Linked by Stuart MacKenzie on Wed 2nd Jul 2003 18:31 UTC
Apple Are you a long time Windows user curious about the Apple Switch campaign? Are you wondering if you should try it? Read below for my experience with the whole thing... twice. Just over a week ago I purchased a new 12" Apple PowerBook G4...
Permalink for comment
To read all comments associated with this story, please click here.
Re: The Pessimist
by Anonymous on Thu 3rd Jul 2003 18:00 UTC

"No Troll. There's a resonable doubt, like it or not."

If there is, nobody has made a worthy case for it.

"I still wait for REAL NUMBERS, using Intel compiler for Intel plateforme"

OHHHHH... is THAT what you're talking about. THAT'S why you're assuming that the benchmarks were skewed. now i understand where you're coming from.

Hopefully, this clarifies things a bit for you. Veritest used gcc for both platforms, instead of Intel's 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.

Keep in mind that gcc has been available on the Intel platform for a lot longer and is more optimized for Intel than for PowerPC. However, you are correct, the Dell numbers would be higher with the Intel compiler, but that the Apple numbers could be higher with a different compiler too.

The point is, if you're going to test SPEC benchmarks, you need to use similar compilers. Otherwise, all your testing is which hardware is best optomized to pump out numbers for that particular compiler.

The reason why Intel has help SPEC benchmarks so high is because their compiler was written SOLELY for the purpose of increasing SPEC numbers.

This is why its important to compare real world benchmarks alongside SPEC numbers... Because SPEC numbers kindof give you a false sense of speed. When SPEC benchmarks were tested, the G5 did better but only margionally so in most tests. In real world tests, the G5 BLASTED past the P4. However, it only did slightly better than they XEON.

"There's a doubt. You choose to believe them. I choose to not. Big deal."

I didn't believe "him" as if it was Steve jobs making the benchmarks. Rather, I believe the independent research study, the SPEC benchmarks and the real world benchmarks. Why you cling to some notion that the P4 did better despite these fact I don't know.

"Not everybody is in your religion. Deal with it."

What does Christianity have to do with my passion for computers?