View Full Version : Re: Intel compiler vs GCC


flip
07-06-2003, 08:58 PM
In article <vggu8r83404u22[at]news.supernews.com>,
"Dan Johnson" <danieljohnson[at]vzavenue.net> wrote:

> "flip" <flippo[at]mac.com> wrote in message
> news:flippo-5D6009.07382806072003[at]news.central.cox.net...
> > In article <vgg12o8m21u880[at]news.supernews.com>,
> > "Dan Johnson" <danieljohnson[at]vzavenue.net> wrote:
> > > Indeed it is not; and the obvious thing for them to do is to take the
> > > SPEC numbers that have already been published for those CPUs.
> >
> > Why is that obvious?
> >
> > When you're doing research, you try to minimize the number of variables.
> > That's what Apple did.
>
> Apple was not doing research, they were doing marketing; they
> did *not* minimize the number of variables; they used different
> GCC builds, different malloc libraries, etc.

But they used the same compiler - which wouldn't be the case if they
used the Intel compiler.

>
> [snip]
> > > But I ask you: are you sure it is Apple's job to make their
> > > competitor's product look worse? :D
> >
> > No. And they didn't.
>
> They certainly seem to have made an effort to depress
> their SPEC scores below the numbers hitherto seen for
> that hardware.

Really? What other SPEC scores can you point to that were obtained with
a cross platform compiler?

Dan Johnson
07-06-2003, 09:49 PM
"flip" <flippo[at]mac.com> wrote in message
news:flippo-641009.14580306072003[at]news.central.cox.net...
> In article <vggu8r83404u22[at]news.supernews.com>,
> "Dan Johnson" <danieljohnson[at]vzavenue.net> wrote:
> > Apple was not doing research, they were doing marketing; they
> > did *not* minimize the number of variables; they used different
> > GCC builds, different malloc libraries, etc.
>
> But they used the same compiler - which wouldn't be the case if they
> used the Intel compiler.

They did not use the same compiler; read the PDF from
veritest's site again.

[snip]
> > They certainly seem to have made an effort to depress
> > their SPEC scores below the numbers hitherto seen for
> > that hardware.
>
> Really? What other SPEC scores can you point to that were obtained with
> a cross platform compiler?

What has that got to do with anything?