Re: New GS/new accelerator

[bobryan9@my-deja.com]

I've heard that going from 8k to 32k cache increases the speed
noticeably.  My understanding is that there should be a point where
increasing the cache size starts to degrade performance.  The
accelerator has to write the cache memory to the GS memory sometimes.
Keeping track of, writing, and fetching code from main memory takes
time.

With 8k cache, the accelerator can hold 8k of a program.  This should
work the best with small loops.  If you wrote a program 8k in length,
the entire program would fit in the cache and the accelerator would not
have to fetch other parts of it from main memory.


> What does cache got to do with it?
> Are we talking from experience in designing accelerators or is this
just
> an observation that existing accelerators go faster with a larger
> cache?  I do not mean to be inflamatory, but I was hoping someone who
> knows could explain the technical reasons behind a large cache.
> Besides, I just watched a rerun of "Whose Line Is It Anyway?".  It
makes
> me exagerate my true state of mind.
>


Sent via Deja.com http://www.deja.com/
Before you buy.