[geeks] Intel's new bechmark idea

[James Sharp]

> What's a good general benchmark for comparative performance? All of the
> "old" machines I have read about are quoted in MIPS.

I really don't believe in a "general" benchmark.  Each benchmark should be
application specific.

Sure, you can benchmark an Alphastation 500 and an SGI
Indigo2/R10K/MaxImpact and rate them each in Rendered Polygons Per Second.
But does that help if you're trying to figure out which one would handle
the most database transacations per second?

>
> Also, as PCs progress, I find myself more and more disgusted with them.
> Stupid bus implementations, busses too small or slow, and so on.

They're driven by what the consumer market thinks they want...more
megahertz, mainly.

>
> My ISP (HiWAAY.NET) uses a quad-667 MHz Alpha. That machine is over five
> years old, and still going on strong, despite the fact that the ISP has
> gone from 5,000 users to 21,000 users. Sure, it's had more hard drive
> space added, and some RAM at one point, but it's still doing it's job.
>
> PCs weren't made to do this. And that bothers me to no end [0].

PeeCees suck.  Its as simple as that.