still I havent heard that any of the hw players are planing any laptops!? why?


    A laptop is much more difficult to work on. If the motherboard itself is successful and sales are good, we could easily -at least in the case of MPC8610 and P1022- move it back to a netbook form factor. But make no mistake, while an Atom netbook costs ~300-400$, and an ARM can cost $100 less, a PowerPC netbook, at least in small scales that we're after, should cost much more than that. Probably more than $600. On the other hand, it would be really cool to have a modern PowerPC laptop again -I'm writing this now on a Powerbook G4 12", the closest thing to a PowerPC "netbook".

    For now I think the best bet in terms of price, time-to-deliver and features would be going forward with the 8610. The P1022 is a sweet CPU even without Altivec, but it will just take too long -Q4/2010- plus it just occured to me, that binaries with FPU code, will not be able to run on the e500 cores without some kind of real-time FPU code translation, with performance loss.

    Btw, here are some early stats:

    http://www.codex.gr/index.php?pageID=&blogItem=60

    [ Edited by feanor on 2009/9/26 10:57 ]
  • »26.09.09 - 07:54
    Profile Visit Website
  • Yokemate of Keyboards
    Yokemate of Keyboards
    Andreas_Wolf
    Posts: 12179 from 2003/5/22
    From: Germany
    > a PowerPC netbook, at least in small scales that we're after, should
    > cost much more than that. Probably more than $600. On the other hand,
    > it would be really cool to have a modern PowerPC laptop again -I'm
    > writing this now on a Powerbook G4 12", the closest thing to a
    > PowerPC "netbook".

    There is already one, albeit with a CPU that's surely not in the class of the CPUs proposed by you:

    https://morph.zone/modules/newbb_plus/viewtopic.php?topic_id=6436&forum=11

    But then, you probably already know that one at least since your thread at the Haiku forum.

    > it just occured to me, that binaries with FPU code, will not be
    > able to run on the e500 cores without some kind of real-time FPU
    > code translation, with performance loss.

    Exactly, though only true for e500v2 (and before), which the P1 (and P2) series has. e500mc of P4 series (and coming P3 and P5 series) has a "desktop compatible" FPU implementation.

    More (and links therein):
    https://morph.zone/modules/newbb_plus/viewtopic.php?topic_id=6313&forum=11&start=3
    https://morph.zone/modules/newbb_plus/viewtopic.php?topic_id=6465&forum=11&start=19
  • »26.09.09 - 11:33
    Profile
  • Acolyte of the Butterfly
    Acolyte of the Butterfly
    feanor
    Posts: 104 from 2009/3/20
    Quote:


    There is already one, albeit with a CPU that's surely not in the class of the CPUs proposed by you:

    https://morph.zone/modules/newbb_plus/viewtopic.php?topic_id=6436&forum=11

    But then, you probably already know that one at least since your thread at the Haiku forum.



    Yes, I saw that one, interesting, but it's not what I was thinking about.

    Quote:


    Exactly, though only true for e500v2 (and before), which the P1 (and P2) series has. e500mc of P4 series (and coming P3 and P5 series) has a "desktop compatible" FPU implementation.



    Yes, unfortunately it applies to our case, the P4 is way too expensive and I couldn't seriously suggest it as an alternative right now. (I know we are saying the same thing, there is no argument here). I just realized that for backwards compatibility, perhaps P1022 is not the best case, though attractive overall. It would need some serious work on the FPU real-time translation, and I can't even estimate the impact of that.
  • »26.09.09 - 12:01
    Profile Visit Website
  • Yokemate of Keyboards
    Yokemate of Keyboards
    Andreas_Wolf
    Posts: 12179 from 2003/5/22
    From: Germany
    > What kind of interest there is on the Haiku side?

    http://www.haiku-os.org/community/forum/market_research_new_powerpc_system
  • »26.09.09 - 12:02
    Profile
  • Paladin of the Pegasos
    Paladin of the Pegasos
    SoundSquare
    Posts: 1213 from 2004/12/1
    From: Paris, France
    Quote:

    The OSW's TetraPower board was supposed to be PPC970 based. None of the 3 proposed CPUs is PPC970. I guess work on the new board would rather be based on the "Pegasos 8641D" (but with 8640D instead) or on the "Efika 8610" :-)


    true, i mixed them sorry.
  • »26.09.09 - 13:35
    Profile
  • Priest of the Order of the Butterfly
    Priest of the Order of the Butterfly
    CountRaven
    Posts: 566 from 2007/12/10
    From: Greece
    Mail sent. Support MorphOS. We need new Hardware.
  • »27.09.09 - 12:02
    Profile Visit Website
  • Caterpillar
    Caterpillar
    Falcon_11
    Posts: 32 from 2004/2/7
    From: Slovakia
    Mail sent. We wish new PPC based Hardware.

    with Regards
    DEAD
    MB :Pegasos-II
    CPU :G4/1GHz
    OS :MOS 2.2 reg, MOS 1.4.5, Ubuntu 8.04, MACOSX Panther on MOLk
    RAM :512MB-DDR266 Apacer
    GFX :ATI-Radeon 9200 128MB
    HDD :MAXTOR-160+80GB ATA133
    TV :Pinnacle Studio PCTV


    Powerbook G4 A1139, MOS3.18
  • »27.09.09 - 13:44
    Profile Visit Website
  • Order of the Butterfly
    Order of the Butterfly
    ironfist
    Posts: 254 from 2004/4/22
    From: Pegasos.org
    jcmarcos:
    Yes, the CrabFire was essentially a Pegasos 2 G4 in a
    custom-built 2U-case and a stripped down Linux OS.

    CrabOS, however, was an operating system made by
    ex. Gentoo developer David Holm. The target platform
    was of course the CrabFire.

    Too bad we didn't get the CrabFire to market. We all had
    our day-jobs aside and the project pretty much died.

    Today, however, I work in my own company with ZyXEL
    firewalls. Their latest firewall-line (USG) are mostly running
    PowerQUICC CPU's. Only the highest end USG 1000-2000
    are running dual-core x86 CPUs.
  • »27.09.09 - 18:54
    Profile Visit Website
  • Cocoon
    Cocoon
    eastone
    Posts: 44 from 2007/8/4
    From: Vaasa/Finland
    Mail is sent.
  • »28.09.09 - 10:18
    Profile
  • Paladin of the Pegasos
    Paladin of the Pegasos
    pampers
    Posts: 1061 from 2009/2/26
    From: Tczew, Poland
    Any update on the figures, how many people are interested in that project?
    MorphOS 3.x
  • »28.09.09 - 12:27
    Profile Visit Website
  • Acolyte of the Butterfly
    Acolyte of the Butterfly
    feanor
    Posts: 104 from 2009/3/20
    Quote:


    pampers wrote:
    Any update on the figures, how many people are interested in that project?


    I was just about to paste this:

    http://www.codex.gr/index.php?pageID=&blogItem=62
  • »28.09.09 - 13:12
    Profile Visit Website
  • Paladin of the Pegasos
    Paladin of the Pegasos
    pampers
    Posts: 1061 from 2009/2/26
    From: Tczew, Poland
    Feanor: is there any limit you have to reach to consider making your project alive?
    MorphOS 3.x
  • »28.09.09 - 15:55
    Profile Visit Website
  • Acolyte of the Butterfly
    Acolyte of the Butterfly
    feanor
    Posts: 104 from 2009/3/20
    I'd like 500 mails yes. I could even consider it at 300 (a typical production run is 500 units), ~60 is too few, but I didn't expect to satisfy the limit in 3 days obviously. I'm a patient man -until the end of October at least. :)
  • »28.09.09 - 15:57
    Profile Visit Website
  • Paladin of the Pegasos
    Paladin of the Pegasos
    pampers
    Posts: 1061 from 2009/2/26
    From: Tczew, Poland
    Did you try to announce that out of Amiga, Morphos and Haiku related forums? Meaby that would be a good chance to get some brand new users to our market :)
    MorphOS 3.x
  • »28.09.09 - 16:36
    Profile Visit Website
  • Acolyte of the Butterfly
    Acolyte of the Butterfly
    feanor
    Posts: 104 from 2009/3/20
    I asked also on linuxppc-dev, and debian-powerpc -though I admit I never found a reply from the debian list. I'll probably try again. I also intend to post on several more linux/ppc lists (gentoo, arch, ubuntu, opensuse).
  • »28.09.09 - 16:44
    Profile Visit Website
  • MorphOS Developer
    Krashan
    Posts: 1107 from 2003/6/11
    From: Białystok...
    @feanor

    Don't be affraid of multiple cores. MorphOS can use them in relatively easy to implement way. Not SMP, of course, but "dual/quadcore makes no sense for MorphOS" is a myth.
  • »28.09.09 - 18:13
    Profile Visit Website
  • Order of the Butterfly
    Order of the Butterfly
    Ruud
    Posts: 335 from 2009/2/2
    From: Hampshire, UK
    @Krashan

    This is interesting...in what way and to what extent could Morphos make use of extra cores without SMP?
    "We live, we die, we laugh, we cry"
  • »28.09.09 - 18:57
    Profile
  • Acolyte of the Butterfly
    Acolyte of the Butterfly
    feanor
    Posts: 104 from 2009/3/20
    Quote:


    Krashan wrote:
    @feanor

    Don't be affraid of multiple cores. MorphOS can use them in relatively easy to implement way. Not SMP, of course, but "dual/quadcore makes no sense for MorphOS" is a myth.


    I'm not afraid of multicores, in fact if P1022 was out now, I would go for this one no question about that, specs are right, the price is right and it's low-power. But samples start Q1/2010, it's a long wait and perhaps people will get bored waiting. We'll see.
  • »30.09.09 - 07:16
    Profile Visit Website
  • ASiegel
    Posts: 1376 from 2003/2/15
    From: Central Europe
    @ Ruud

    Quote:

    This is interesting...in what way and to what extent could Morphos make use of extra cores without SMP?


    In the same general way as MorphOS is able to offload certain tasks from the CPU to a graphics processor, for instance.

    There are reasons why seemingly every major OS supports SMP, however ;-)
  • »30.09.09 - 08:09
    Profile
  • MorphOS Developer
    Krashan
    Posts: 1107 from 2003/6/11
    From: Białystok...
    Quote:

    Ruud wrote:

    This is interesting...in what way and to what extent could Morphos make use of extra cores without SMP?


    The same way as PowerUp used two different processors. I see it as a library allowing for launching processes, or even an extension to dos.library. IPC may be integrated in exec. In fact supporting multiple cores of one processor is easier than PowerUp because of following reasons:

    1. Cores are identical, so you need not to use different compiler. You may write the same code which runs on both single core and multicore systems.

    2. Cache coherency between cores is ensured by hardware.

    Disadvantages are:

    1. Only new applications using the extension may take advantage of multiple cores (on the other hand it does not break compatibility). Old apps will run on "main" core only.

    2. Programmer should desing an application multithreaded way (but this is also needed for systems with SMP as far as I know).
  • »30.09.09 - 14:33
    Profile Visit Website
  • ASiegel
    Posts: 1376 from 2003/2/15
    From: Central Europe
    @ Krashan

    Quote:

    2. Programmer should desing an application multithreaded way (but this is also needed for systems with SMP as far as I know).


    Yes, if a single application is supposed to utilize, say, four cores when running on an SMP-capable OS, then you need to design it to be multithreaded.

    That being said, you can run four single-threaded applications on a quad-core machine and your typical SMP-capable OS will manage to utilize all four cores (one per app, for instance) rather than run the applications on the main core only.
  • »30.09.09 - 15:15
    Profile
  • Paladin of the Pegasos
    Paladin of the Pegasos
    jcmarcos
    Posts: 1178 from 2003/3/13
    From: Pinto, Madrid ...
    Quote:

    Krashan wrote:
    Quote:

    Ruud wrote:

    in what way and to what extent could Morphos make use of extra cores without SMP?


    The same way as PowerUp used two different processors.


    Exactly the same thing I thought of years ago. In fact, the PowerUP framework was more difficult than this scenario.

    Quote:

    I see it as a library allowing for launching processes, or even an extension to dos.library.


    The "dos.library" is the one that starts processes?

    Quote:

    IPC may be integrated in exec


    Of course, some extensions would be needed in the kernel. By the way, is anyone surprised that we are talking about SMP, and there's NO mention of Quark? MorphOS IS the A-Box, there's still a SMP capable kernel beneath, and funnily, its SMP abilities wouldn't be used.

    Quote:

    Cores are identical, so you need not to use different compiler.


    Yes, one minor (ahem) detail, that emphzsizes just how amazing was the PowerUP system. A computer inside a computer, an operating system inside an operating system.

    Quote:

    Cache coherency between cores is ensured by hardware.


    There's been a lot of talk about this since a long ago...

    Quote:

    Only new applications using the extension may take advantage of multiple cores. Programmer should desing an application multithreaded way


    Of course, these are not disadvantages of this implementation, only the obvious, natural compromises, of SMP computing. For example, sometimes, doing something on several cores is actually slower than ina single one. That can't be counted as a disadvantage of the implementation, it's just life.
  • »30.09.09 - 15:22
    Profile
  • Acolyte of the Butterfly
    Acolyte of the Butterfly
    feanor
    Posts: 104 from 2009/3/20
    Quote:


    jcmarcos wrote:
    ...That can't be counted as a disadvantage of the implementation, it's just life.


    Actually, life doesn't really bother with such details, it's just computers that deal with such stuff :)
  • »30.09.09 - 15:30
    Profile Visit Website
  • Cocoon
    Cocoon
    fairlanefastback
    Posts: 54 from 2007/2/6
    I sent my email yesterday. :-D
  • »30.09.09 - 15:34
    Profile
  • Acolyte of the Butterfly
    Acolyte of the Butterfly
    Georg
    Posts: 111 from 2004/4/7
    @Krashan

    I would do multiple core support by simply allowing (through some new Exec functions) tasks to enter and leave a special state where they are multi-core-safe. While in this state the scheduler is allowed to run them on other cores. See here.
  • »30.09.09 - 15:45
    Profile