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

[Mark Berryman]

On 4/28/23 8:33 AM, Mark Daniel wrote:
> .
 > .
 > .
> This is slightly off the topic of KERNEL mode consumption on X86 but ...
> 
> I have put all three into a ZIP archive at
> 
>     https://wasd.vsm.com.au/other/vups_230428a.zip
>     https://wasd.vsm.com.au/other/vups_230428a.txt
> 
> for anyone who would like to experiment.
> 
> The comparative results across a number of platforms I have access to 
> are as follows (extraneous white-space removed).
 > .
 > .
 > .

Some results from my own systems:

|$ @wasd_vups
|AlphaServer DS15 with 1 CPU and 2048MB running VMS V8.4-2L2
|INFO: Preventing endless loop (10$) on fast CPUs
|Approximate System VUPs Rating : 468.7 ( min: 467.4 max: 470.6 )
|
|$ @migs_vups
|INFO: Preventing endless loop (10$) on fast CPUs
|Approximate System VUPs Rating :  451.2  ( min: 448  max: 452 )
|
|$ @emuvm_vups
|INFO: Preventing endless loop (10$) on fast CPUs
|Approximate System VUPs Rating : 452.0 ( min: 452.0 max: 452.0 )
|
|$ run bogomips_axp
|AlphaServer DS15 1 CPU 2048MB V8.4-2L2
|Calibrating delay loop.. ok - 994.20 BogoMips

|$ @wasd_vups
|HP rx2620 (1.40GHz/6.0MB) with 4 CPU and 6143MB running VMS V8.4-2L3
|INFO: Preventing endless loop (10$) on fast CPUs
|Approximate System VUPs Rating : 488.1 ( min: 487.2 max: 488.8 )
|
|$ @migs_vups
|INFO: Preventing endless loop (10$) on fast CPUs
|Approximate System VUPs Rating :  473.2  ( min: 472  max: 473 )
|
|$ @emuvm_vups
|INFO: Preventing endless loop (10$) on fast CPUs
|Approximate System VUPs Rating : 473.8 ( min: 473.8 max: 473.8 )
|
|$ run bogomips_i64
|HP rx2620  (1.40GHz/6.0MB) 4 CPUs 6143MB V8.4-2L3
|Calibrating delay loop.. ok - 692.73 BogoMips

This next system is a virtual guest of an ESXi host.
The host is a DL380 Gen9 with Intel E5-2660 v3 CPUs at 2.60GHz
|$ @wasd_vups
|VMware, Inc. VMware7,1 with 4 CPU and 16124MB running VMS E9.2-1
|Approximate System VUPs Rating : 509.6 ( min: 496.6 max: 516.2 )
|
|$ @migs_vups
|Approximate System VUPs Rating :  504.2  ( min: 492  max: 508 )
|
|$ @emuvm_vups
|Approximate System VUPs Rating : 503.8 ( min: 486.2 max: 510.4 )
|
|$ run bogomips_x86
|VMware, Inc. VMware7,1 4 CPUs 16124MB E9.2-1
|Calibrating delay loop.. ok - 909.95 BogoMips

It was necessary to compile bogomips /noopt on x86.  Otherwise, the 
delay loop was optimized away.  (For fairness, /noopt was used on the 
other platforms as well).

If I knew what arguments to give to the prime_sieve program, I would 
have included that as well.

Mark Berryman