Text 9365, 64 rader
Skriven 2006-01-23 11:59:34 av Rich Gauszka (1:379/45)
   Kommentar till text 9363 av RobertB. (1:379/45)
Ärende: Re: apple skews the benchmarks
======================================
From: "Rich Gauszka" <gauszka@hotmail.com>

"RobertB." <rb28@nyu.edu> wrote in message
news:rb28-538F4C.10492423012006@w3.nls.net...
>I don't have the results in front of me, but didn't they run the new
> dual-core machines against dual-processor G5s? There were third-party
> ratings that did just that, but using real-world applications.
>
> robert
>
> In article <43c558f7@w3.nls.net>, "Rich Gauszka" <gauszka@hotmail.com>
> wrote:
>
>> Jobs does a job on the performance advantage?
>>
>> http://weblog.infoworld.com/enterprisemac/archives/2006/01/the_mac_perform.h
tm
>> l
>>
>> Apple has bought itself another controversy, and once again, needlessly.
>> It's not exactly a dark cloud over the announcements of its new machines,
>> but it'll be a topic of conversation here and elsewhere, and an issue for
>> which Apple will have to answer.
>>
>> In short, Apple used multiprocessor benchmarks to skew the performance
>> advantage that its Intel-based machines enjoy compared to single-core
>> PowerPC G4 and G5. Apple used the industry-standard SPEC suite components
>> SPECint2000 and SPECfp2000, but here's the catch: Apple used
>> SPECint_rate2000 and SPECfp_rate2000. Both tests spawn multiple parallel
>> benchmark processes and are specifically intended for comparing
>> multiprocessor systems. Single CPU, or single-core machines do positively
>> lousy on SPEC*_rate2000 tests. That's predictable and universally
>> understood. Add a second CPU or a second core and, as you would expect,
>> SPEC*_rate2000 performance on any multiprocessor-optimized test
>> skyrockets
>> compared to a single-processor box.
>>

I just saw the IMac, PowerBook/MacBook results that Jobs dished out at the
intro. I was hoping that Apple would announce an Intel based Mac-Mini  at the
time

Many of the real world application tests will have to wait for native apps. It
really isn't fair to Apple to do any benchmarks of Rosetta ported apps

http://macdailynews.com/index.php/weblog/comments/8310/

"Our Mac tests focus exclusively on multimedia performance, so for
less-demanding programs such as Microsoft Office, the nonnative performance
picture might not be as dire. But if you want to run Photoshop or a nonnative
video-editing program such as Sorenson Squeeze, we highly recommend you wait
until the software catches up before purchasing a new iMac Core Duo. On
Photoshop, the iMac Core Duo was 81 percent slower than the iMac G5, taking 6
minutes, 30 seconds to run our photo script compared to the iMac G5's 3-minute,
36-second time. The Sorenson scores were even worse, to the tune of a whopping
463 percent difference. The iMac G5 took 5 minutes, 11 seconds to complete our
test. The iMac Core Duo? An unacceptable 24 minutes," Brown writes. "If you
find those nonnative scores alarming, you're not alone. But you can take heart
in the fact that some third-party programs--Quark, for example--have already
been ported over to the so-called universal binary that will run on both
Intel-powered and older PowerPC-based Macs...

--- BBBS/NT v4.01 Flag-5
 * Origin: Barktopia BBS Site http://HarborWebs.com:8081 (1:379/45)