John Clogg writes:

> Wirt wrote:
>  >What a difference a week can make. Today, IBM broke even those
>  bounds. It
>  >announced plans to start work on a 10,000 MHz processor.
>  ========================================================
>  Wirt, the article you excerpted said IBM had contracted with DOE to build
>  a supercomputer "capable of executing 10 trillion instructions per
>  second".  This is definitely NOT the same thing as a 10,000 MHz
>  processor!  First of all, a machine cycle is undoubtedly longer than one
>  clock pulse.  Secondly, we don't know whether the processor under
>  development will complete one instruction per cycle.  The third salient
>  point is that it is extremely doubtful that the supercomputer being
>  developed is a single-processor machine.

All of what John says is correct -- and I would have written the same thing if
I had read the same posting written by someone else. But the more important
moral yet is that you should never respond to such things on days when you're
so busy that you have to remember to breathe. That level of distraction
doesn't bode well for either accuracy or literacy.

On a more minor nit, overlapped, pipelined, predictive processors have been
evolving for some time now towards a statistical one-instruction-per-clock
pulse (and, of course, there are two clock pulses potentially available in one
Hertz).

Nonetheless, it was an egregious slip of the tongue to call it 10,000 MHz.
Although it certainly may not be evident from my posting, I presumed when I
read the Reuters article that the new machine was to be architected as a
massively parallel machine from the kinds of problems that are being forseen
that it will help solve, and several people later wrote that the machine will
have 8000 subprocessors.

My apologies.

Wirt Atmar