Slashdot Mirror


Dvorak Thinks Apple Will Switch to Intel

SeanTobin was among several users who noted that Dvorak's latest column discusses the possibility of Apple going to Intel for future macs. Yeah, this rumor pops up pretty often, but I wonder how long before we'd get binary compatibility between other x86 unix OSs.

13 of 419 comments (clear)

  1. Why does anyone listen to Dvorak? by Anonymous Coward · · Score: 5, Insightful

    He's an idiot!

    1. Re:Why does anyone listen to Dvorak? by Rick+the+Red · · Score: 5, Insightful

      No shit. First Cringly, now Dvorak. Why is Slashdot becomming the front man for all the loser know-nothings with a column? If there isn't anything better to post than "Cringly said this" and "Dvorak said that", then don't post. This is supposed to be news for nerds, not blathering for nerds.

      --
      If all this should have a reason, we would be the last to know.
    2. Re:Why does anyone listen to Dvorak? by Midnight+Thunder · · Score: 5, Insightful

      Look on the bright side, now that the 'nerd' community is aware that Dvorak has said something stupid again, we now know where management is getting its facts from. This allows us to be wise and explain to management in simple terms that Dvork is on crack again and why what he proposes is unlikely to happen.

      --
      Jumpstart the tartan drive.
  2. Dvorak always does this. by Anonymous Coward · · Score: 5, Insightful

    Takes something with a shred of truth (the people being at said conferences) and blowing it into something "newsworthy".

    1. Re:Dvorak always does this. by Anonymous Coward · · Score: 5, Insightful

      Dvorak has never been right. He has a past history of ranting incoherently, throwing a few opinions he knows is going to press some buttons to get a little extra readership, before simply jumping across to another topic to do more of the same.

      Reporting on the opinions of my retarded neighbour who collects roadkill and has an IQ somewhere under 70 would be just as accurate as Dvorak's rants.

  3. x86? by RebelWebmaster · · Score: 5, Insightful

    For one thing, Dvorak thinks Apple will use Itanium. Not exactly binary compatible with other x86 unices...

  4. No mention of IBM? by tbmoore · · Score: 5, Insightful

    There's no mention of Apple's most likely upgrade path in the next 12-18 months, the IBM PPC 970. Uh... hello?

  5. Strange, but... by koh · · Score: 5, Insightful

    You can tell high-level languages are the standard when someone proposes to switch a whole architecture to the x86 platform.

    Remember the times the x86 was pointed at because of its lack of registers ? Recently read an pentium to-the-metal optimization guide, and discovered you had to recode your optimizations backwards to port them from p3 to p4 ?

    I can't possibly understand how a switch to intel processors can possibly benefit Apple...

    --
    Karma cannot be described by words alone.
  6. An "Intel" arch, but not x86 by popular · · Score: 5, Insightful

    Dvorak is suggesting that Apple will switch to Itanium, which according to the roadmaps is nowhere near being ready for the desktop. At present, Intel is jamming larger and larger caches into Itanic until it will float against other processors in the server space, giving it an otherworldly transistor count not ready for the desktop in THIS decade -- the fabrication is simply too complex (read: $$$$), the power requirements are through the roof, and the compiler technology for IA-64 is many years from maturity. The Merced core for Itanic is absolutely useless, and I won't even get into the questions about whether even future generations will be viable.

    A better 64 bit choice, particularly for Apple, will be IBM's upcoming PPC 970, which doesn't require massive retooling.

  7. Possible, but not to a PC architechture by Psykechan · · Score: 5, Insightful

    This wouldn't be the first time that the Mac has changed processors. (680x0 -> PPC) It's unlikely that Apple would keep the crappy PC style architechture though. Take a look at the base 1 MB and the terrible interrupt controller cascade. Apple wouldn't want to inherit this, plus if they stay far enough outside the PC, they can maintain their individuality.

    I can picture geeks buying x86Mac hardware to run Linux on as it should be more stable than current x86 hardware. I can also picture x86 virtualization software (VirtualPC) being useful. Apple no longer has to deal with the low clock speed stigma.

    This sounds like it would be a good thing.

  8. Speed 'gain' by TheRaven64 · · Score: 5, Insightful
    He makes the point that switching to to Itanium would give speed gains, and that Apple have managed to switch from 6502 to 68k (Apple II to Mac, but I don't remember the Mac being Apple II compatible), then again to PPC. The PPC shipped with a code translator which made the old 68K apps run slowly, but the speed gains in the PPC made them catch up quickly. If they switched to Itanium, then they would have to do this again. The OS is portable, so that could probably be 100% native (early PPC versions ran some portions of the OS in the 68k emulator), as could most of the bundled apps. Then, people would have to either use a slow (emulated) version of their software, or buy a new version.

    He makes a point that they could release a dual CPU machine with an Itanium and a PPC chip, but this would be slower than a single CPU model for most things (dual CPU where each CPU is a different architecture is tricky and leads to performance hits). Since all Apple's current top of the line models have 2 PPCs, the new machine would be slower than the old ones.

    On the other hand, the PPC 970 is comming into production, a 64-bit PPC with 2GHz+ clock speeds. 64 is twice as big as 32, so marketing can claim it's as fast as a 4GHz Pentium 4 (actually it might be almost that fast, since the P4 is famous for high clock rates and low performance per clock). Being a PPC, this chip is also backwards comaptible. Oh, and it has 2 AltiVec units, so all that AltiVec code Apple has been pushing for the last couple of years should really sing. A 900MHz FSB reduces the old memory bottleneck present in current PPCs. I'm not sure how much the PPC970 will cost, but I doubt it will be much more than Itanium, and it's far more attractive from Apple's point of view. This Dvorak guy seems to have forgotten that the Apple IBM Motorola alliance had 3 members...

    --
    I am TheRaven on Soylent News
  9. And we believe him? by 00_NOP · · Score: 5, Insightful

    I have a book here called "Dvorak predicts" from 1994 which states inter alia 'Apple will die if it merges', 'Apple needs to make a run-time Mac', 'the real Unix operating system is an archaic command line', 'Unix has no advantage except it's easy to program', 'Unix is old fashioned in its design and OS/2 or Windows NT architectures are the wave of the future'.

    Correct me if I am wrong, but Apple merged and did not die, there is no rt mac archiecture available (excepting some good hacks that no one would use for business critical processes), unix based servers dominate the internet and MS are scared stiff that an old fashioned unix-like os is going to fillet their business.

    Mr Dvorak is as entitled as anyone else to make his predictions, but that doesn't mean he is any good at it.

  10. Backwards compatibility by ccmay · · Score: 5, Insightful
    Apple has also cultivated a fanatical following, who have long since accepted the fact that Apple eschews long-term backward compatibility.

    This is the most ridiculous thing in the whole article. Obviously he has forgotten the 68k emulator after the PowerPC changeover, as well as the Classic environment on OS X, both of which have worked perfectly in my experience.

    Furthermore, I think there is a higher proportion of old Apple machines still running than equivalent old PC's. I saw an SE/30 doing a fine job as a mail server not that long ago. How many people are still using 286/386 vintage stuff?

    -ccm

    --
    Too much Law; not enough Order.