Sounds good to me :) Did you expect anything else?

---

I would have expected nine - eight on the CPU cores, and a ninth on the GTX 260

But the GTX 260 isn't a Fermi card, so - although I'm delighted to see you're doing well - it doesn't really belong in this thread.

Thanks to Josef W. Segur for correcting my app_info file. My 1st gpu using a optimised cpu app Task 1643724208 took 12.15 minutes at an true angle range of: 0.385434

---

I dont suppose theres any eta or info on when a beta might show up for the 480 that'll work on a regular ole non-optimised client? (the kind without an app_info)

---

I dont suppose theres any eta or info on when a beta might show up for the 480 that'll work on a regular ole non-optimised client? (the kind without an app_info)

The client for a 480 (fermi) is already out.
Windows/x86 6.10 (cuda_fermi) 8 Jun 2010 22:50:03 UTC

See http://setiathome.berkeley.edu/apps.php

If you are running non app_info and have a 480/470/465 installed with correct drivers you should pick up work units (When they are available/project is up of course)

Once you have the card installed and recognised by BOINC you will get the workunits assuming you have

Use NVIDIA GPU
Enforced by version 6.10+ yes

set in your project preferences (or local preferences if set).

---

GPU Users Group

Wow, so much info in this thread. Hard to pick out what I am looking for.

Is there currently a location to download an app_info setup for Fermi? I've got one working but it was based off of the stuff posted in May.

Is there a way, or any benefit, to have my 480 work in more than 1 WU at a time?

---

Wow, so much info in this thread. Hard to pick out what I am looking for.

Is there currently a location to download an app_info setup for Fermi? I've got one working but it was based off of the stuff posted in May.

Is there a way, or any benefit, to have my 480 work in more than 1 WU at a time?

I run 3 WU's on a GTX470 and that gives me the highest output.

---

Rig name: "x6Crunchy"
OS: Win 7 x64
MB: Asus M4N98TD EVO
CPU: AMD X6 1055T 2.8(1,2v)
GPU: 2x Asus GTX560ti
Member of: Dutch Power Cows

Wow, so much info in this thread. Hard to pick out what I am looking for.

Is there currently a location to download an app_info setup for Fermi? I've got one working but it was based off of the stuff posted in May.

Is there a way, or any benefit, to have my 480 work in more than 1 WU at a time?

There is no real one size fits all as you can see from this thread.
It will depend on what apps you are using or have available and what CPU capbility version you chose and 32 or 64 bit versions.
Chances are if your one from May is working OK you dont need to do anything.
If you post your current app_info we could take a look.

---

GPU Users Group

After re-reading (and again and again) some posts in this thread, I think I know what I need to do now. I'm running an older version of Boinc and using a potentially experimental 6.09_cuda_fermi.exe. So, first thing I will upgrade to 6.10.56 and get the latest files I need. The servers are down now so it will have to wait for tomorrow. <crosses fingers>

After that, I'll make a copy of the Fermi App section and make the necessary updates (cuda to fermi_cuda under plan_class) to allow me to reschedule from CPU to GPU.

I'm also going to install the lunatics optimized for my CPU. 2 questions regarding this...

1) For a core i7, which yields the best result?
2) Where, in my steps above should this go? Does the installer modify the app_info.xml file or does it overwrite it with it's own? Otherwise I may just take one posted above that has both the lunatics and the 610 fermi bits.

My main PC has about 400-500 tasks assigned to the CPU (I had it shut down for a while) and I'd love to get these rescheduled to the GPU.

I'll back up all my project data prior to messing around. If the above fails, I'm gonna do the shotgun approach posted earlier and just edit the client_state.xml and change "cuda" to "fermi_cuda".

Fantastic info in this thread, I just wish it was more user friendly to go through and that the great info in it could be "stickied" so it's easier to find.

Thanks all!

---

I can answer part of your questions. The installer puts in it's own app_info and places your old one in a separate file marked oldApp_backup. As for which yields the best results, it is pretty much a toss up between the ssse3 and the sse4.1. It's best to try each on your machine but there isn't that much difference between them. I noticed Joe Segur's app uses ssse3, if I had a Fermi card I think I would trust his judgment and use his. Of course that is just my opinion. :-)

---

PROUD MEMBER OF Team Starfire World BOINC

I can answer part of your questions. The installer puts in it's own app_info and places your old one in a separate file marked oldApp_backup. As for which yields the best results, it is pretty much a toss up between the ssse3 and the sse4.1. It's best to try each on your machine but there isn't that much difference between them. I noticed Joe Segur's app uses ssse3, if I had a Fermi card I think I would trust his judgment and use his. Of course that is just my opinion. :-)

Thanks for the info. Once I get the new Boinc and files, I'll just give Joe's xml file a try. Anyone have any tips on reading those things? I have a hard time finding where to copy and paste. Even using XMLNotepad doesn't help me much.

---

I run 3 WU's on a GTX470 and that gives me the highest output.

Can some please point me in the direction of how to process more than 1 task at a time?
Thanks in advance

---

Got it working today. Took several attempts to get the app_info right, but by following the instructions in post 2, then adding the X64 platform based on posts further down it worked. I did the duplicate thing and changed the plan_class and now I can even reschedule to the GPU.

Nice to feed that thing again. Big thanks to Richard for putting all this out here.

---

I run 3 WU's on a GTX470 and that gives me the highest output.

Can some please point me in the direction of how to process more than 1 task at a time?
Thanks in advance

In your app_info.xml look for the following:

<coproc>
<type>CUDA</type>
<count>1</count>
</coproc>

Change count into 0.33 for 3 WU's on your card.
Change count into 0.50 for 2 WU's on your card.
Change count into 1 for 1 WU on your card.

---

Rig name: "x6Crunchy"
OS: Win 7 x64
MB: Asus M4N98TD EVO
CPU: AMD X6 1055T 2.8(1,2v)
GPU: 2x Asus GTX560ti
Member of: Dutch Power Cows

Downloaded yesterday 20 wu application 6.10 for fermi (gtx480).

They ALL cancel (computational error) after 1 hr 3 min 1 sec.

I use windows-xp-pro 257.21 driver.

What is going wrong??

Ton (ftpd) Netherlands

---

Downloaded yesterday 20 wu application 6.10 for fermi (gtx480).

They ALL cancel (computational error) after 1 hr 3 min 1 sec.

I use windows-xp-pro 257.21 driver.

What is going wrong??

Ton (ftpd) Netherlands

Heb je flops in je app_info.xml?

---

Rig name: "x6Crunchy"
OS: Win 7 x64
MB: Asus M4N98TD EVO
CPU: AMD X6 1055T 2.8(1,2v)
GPU: 2x Asus GTX560ti
Member of: Dutch Power Cows

Geen flauw idee, waar dit bestand kan/moet staan. Ik gebruik alles standaard!

Alle vorige wu deden het uitstekend binnen 8 min of sneller.

Ton van Born (ftpd) Netherlands

fermi app is running incredibly slow, well at least i think. take a look.

7/3/2010 12:55:43 PM NVIDIA GPU 0: GeForce GTX 470 (driver version 25721, CUDA version 3010, compute capability 2.0, 1248MB, 726 GFLOPS peak)

http://setiathome.berkeley.edu/show_host_detail.php?hostid=4001951

---

Geen flauw idee, waar dit bestand kan/moet staan. Ik gebruik alles standaard!

Alle vorige wu deden het uitstekend binnen 8 min of sneller.

Ton van Born (ftpd) Netherlands

Als je alles standaard hebt staan zou het niet aan de flops mogen liggen.
Maar heb er wel eerder iets over gezien, had iets met de "dcf" te maken geloof ik.

---

Rig name: "x6Crunchy"
OS: Win 7 x64
MB: Asus M4N98TD EVO
CPU: AMD X6 1055T 2.8(1,2v)
GPU: 2x Asus GTX560ti
Member of: Dutch Power Cows

fermi app is running incredibly slow, well at least i think. take a look.

7/3/2010 12:55:43 PM NVIDIA GPU 0: GeForce GTX 470 (driver version 25721, CUDA version 3010, compute capability 2.0, 1248MB, 726 GFLOPS peak)

http://setiathome.berkeley.edu/show_host_detail.php?hostid=4001951

Hard to tell.
3 "normal" WU's take about 21 minutes each on my Fermi.
I run 3 WU's at once at the GTX470, that crunches me about 8 or 9 WU's every hour.
The small WU's (±40 credits) take about 330 seconds.

Because of the small cache (20 WU limit) I accidently received a VLAR on my GPU and that really slows down the 2 other WU's on the GPU... They take about 10 minutes longer...

---

Rig name: "x6Crunchy"
OS: Win 7 x64
MB: Asus M4N98TD EVO
CPU: AMD X6 1055T 2.8(1,2v)
GPU: 2x Asus GTX560ti
Member of: Dutch Power Cows