Apple Exec Responds To Benchmarking Controversy

Controversy has reared its boisterous head, especially in the online geek communities, over Appleis claim that the Power Mac G5 is the "fastest personal computer" on the planet. The controversy comes from Appleis testing methods to get benchmarks that support that claim, which some have said were grossly unfair to the Intel world. The company published the testing methods, and Mac and Wintel advocates alike have weighed in on the issue. For more information on this situation, see TMOis full commentary on the subject.

In a somewhat rare move, an Apple executive has commented directly on the subject. In a recent phone interview posted to Slashdot, Appleis Vice President of Hardware Marketing Greg Joswiak claimed that Appleis G5 and P4/Xeon comparisons were designed to be as fair and balanced as possible, disclosing all details in an effort to prove this fact. Joswiak also said that if Apple were trying to be deceptive, releasing all of the test data would be "a silly way to do things."

He goes on to explain Appleis choice of the GCC compiler on both platforms, instead of using more platform-optimized compilers, such as Intelis ICC. According to Joswiak, the Intel-based machines would fare better with the Intel compiler, but the G5 would score higher with another compiler also. Also, according to Mr. Joswiak, Apple chose the options that made the Intel chips look faster, such as running the tests under Linux instead of Windows, and turning hyperthreading off. From the Slashdot article:

He said Veritest used gcc for both platforms, instead of Intelis compiler, simply because the benchmarks measure two things at the same time: compiler, and hardware. To test the hardware alone, you must normalize the compiler out of the equation -- using the same version and similar settings -- and, if anything, Joswiak said, gcc has been available on the Intel platform for a lot longer and is more optimized for Intel than for PowerPC.

He conceded readily that the Dell numbers would be higher with the Intel compiler, but that the Apple numbers could be higher with a different compiler too.

Joswiak added that in the Intel modifications for the tests, they chose the option that provided higher scores for the Intel machine, not lower. The scores were higher under Linux than under Windows, and in the rate test, the scores were higher with hyperthreading disabled than enabled. He also said they would be happy to do the tests on Windows and with hyperthreading enabled, if people wanted it, as it would only make the G5 look better.

More interesting technical information can be found in the article on Slashdot. Greg Joswiak will be presenting the Macworld New York keynote address in July.

No Comments

Log-in to comment