CONFIRMED IBM Power PC 970

11921232425

Comments

  • Reply 401 of 489
    [quote]Originally posted by moki:

    <strong>



    they do list what they use; here's the gzip test for instance:



    .....





    164.gzip's reference workload has five components: a large TIFF image, a webserver log, a program binary, random data, and a source tar file. With the exception of the random data, these components were selected as a reasonably representative set of things that gzip might be most often used on. The random data is present to test gzip's worst-case behavior.



    .....



    ...and you can download the reference data files to run the tests yourself.



    As for why the G4 scores so poorly, I honestly have no idea -- it isn't _that_ slow of a processor.</strong><hr></blockquote>



    I meant they don't state the number of bytes out in the open where a lazy SOB like me can spot it quickly. I don't value SPECmarks so I have no particular interest in downloading and running the things. Somebody who does value the things ought to do that and use some of Apple's analysis tools to figure out why it comes in so poorly.
  • Reply 402 of 489
    noahjnoahj Posts: 4,503member
  • Reply 403 of 489
    bartobarto Posts: 2,246member
    Read it this morning (I get The Oz delivered).



    David Frith is not the best Mac jornalist, he re-hashes other people's info basically.



    Last year he used MOSR as a reliable basis for the introduction of the G5 in 2002.



    Nothing to see here, move along.



    Barto
  • Reply 404 of 489
    mokimoki Posts: 551member
    This is quite a nice article on the PPC 970, for those of you who haven't seen it (it is quite technical, though):



    <a href="http://arstechnica.com/cpu/02q2/ppc970/ppc970-1.html"; target="_blank">http://arstechnica.com/cpu/02q2/ppc970/ppc970-1.html</a>;



    ...a nice highlight to read (as well as the power consumption and multiprocessor abilities of the 970):



    "If the P4 takes a narrow and deep approach to performance and the G4e takes a wide and shallow approach, the 970's approach could be characterized as wide and deep. In other words, the 970 wants to have it both ways: an extremely wide execution core and a 16-stage (integer) pipeline that, while not as deep as the P4's, is nonetheless built for speed"
  • Reply 405 of 489
    tabootaboo Posts: 128member
    For what it's worth (I know, not much, really), this was in yesterday's "IBM Microelectronics News and Updates".



    [quote] PowerPC?



    IBM unveils details of new PowerPC chip



    The Journal News

    October 15, 2002



    IBM Corp. has a new, high-performance PowerPC microprocessor in the pipeline that will be used in Apple's next generation of computers. The PowerPC 970 inherits technology from the POWER4 chip that IBM deploys in its high-end Unix servers.



    The PowerPC 970 will run at clock speeds of 1.6 gigahertz to 1.8 gigahertz. IBM's PowerPC now tops out at 1 gigahertz.



    Though IBM hasn't announced customers for the new chip, industry sources confirmed that Apple will be among the first in line. The iMac maker's fastest machines now have 1.25 PowerPC gigahertz processors from Motorola.



    The complete article is located at:

    <a href="http://www.thejournalnews.com/newsroom/101502/15ibm.html"; target="_blank">http://www.thejournalnews.com/newsroom/101502/15ibm.html</a>;



    Apple Fans Await IBM Chip





    NEW YORK - It's been nearly ten years since a new chip has excited fans of Apple Computer.



    But IBM's semiconductors division released the first details of a new chip architecture, which some suspect could be aimed at the next generation of Apple computers.



    It's called the GigaProcessor Ultralite and evolved from the same line of PowerPC processors that IBM and Motorola have supplied to Apple since the launch of the first PowerMac computers in 1994.



    The main difference from previous versions of the PowerPC is that the new IBM design calls for the chip to be capable of 64-bit computing. In the Windows world, 64-bit chips are the next evolutionary step for both high-end server computers and, to a lesser extent, desktop systems. The main advantage with 64-bit over conventional 32-bit processors is that the systems can work with vastly larger banks of memory, which in turn speeds up the task of crunching through large complex sets of data.



    The Forbes article is available at:

    <a href="http://www.forbes.com/2002/10/14/1014apple.html?partner=yahoo&referrer="; target="_blank">http://www.forbes.com/2002/10/14/1014apple.html?partner=yahoo&referrer=</a>;

    <hr></blockquote>



    This'll be the 3rd time Apple has been mentioned as the end-user of the 970 in one of IBM's mail-outs.



    [ 10-31-2002: Message edited by: taboo ]</p>
  • Reply 406 of 489
    jerombajeromba Posts: 357member
    Don't know if somebody post this but here it is :



    <a href="http://www-3.ibm.com/chips/techlib/techlib.nsf/techdocs/A1387A29AC1C2AE087256C5200611780/$file/PPC970_MPF2002.pdf"; target="_blank">IBM INFO ON PPC970</a>



    edit: UBB URL doesn't work ???

    edit: thanks MacRonin



    [ 11-07-2002: Message edited by: jeromba ]</p>
  • Reply 407 of 489
    macroninmacronin Posts: 1,174member
    Try this one...



    <a href="http://www-3.ibm.com/chips/techlib/techlib.nsf/techdocs/A1387A29AC1C2AE087256C5200611780/$file/PPC970_MPF2002.pdf"; target="_blank">IBM INFO ON PPC970</a>



    You had a single space between the .pdf extension & the close bracket...
  • Reply 408 of 489
    thegeldingthegelding Posts: 3,230member
    nice link macronin



    so only 19 watts at 1.2g---perhaps they can use this in the Powerbooks...maybe even next rev of iBooks...i know the G3 puts out very little watts, but what is the 1g G4 putting out in the PowerBooks now? g
  • Reply 409 of 489
    macroninmacronin Posts: 1,174member
    BIG BUMP...
  • Reply 410 of 489
    [quote]Originally posted by MacRonin:

    <strong>BIG BUMP...</strong><hr></blockquote>



    Man i was excited thinking someone had some insider info on the new chip, but alas just a bump. It's kinda' like when that that dude with Mr. Happy on South Park describes the ending to the movie "Contact".
  • Reply 411 of 489
    bigcbigc Posts: 1,224member
    Well then, <a href="http://www.llnl.gov/llnl/06news/Images/comp2women.jpg"; target="_blank">here </a> is a picture of the IBM 970 boxes being tested. Note the XRAID (minus a few HD) in the upper left of the picture. Hopefully these are not the boxes the 970 will ship in.
  • Reply 412 of 489
    stoostoo Posts: 1,490member
    Newer versions of GCC (3.1 an up) are more efficient/optimised than previous versions and should produce better SPEC scores. I've no idea how much better: anyone else know?
  • Reply 413 of 489
    bigcbigc Posts: 1,224member
    doesn't IBM use there own compilers for spec marks??
  • Reply 414 of 489
    amorphamorph Posts: 7,112member
    They would, but SPEC isn't written in PL/I.



    <img src="graemlins/lol.gif" border="0" alt="[Laughing]" />
  • Reply 415 of 489
    outsideroutsider Posts: 6,008member
    According to <a href="http://www-6.ibm.com/jp/chips/forum0/pdf/05.pdf"; target="_blank">this PDF</a> ,the next processor in the 9xx line is due in 2004. It would stand to reason that the 970 is very nearly ready for release in early-spring 2003.
  • Reply 416 of 489
    [quote]Originally posted by Bigc:

    <strong>Well then, <a href="http://www.llnl.gov/llnl/06news/Images/comp2women.jpg"; target="_blank">here </a> is a picture of the IBM 970 boxes being tested. Note the XRAID (minus a few HD) in the upper left of the picture. Hopefully these are not the boxes the 970 will ship in.</strong><hr></blockquote>



    Dude! You kill Me! <img src="graemlins/lol.gif" border="0" alt="[Laughing]" />
  • Reply 417 of 489
    Bigc, that line "Well then, here is a picture of the IBM 970 boxes being tested", and the pic was great. Thanks for the humor.



    Outsider, interesting PDF. Aside from what you point out, I thought it was interesting on the last page, where it stated that the PPC 750CXe was currently shipping in 600MHz config and the PPC 750FX would be shipping in a 733MHz config in 11/02. The part that was interesting (as in confirming that Apple has a special deal with IBM, like they do with Moto) was that the iBook currently ships in 700MHz and 800MHz G3s. I'm not sure what version of the PPC 750 Apple uses though. That implies that Apple also has a special deal concerning the 9XX family. I say 9XX family because it is possible that Apple may not get the 970, but instead a 9XX (you take a guess as to what numerals the X's are, Me ... I'm not sure).
  • Reply 418 of 489
    telomartelomar Posts: 1,804member
    [quote]Originally posted by Outsider:

    <strong>According to <a href="http://www-6.ibm.com/jp/chips/forum0/pdf/05.pdf"; target="_blank">this PDF</a> ,the next processor in the 9xx line is due in 2004. It would stand to reason that the 970 is very nearly ready for release in early-spring 2003.</strong><hr></blockquote>



    Well keep in mind that's a planned time. What was more interesting is it had the next evolution of the G3s, which contain altivec and are multicore, as due in 2003.
  • Reply 419 of 489
    bungebunge Posts: 7,329member
    [quote]Originally posted by Telomar:

    <strong>



    Well keep in mind that's a planned time. What was more interesting is it had the next evolution of the G3s, which contain altivec and are multicore, as due in 2003.</strong><hr></blockquote>



    Has this moved out of the realm of speculation?
  • Reply 420 of 489
    brussellbrussell Posts: 9,812member
    Question: On the IBM PowerPC roadmap, there's still this .13, RIO, 1Ghz+ chip with SIMD. Is that the 970? Or is that some revision of the G3 with altivec that people are always talking about.
Sign In or Register to comment.