[Info-vax] Unix on A DEC Vax?

[John Wallace]

On Jan 18, 5:04 pm, "Stanley F. Quayle" <stanley.f.qua... at gmail.com>
wrote:
> > My cell phone probably has significantly more computing power and far more memory and storage than this "minicomputer",
>
> I have SIMH on my Android phone.  Fun to work with, but not really practical -- it doesn't access the WIFI network interface.  If it did, it could be useful, sort of.
>
> > And the time needed to run a particular CPU test on an emulator will always reveal that it is slower than running native code on the host CPU.
>
> Would you expect an emulator to test as *faster* than native code?
>
> > Having seen the speed of shadow copies under SimH and the free Alpha
>
> emulators the improved disk speeds are no surprise.  Is the full backup
> time for CHARON-VAX quoted on your web page to tape or disk?
>
> As I recall, he's backing up to virtual tape.  That becomes a file in Windows, which is then archived to storage elsewhere using standard Windows tools.
>
> > eat a CPU
>
> True, emulating a different processor is a full-time job.  CHARON comes with a "slowdown" kernel widget that stops the interpreter when the emulated CPU is idle.  I've read discussions about SIMH doing the same thing, although I don't know if it ever came to pass.

"Would you expect an emulator to test as *faster* than native code? "

Who can say, with a question as non-specific as that? An Alpha
emulator on a modern x86 being faster than an Alpha Multia might not
be unreasonable to expect. How would one find out?

I would hope that reputable suppliers would ask more specific
questions than the one you just asked, and that some of the better
suppliers might even offer quantifiable benchmarks (formal or
informal) for specific workloads in given configurations, so that
potential customers could consider performance before making a
decision as to whether to even investigate further.

But my hopes are not always realised.