[Info-vax] Some VMS/x86 perf test data from WASD maintainer.

[Jan-Erik Söderholm]

Den 2023-04-30 kl. 13:52, skrev Volker Halle:
> Jan-Erik Söderholm schrieb am Sonntag, 30. April 2023 um 13:15:12 UTC+2:
> 
>> Interesting that these are much more close to each other then
>> on the x86 test.
> 
> DS20Es are physical systems and there is probably less interference than from the VM hypervisor and host OS.
> 
>> I also noted that the WASD version did *not* print the "Preventing
>> endless loop" message on the DS20e, only the MIGS version did...
> 
> I had to add these checks on 'faster' CPUs (Alpha 1 GHz or higher) to prevent endless loops, if the no. of executions of the internal DCL loop were not enough to at least use 10 ms (1 tick) worth of CPUTIM.
> 
>> Interesting that this i5 2.4 GHz laptop gave better numbers then the
>> i5 3.7 GHz system from Volker below...
> 
> the various VUPS results on your i5-1135G7 @2.4 GHz are only about 2,7% higher than on my i5-9600K @3.7 GHz and there are certanly other components involved in this test than just the plain CPU speed.
> 
> I normally use PassMarks to compare CPUs: https://www.cpubenchmark.net/ and the Single thread rating values of your (2710) and my (2759) CPUs are very similar (mine is only rated 1,8% faster). So I find it amazing, that these VUPS values are actually so close ;-)
> 
> Volker.

OK. I might have remembered the "endless loop" message from an
DS25 I once had.

And yes, there are too many "unknowns" to really compare things here...

Anyway, it's up and running, and that is fun enough. Will probably
allocate some unused laptop as the "VMS system".

Have a box of Lantronix ETS8 terminal servers that I was going to
verify/reset, and that is also easier with an VMS system available.

Now, I'm just holding my breath until I have a Cobol compiler to
play with... :-)