On Oct 2, 10:02=A0am, chrisv <chr...@[EMAIL PROTECTED]
> wrote:
> Robert Myers wrote:
>
> >You're stuck in a mental rut. =A0Who cares if PC's go 50% faster? =A0
>
> It's price/performance that is the "bottom line". =A0So, "who cares" if
> Intel has no serious competition, so are allowed to feed us
> overpriced, mediocre products? =A0
>
> We care. =A0The world cares. =A0Sheesh.
>
In reality it matters to hardly anyone. Those who really need muscle
have only one way to go, which is multiple cores. In that case, 50%
more cores isn't all that different from 50% better performance from a
single core.
> >The problems are elsewhere. =A0
>
> What "problems" are you referring to? =A0The "problems" you find
> technically interesting, or the "problems" the real world faces,
> trying to get the job done in the most efficient manner?
>
The real problems have very little to do with hardware. The hardware
that has evolved simply enables the bad habits of the world of
computer software.
> >So, no, your insight doesn't impress me.
> >Even were Itanium and NetBurst the worse architectures, we'd be making
> >more fundamental progress by continuing to struggle with the problems
> >they create.
>
> Says you. =A0That's absurd, says me.
>
> For a few academics, the challenge of making a k00l-enough compiler to
> make IA64 kick ass may be very interesting. =A0Meanwhile, the hundreds
> of millions of PC users are making *real* progress with great products
> like the C2D. =A0
>
> You might say "maybe in the long run we'd be better-off with the kool
> compiler technology". =A0I would respond "maybe not". =A0Maybe it's a
> complete dead-end, like Netburst (which, in hindsight, was a *really*
> bad idea). =A0Maybe, when CPU's with 64 cores are being made, IA64 will
> look to be similarly wrong-headed.
>
The only thing you can say about Itanium at this point is that it
didn't work the way it was expected to. We'll probably never really
understand why. There was more than one dead-end in the pursuit of
the ideas around Itanium. If you never encounter dead-ends though, I
say it means you are not being sufficiently adventurous.
The chief architect for P4 has said that he expected to backfill the
original design into something more respectable but that, yes, it was
rushed out only to get the clock rate up. For some really fundamental
reasons, running much faster to get the same or only slightly better
performance seems on the face of it to be a really, really dumb thing
to do, except possibly from the POV of selling chips, at least in the
short haul.
Better compiler technology is not a dead end.
Robert.
|
