Speed of Apple Intel dev systems impress developers

Posted:
in Future Apple Hardware edited January 2014
The speed of Mac OS X running on Intel hardware is impressing some developers who've been privy to one of Apple's first Intel-based developer transition systems.



The systems started shipping to Mac OS X developers three weeks ago, each equipped with a 3.6 GHz Intel Pentium 4 processor with 2 MB L2 Cache, 800MHz front-side bus, 1GB of 533MHz DDR2 Dual Channel SDRAM, and an Intel Graphics Media Accelerator 900.



Developers are renting the $999 hardware from Apple for a period of 18 months in order to get a head start in porting their applications to run on the Intel version of Mac OS X.



"It's fast," said one developer source of Mac OS X running on Intel's Pentium processors. "Faster than [Mac OS X] on my Dual 2GHz Power Mac G5." In addition to booting Windows XP at blazing speeds, the included version of Mac OS X for Intel takes "as little as 10 seconds" to boot to the Desktop from when the Apple logo first displays on screen.



Included with the Mac OS X for Intel distribution is an Applications folder stocked with a mixture of PowerPC and Intel-native applications. Applications that are compiled only for PowerPC processors are of filetype "Application (PowerPC)" whereas Intel-native binaries are labeled of standard type "Application".



Developers sources say the early version of Rosetta, a dynamic binary translator that is designed to run unaltered PowerPC applications on Intel Macs, is also impressive. "Rosetta is completely 100 percent seamless and nothing like the Classic environment used to run older Mac OS 8 and 9 applications under Mac OS X," one source told AppleInsider.



"With the exception of the "PowerPC" denotation and the presence of "Open in Rosetta" checkbox in the application info boxes, you can't tell which applications are universal and which are PowerPC-only unless you examine package contents," the source explained.



Since the developer version of Mac OS X for Intel offers users the option of running any application under Rosetta, developers have been able to perform rudimentary speed comparisons between native Intel Mac applications and those that must first filter through the Rosetta binary translator.



"Taking a universal binary and timing its startup in Intel native speed versus its startup when opened via Rosetta results in a slowdown, but not as much as one would think," said another source. "The apps run at about 65 to 70 percent of their normal speed."



However, some PowerPC-native applications realize little to no speed reductions while running under Rosetta. A source told AppleInsider the current PowerPC version of the popular Firefox web browser loads just as fast under Mac OS X Intel as it does on a high-end dual processor Power Mac G5.



If reports are accurate, Mac users have a lot to look forward to in regards to web browsing under Mac OS X for Intel. According to sources, web browsing in general is much faster under Mac OS X for Intel than it is under the shipping version of Mac OS X for PowerPC. Web pages snap to the screen, the same way they do in Internet Explorer running on a new Pentium system, they say.



The first Mac systems to sport Intel processors are expected to hit the market around the middle of next year according to statements made by Apple, though recent mumblings indicate that the company may be striving to beat those estimates by several months.
«134567

Comments

  • Reply 1 of 133
    mimacmimac Posts: 872member
    All very good news indeed, although trouble is brewing.
  • Reply 2 of 133
    boogabooga Posts: 1,082member
    Quote:

    Originally posted by MiMac

    All very good news indeed, although trouble is brewing.



    That's no trouble as long as you're not using AMD
  • Reply 3 of 133
    mimacmimac Posts: 872member
    Quote:

    Originally posted by Booga

    That's no trouble as long as you're not using AMD



    Yes...for now, though who can say what might happen if Apple decide they'd like an AMD processor in the future?
  • Reply 4 of 133
    hmurchisonhmurchison Posts: 12,425member
    harumphfff "Megahertz Myth huh"
  • Reply 5 of 133
    So I guess the apparent speed of the developer machines is a good sign for those of us waiting to buy a new Intel PowerMac when they finally make it to the scene (as I've read, they'll be the last to be updated to the Intel platform.... <sigh>). \
  • Reply 6 of 133
    existenceexistence Posts: 991member
    Quote:

    Originally posted by baranovich

    So I guess the apparent speed of the developer machines is a good sign for those of us waiting to buy a new Intel PowerMac when they finally make it to the scene (as I've read, they'll be the last to be updated to the Intel platform.... <sigh>). \



    Don't worry...buy a Yonah Powerbook instead! For most things, a dualcore Yonah PowerBook should outrun Apple's quad-PPC PowerMacs. It will be the first time in 7 years that PowerBooks are faster than PowerMacs.
  • Reply 7 of 133
    melgrossmelgross Posts: 33,510member
    Quote:

    Originally posted by hmurchison

    harumphfff "Megahertz Myth huh"



    Uh oh, you're turning red again. You better stay away from those enchilada's
  • Reply 8 of 133
    hmurchisonhmurchison Posts: 12,425member
    Well if this is actually truth and not the MacScoobydoo type of hyperbole then that bodes well for OS X Leopard performance on a Conroe chip in 2007.



    Count me in ..hopefully.
  • Reply 9 of 133
    Quote:

    Originally posted by Existence

    Don't worry...buy a Yonah Powerbook instead! For most things, a dualcore Yonah PowerBook should outrun Apple's quad-PPC PowerMacs. It will be the first time in 7 years that PowerBooks are faster than PowerMacs.



    Thats great and all, but if they have these super Yonah powered PowerBooks wouldn't it make sense for Apple to make some really BEEFY PowerMacs to compete and/or surpass them? For that, I'm willing to bite my lip and wait.
  • Reply 10 of 133
    macgregormacgregor Posts: 1,434member
    I would rather see a survey of multiple developers with specific descriptions, than a couple of anecdotes from a couple of sources. How many dev Mactels are there and how do they all feel about the speed? How difficult is that to find out? I want real journalistic research....well...we haven't seen that in a few years politically so I guess I shouldn't expect too much.
  • Reply 11 of 133
    Very good news indeed... I am looking forward to my laptop upgrade in late '06 early '07 - though I have to say, currently my 1.25Ghz 15" is singing along under 10.4.2 for most things.



    Where I would like to see some comparisons between the two architrectures is under loads like video compression/ effects - ie Final Cut/ Shake etc, where the optimisation on Altivec vs optimisation on SSE2/3 will be shown. This is the balance of the platform for me.
  • Reply 12 of 133
    melgrossmelgross Posts: 33,510member
    I wonder how it would compare to the new Firefox 1.0.5 G5 optimized build.



    This is one of the biggest problems we've had with the performance over the years. too many developers stick with the lowest common denominator. These days that's the G3. So a G4 or G5 doesn't give impressive speedups on many (most?) programs.



    When Apple optimized FCP for the G5 I noticed a hugh improvement in rendering times, as well as improvements in interface speeds.



    I can tell you from my own long experience as a Photoshop beta tester that Adobe has several generations of filters etc in the product.
  • Reply 13 of 133
    gerardjgerardj Posts: 15member
    That article seems to take a whole lot of words to tell me nothing new. I'm still waiting for some real comparisons.



    The Intel system is "Faster than [Mac OS X] on my Dual 2GHz Power Mac G5." says one developer. Stating that Mac OS X boots from Apple screen to desktop in 10 seconds. While that is an impressive number, he's not exactly comparing top-of-the-line systems. A dual 2.7 PowerMac boots pretty damned fast across the same points. The bottleneck here isn't the processor in most cases, but the hard drive's ability to get data to the logic board. MY guess is the devel systems are using 10,000 RPM high-end drives instead of the large slow drives in the G5 systems.



    Rosetta is seamless and causes apps to run slightly slower. We knew that already; Steve told us.



    "Web pages snap to the screen..." Did Apple by chance make a popular hack for Safari the default on the Intel system? Safari usually waits for most of a page's elements to be identified and sized before it displays a page. Lower that delay value on a G5 also makes web pages "snap to the screen"



    What's missing from this report: anything remotely resembling a benchmark!



    WHAT apps are native? Are iMovie and iDVD on the list? Complete a project on both platforms and compare the rendering and encoding/multiplexing steps.

    Is Mathmatica one of them? Run the same simulation on both platforms and test the differences.



    I keep hearing all this warm fuzzy stuff telling me that Intel seems as fast or faster than a dual 2.7, but no-one has produced any numbers to cement that claim to being fact.



    Sorry, I just have a REALLY hard time seeing how a G5 with faster/wider bus, AltiVec and dual processors is not just going to run circles around a single P4 in any type of serious data crunching test.
  • Reply 14 of 133
    skatmanskatman Posts: 609member
    I'm curious if OSX for Intel supports hyperthreading?
  • Reply 15 of 133
    kcmackcmac Posts: 1,051member
    Quote:

    Originally posted by hmurchison

    harumphfff "Megahertz Myth huh"



    Wasn't Ave Tevanian (spelling?) always the guy kind of driving that ship? How long ago was he moved to a different position with Apple? Did it correspond with this secret life Apple has been living with Intel? Now it is appearing that OS X might have really been held back by everything up to now? Hmmmm.



    The speed thing sounds good none the less. Looking forward to it.
  • Reply 16 of 133
    o4blackwrxo4blackwrx Posts: 383member
    Quote:

    Originally posted by melgross

    I wonder how it would compare to the new Firefox 1.0.5 G5 optimized build.



    This is one of the biggest problems we've had with the performance over the years. too many developers stick with the lowest common denominator. These days that's the G3. So a G4 or G5 doesn't give impressive speedups on many (most?) programs.



    When Apple optimized FCP for the G5 I noticed a hugh improvement in rendering times, as well as improvements in interface speeds.



    I can tell you from my own long experience as a Photoshop beta tester that Adobe has several generations of filters etc in the product.






    I totally agree, where are the other "optimized for G5" applications out there?? Apple sure hasn't even made an effort to do it with most of their applications. Tiger should've come in 2 versions. 64-bit and 32-bit along with being optimized for Dual Processors. Apple is going to make the Intel look amazing with over 5 years of R&D into it. I feel like I have been cheated by spending $3,200 on a G5 that was suppose to be the "next big thing" when in reality Apple hasn't put forth effort into making it the beast it could be.
  • Reply 17 of 133
    vasvas Posts: 16member
    Hey, what about some comparisons of Windows XP and Mac OS X Tiger on the exact same hardware? Will OS X be smoked compared to Windows or not?
  • Reply 18 of 133
    baranovichbaranovich Posts: 184member
    Quote:

    Originally posted by vas

    Hey, what about some comparisons of Windows XP and Mac OS X Tiger on the exact same hardware? Will OS X be smoked compared to Windows or not?



    Yeah I'm VERY curious too...
  • Reply 19 of 133
    big macbig mac Posts: 480member
    Quote:

    Originally posted by Gerardj "Web pages snap to the screen..." Did Apple by chance make a popular hack for Safari the default on the Intel system? Safari usually waits for most of a page's elements to be identified and sized before it displays a page. Lower that delay value on a G5 also makes web pages "snap to the screen"



    That particular comment makes little sense. It's not like Safari pegs the Mac's CPU(s), so there's absolutely no way that could ever be a valid benchmark of microprocessor performance.
  • Reply 20 of 133
    rnskrnsk Posts: 35member
    The reason no one is telling you guys the kind of specific info you are looking for is because they really, really can't.



    Its not because they don't *know* mind you...its because, well, Apple said so.



    What you are reading here however is "fairly accurate". I would not say its "anecdotal" or "a couple of developers".



    I don't believe anyone who has or is developing on the x86 version of OS X right now would disagree with the statements made in this piece.



    They wouldn't get...specific tho. Publishing benchmarks is strictly and explicitly forbidden.



    I think in fact the only folks that don't/won't/can't believe it are those with too vested an interest in "Intel hate".
Sign In or Register to comment.