Slashdot Mirror


Intel Mac Performance Behind Hype

Barry Norton writes "Steve Jobs, at the MacWorld tradeshow, boasted: 'the new iMac [with] Intel processor is two to three times faster than the iMac G5.' MacWorld (the publication) has been putting the iMacs through their paces. The results are a good deal less impressive than Steve's boast, showing an average performance increase of 10 to 25 per cent while performing a series of everyday tasks with software specially designed for the new systems." Ars Technica had another perspective on the new systems earlier this week.

4 of 444 comments (clear)

  1. Re:Newsflash! by the_humeister · · Score: 0, Redundant

    No, but it is rather misleading. On the other hand, I doubt most prospective buyers would believe what he said either.

  2. mod STORY down, it's both a dupe and a troll. by javaxman · · Score: 0, Redundant
    We had a story on the exact same subject just days ago, and the vast majority of the ( informed ) posts pointed out that *in the keynote* Steve Jobs said that the new machine is 2-3 times faster *using the specINT benchmark*, and that other parts of the system were identical to the G5 iMac. Ignoring that qualification, while focusing on the 2-3 times statement, is simply dishonest... i.e. it's something you wouldn't ignore unless doing so made your story more sensational.

    Funny, most of the posts on this story make exactly that point. Crap stories like this remove a lot of the value from reading slashdot. Maybe I'll start looking for my "stuff that matters" elsewhere.

    I'm going to encourage everyone to start replying to crap stories with "mod STORY down" comments. I've had enough. If we all start doing this, I can quickly check the comments for a long list of 0-moderated "mod STORY down" comments and just skip the story. We'd be doing each other a favor. The 'editors' are going to kill slashdot with this kind of crap. Surely there's some actual news, or even some interesting tech-related web page to look at somewhere, instead of this rehashed garbage?

    Of all the people who have submitted stories, there has to be *one* that isn't a dupe, right?

    Or should I cynically assume that this story ( and others ) are duplicated based on the number of posts/pageviews they generate ?

  3. Re:Newsflash! by scribbla · · Score: 0, Redundant

    Apple's hype is over the top. The Apple home page: "2x faster. Twice as amazing." Yet in real world applications, speeds are much less.

  4. Re:Newsflash! by BerntB · · Score: 0, Redundant
    Apple, on the other hand, is notorious for being overly optimistic in their speed comparisons - They always pick the benchmark which will make the competition look as bad as possible
    This brings back bad memories when I was trying to reason with the most dishonest troll (Swedish) I've even heard of. He probably printed the netiquette on his toilet papers; quoting emails, fragrant lying, lying about things in email(!), canceling of posts (I don't know if he used to repost falsified ones, though). Etc, etc.

    I don't disagree with your points on Apple marketing speech regarding processor speeds. They are as bad as Intel and SPEC marks, but that is with the processor maker. If you would design a test to cheat on it, here is how you'd do it:

    • Take an old, respected test used to compare standard systems, not processors
    • Join the organization releasing the tests and put lots of money into it, so you can both influence the choices and see coming test versions early (needed for the rest of the steps)
    • Specially build test systems with faster memory architectures than any standard chipset supports (the SPEC said that you had to be able to buy the systems; let some people write that they had 'em!)
    • Specially write a compiler that literally generates hand optimized code for the specific test cases in the SPEC suite; have a ok compiler added to it for any other use
    • Make certain the test code isn't released unless people pays too much money for individuals (otherwise the previous steps are quite meaningless)
    • Publish the test figures everywhere and make certain journo's mention them as gospel

    I haven't trusted the computer press since. Big advertisers can do anything and smell like roses.

    Disclaimer: It was quite a while ago so details on the SPEC might be wrong -- and I don't know anything about the last 6-7 years.

    (-: Full disclosure of my loves and hates to verify veracity: PCs I buy are strictly AMD since I read up on SPEC. I like Macs, Debian and Emacs. Vi and RPM are bad. I think about moving to BSD. Microsoft is criminal (sorry, that was a verdict, not opinion). :-)

    --
    Karma: Excellent (My Karma? I wish...:-( )