Re: Superstitious learning in Computer Architecture

glen herrmannsfeldt wrote:
Note that even CISC doesn't avoid the problem, with specific
optimizations for different models in the x86 family.

Yes, I was just about to point that out.

Of course, it makes sense that optimizations would be different, going
from the microprogrammed 80386 to the cache-and-pipelines Pentium.

Now, though, we seem to have reached the limit. We can't make our CPUs
any bigger or more powerful, we can only put more of them on a chip. So
the only change will be how badly we need to make our algorithms
parallel from now on.

I think there are still a few tricks that a Pentium IV cannot do that
the processors from an SX-6 or a Cray X-1 were able to do, and thus a
*little* more effort should be made in improving the individual CPU.
The Itanium was Intel's attempt to make (some limited aspects of) that
kind of supercomputing available to the masses; there is much about it
I don't like, but I still admire the fact that they made an attempt. No
one else seems about to make a try.

John Savard

.