Plateforme Level Extreme
Abonnement
Profil corporatif
Produits & Services
Support
Légal
English
A tip on hardware to speed up VFP
Message
De
06/02/2001 16:19:05
 
 
À
06/02/2001 16:04:32
Information générale
Forum:
Visual FoxPro
Catégorie:
Autre
Divers
Thread ID:
00472486
Message ID:
00473165
Vues:
39
Hi Gar,

If I'm being a pain about this, feel free to ignore. . .

So both were multiprocessors, with the second one being less "powerful" all around than the first.

What were the CPU mhz of each?

With the 2 scenarios you have described it may even have been possible to get better than the industry average 1.7x difference in performance, and it looks like you did on the bigger box.

The 1.7x comes from a mixed workload of several simultaneous jobs and the (approx.) .3 "loss" (people might have expected 2x) is the result, mostly, of contention for RAM and the overhead associated with giving each processor the latest content of the RAM whenever it asks for some.
So in your case, running only one process (other than OS processes) that contention should be minimal, freeing up more processor cycles to do real user work.

JimN


>No it was not truly standard. A local store had had a canceled order on a dual processor machine. We bought it at bargain with the 256 M or Ram and 8 Meg sccsi hard disk. Plugging in the second processor did not make it faster that the big machine with 2 processors -- but make it 1.5 it's old speed.
>>Hi Gar,
>>
>>>>Where's Mac. Rubel when you really need a benchmark! < bg >
>I believe that what Erik replied - that VFP does multithread internally, though *we* cannot make use of it directly ourselves - is the most likely explanation. I'm pretty sure that I have read some MS VFP team member saying that it *does* multithread internally.
>>>
>>>One last thing. We tried it on one of our more standard workstations -- 256 MB --8 Gig Scsci. We got a pretty big increase there as well -- around 1.5. So it seems that as Erik says VFP is multi-threading --and you can get a real perfornance improvement with multi-processors. This also implies that faster chips may be a good thing as well. In short VFP can apparently take pretty much take advantage of every toy out there...
>>
>>I take it that the "more standard workstation" is *not* a multiprocessor, so I infer that it has a faster processor than the dualed server.
>>What are the processor speeds involved? What the RAM on the dual?
>>
>>Cheers,
>>
>>JimN
Précédent
Suivant
Répondre
Fil
Voir

Click here to load this message in the networking platform