From: bill@triangle.cs.uofs.edu on behalf of Bill Gunshannon
[bill@cs.uofs.edu]
Sent: Tuesday, August 23, 2005 9:06 PM
To: Info-VAX@Mvb.Saic.Com
Subject: Re: Simh. How to triple the speed

In article <q%OOe.34046$Il.13353@fe2.news.blueyonder.co.uk>,
	Alan Greig <greigaln@netscape.net> writes:
> 
> 
> Dan Foster wrote:
> 
>> 
>> That's not bad. SIMH emulates the MicroVAX 3900, which has a VUPS rating
>> of 3.8.
> 
>> Mr. Quayle, a CHARON reseller, mentioned it was ~95 VUPS on a 'high end
>> PC' (making me think 3 GHz Xeon or some such) for CHARON, last year.
> 
> I've just tried the demo of Charon VAX (I know there may be faster 
> Charon products so take this as indicitive of the demo only as per the 
> agreement I clicked on)and it gets 11 VUPS on my PC. Simh gets me 7.8
> so there is obviously some scope for speeding up simh. But simh is a 
> free emulator which doesn't have full time staff and commercial funded 
> development. I think simh does rather well. I'd be amazed if anyone is 
> getting 95 VUPS out of Charon VAX unless it's a cluster emulated on an 
> SMP system. And you can do that with simh has well. Simh also emulates a 
> huge range of proecssors other than VAX of course.
> 
>> 
>> Could you make the DCL scripts available or mention more details such
>> that I could locate them via a web search? I think I've heard of the
>> ones you used but can't remember enough useful details to find them again.
> 
> Watch as it may wrap.
> 
> $! CALCULATE_VUPS:
> $!
> $ set noon
> $ orig_privs        = f$setprv("ALTPRI")
> $ process_priority  = f$getjpi(0,"PRIB")
> $ cpu_multiplier    = 10                        ! VAX = 10 - Alpha/AXP = 40
> $ cpu_round_add     =  1                        ! VAX =  1 - Alpha/AXP =  9
> $ cpu_round_divide  = cpu_round_add + 1
> $ init_counter      = cpu_multiplier * 525
> $ init_loop_maximum = 205
> $ start_cputime     = f$getjpi(0,"CPUTIM")
> $ loop_index        = 0
> $ 10$:
> $     loop_index = loop_index + 1
> $     if loop_index .ne. init_loop_maximum then goto 10$
> $ end_cputime  = f$getjpi(0,"CPUTIM")
> $ init_vups    = ((init_counter / (end_cputime - start_cputime) + -
>                     cpu_round_add) / cpu_round_divide) * cpu_round_divide
> $ loop_maximum = (init_vups * init_loop_maximum) / 10
> $ base_counter = (init_counter * init_vups) / 10
> $ vups         = 0
> $ times_through_loop = 0
> $ 20$:
> $    start_cputime = f$getjpi(0,"CPUTIM")
> $    loop_index = 0
> $    30$:
> $        loop_index = loop_index + 1
> $        if loop_index .ne. loop_maximum then goto 30$
> $    end_cputime = f$getjpi(0,"CPUTIM")
> $    new_vups = ((base_counter / (end_cputime - start_cputime) + -
>                    cpu_round_add) / cpu_round_divide) * cpu_round_divide
> $    if  new_vups .eq. vups then goto 40$
> $    vups = new_vups
> $    times_through_loop = times_through_loop + 1
> $ if times_through_loop .le. 5 then goto 20$
> $ 40$:
> $ new_privs = f$setprv(orig_privs)
> $ set message /nofacility/noidentification/noseverity/notext
> $! ASSIGN/SYSTEM/EXEC  'vups'  MACHINE_VUPS_RATING
> $ set message /facility/identification/severity/text
> $ write sys$output "Approximate System VUPs Rating :  ", -
>                     vups / 10,".", vups - ((vups / 10) * 10)
> $ exit
> $
> 
> 
>> I'd be happy to try it on SIMH+VMS 7.3 setup running on a P4/3.0 GHz and
>> report back results.
>> 

I couldn't resist.  I ran it on the VAX here. 

Approximate System VUPs Rating :  28.0

That should keep the students happy.

bill

-- 
Bill Gunshannon          |  de-moc-ra-cy (di mok' ra see) n.  Three wolves
bill@cs.scranton.edu     |  and a sheep voting on what's for dinner.
University of Scranton   |
Scranton, Pennsylvania   |         #include <std.disclaimer.h>