what video card you using? and what WU is it on?
SMP & GPU2 setup, am I missing something?
So today I added a video card to my amd sig rig. It's not a 24/7 folder, but when I'm not gaming I'd like it to fold. Up until today, it had the x800 in it, which can't fold. Today I put a nice Nvidia card in expecting a nice boost in ppd.
I have been running dual VM/ubuntu clients. Normally I just let it go without making any adjustments to priority or affinity. I think it defaults to normal priority and lets both VM's run each on all 4 cores.
After adding the gpu, I made sure that the gpu2 client was set to high priority and I left the VM at normal. Well, the card is getting some horrible ppd. I know the card very well and it's not producing like it should. I tried to change the affinity on the vm's so that each was running on two separate cores. Then I let the gpu2 client run on all 4 cores. It's still getting horrible ppd. Am I missing something here?
For some reason I though that the smp clients would take a hit and the gpu2 client would be fine. Maybe it's the other way around and the gpu2 client takes the hit?
I have been running dual VM/ubuntu clients. Normally I just let it go without making any adjustments to priority or affinity. I think it defaults to normal priority and lets both VM's run each on all 4 cores.
After adding the gpu, I made sure that the gpu2 client was set to high priority and I left the VM at normal. Well, the card is getting some horrible ppd. I know the card very well and it's not producing like it should. I tried to change the affinity on the vm's so that each was running on two separate cores. Then I let the gpu2 client run on all 4 cores. It's still getting horrible ppd. Am I missing something here?
For some reason I though that the smp clients would take a hit and the gpu2 client would be fine. Maybe it's the other way around and the gpu2 client takes the hit?
1 - 3 of 3 Posts
I think that I have it figured out. The gpu2 client would default to using only core3 every time that it completed a wu. I had priority set correctly, but needed a solution for forcing the affinity to be on more than one core. After setting up priffinity, I have the gpu2 client set to use all 4 cores and on high.
Then I set up each of the vm's to run on two different cores each at normal priority. Now my gpu is working normal and each vm only lost around 150-200ppd.
Then I set up each of the vm's to run on two different cores each at normal priority. Now my gpu is working normal and each vm only lost around 150-200ppd.
1 - 3 of 3 Posts
- This is an older thread, you may not receive a response, and could be reviving an old thread. Please consider creating a new thread.
Overclock.net
A forum community dedicated to overclocking enthusiasts and testing the limits of computing. Come join the discussion about computing, builds, collections, displays, models, styles, scales, specifications, reviews, accessories, classifieds, and more!
Full Forum Listing
Explore Our Forums
Top Contributors this Month
View All
HappySheep
351 Replies
Ichirou
199 Replies
GRABibus
194 Replies
Recommended Communities
