It's a few years since I was down in these weeds, but I remember someone
saying these days, data access time is more important than CPU speed.

I remember working on a product that many TCBs could access concurrently.
We had a Compare and Swap on the "next trace entry" field.
This was a killer, because the data was sometimes in the same CPU (so
within millimeters), and sometimes it was in a different book - so 1 meter
away ( speed of light 3 nano seconds for this time)
We replaced the common trace buffer with a trace table buffer per TCB, and
got a big boost in performance.  The trace buffer was nearly always in the
CPU cache so fast access time.

Colin


On Wed, 16 Apr 2025 at 15:51, Mike Schwab <
[email protected]> wrote:

> 5.5GHz is a 2 inch 5 cm signal.  10 GHz would require a signal length of 1
> inch 2.5 cm.
>
> On Wed, Apr 16, 2025 at 8:31 AM Steve Beaver <
> [email protected]> wrote:
>
> > We all know the z17 has been announced.
> >
> >
> >
> > What I am disappointed in is the CP's have not gone faster than 5.5 Ghz.
> >
> > I know the z17 is an evolution, but why have they not gotten faster?
> >
> >
> >
> > Steve
> >
> >
> > ----------------------------------------------------------------------
> > For IBM-MAIN subscribe / signoff / archive access instructions,
> > send email to [email protected] with the message: INFO IBM-MAIN
> >
>
>
> --
> Mike A Schwab, Springfield IL USA
> Where do Forest Rangers go to get away from it all?
>
> ----------------------------------------------------------------------
> For IBM-MAIN subscribe / signoff / archive access instructions,
> send email to [email protected] with the message: INFO IBM-MAIN
>

----------------------------------------------------------------------
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to [email protected] with the message: INFO IBM-MAIN

Reply via email to