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

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

I'm running the same driver & I get same read out as above.
4/07/2010 9:57:57 a.m. NVIDIA GPU 0: GeForce GTX 470 (driver version 25721, CUDA version 3010, compute capability 2.0, 1248MB, 726 GFLOPS peak) Boinc .56 64 bit

http://setiathome.berkeley.edu/show_host_detail.php?hostid=5417843

---

Re-posting, by popular request, from CUDA MB V12b rebuild supposed to work with Fermi GPUs.

This note is aimed at people running optimised apps already. That's essential: you will need to modify an existing app_info.xml file.

This isn't the place to go into the whole science of installing optimised applications by hand, but in brief: stop BOINC first, keep backups, use a simple ANSI-mode text editor. If in doubt, read the BOINC FAQ version - fuller, and can be updated in the future.

You will need to add a whole new <app_version> section:

    <app_version>
        <app_name>setiathome_enhanced</app_name>
    	<version_num>610</version_num>
    	<avg_ncpus>0.200000</avg_ncpus>
    	<max_ncpus>0.200000</max_ncpus>
    	<plan_class>cuda_fermi</plan_class>
	<file_ref>
            <file_name>setiathome_6.10_windows_intelx86__cuda_fermi.exe</file_name>
            <main_program/>
	</file_ref>
	<file_ref>
            <file_name>cudart32_30_14.dll</file_name>
	</file_ref>
   	<file_ref>
            <file_name>cufft32_30_14.dll</file_name>
   	</file_ref>
	<file_ref>
            <file_name>libfftw3f-3-1-1a_upx.dll</file_name>
   	</file_ref>
	<coproc>
            <type>CUDA</type>
            <count>1</count>
	</coproc>
    </app_version>

You'll also have to add <file_info> sections for any file you're not already using. You may have libfftw3f-3-1-1a_upx.dll already, in which case you don't need to add it again: but the full set is

    <file_info>
        <name>setiathome_6.10_windows_intelx86__cuda_fermi.exe</name>
        <executable/>
    </file_info>
    <file_info>
        <name>cudart32_30_14.dll</name>
        <executable/>
    </file_info>
    <file_info>
        <name>cufft32_30_14.dll</name>
        <executable/>
    </file_info>
    <file_info>
        <name>libfftw3f-3-1-1a_upx.dll</name>
        <executable/>
    </file_info>

Finally, you'll need the files themselves: download from

http://boinc2.ssl.berkeley.edu/beta/download/setiathome_6.10_windows_intelx86__cuda_fermi.exe (2,476 KB)
http://boinc2.ssl.berkeley.edu/beta/download/cudart32_30_14.dll (280 KB)
http://boinc2.ssl.berkeley.edu/beta/download/cufft32_30_14.dll (12,188 KB)
http://boinc2.ssl.berkeley.edu/beta/download/libfftw3f-3-1-1a_upx.dll (439 KB)

Make sure the file sizes are correct - sometimes these manual downloads crash out early.

Good morning.

I just picked up a GTX480 to try the thing out on SETI. The BOINC manager gets stuck at ~4.4% while downloading cufft32_30_14.dll. At the advice of another thread, I came here and attempted to download the files above by hand. All but cufft32_30_14.dll will download. It gets to about 370K and then stalls.

Is there an alternate location for this .dll or is there some setting in BOINC or SETI that I can set that might be interfering with the simple download?

I would prefer not running optimized in the beginning, so that I can see what success looks like. But for now that is where I am stuck. Any help would be appreciated. In case it helps:

Motherboard: ASUS P6T7
GPU: EVGA GTX480
BOINC Message Info:
7/10/2010 6:39:38 AM Starting BOINC client version 6.10.56 for windows_x86_64
7/10/2010 6:39:38 AM log flags: file_xfer, sched_ops, task
7/10/2010 6:39:38 AM Libraries: libcurl/7.19.7 OpenSSL/0.9.8l zlib/1.2.3
7/10/2010 6:39:38 AM Data directory: D:\ProgramData\BOINC
7/10/2010 6:39:38 AM Running under account SeyfertR
7/10/2010 6:39:38 AM Processor: 8 GenuineIntel Intel(R) Core(TM) i7 CPU 920 @ 2.67GHz [Family 6 Model 26 Stepping 5]
7/10/2010 6:39:38 AM Processor: 256.00 KB cache
7/10/2010 6:39:38 AM Processor features: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss htt tm pni ssse3 cx16 sse4_1 sse4_2 syscall nx lm vmx tm2 popcnt pbe
7/10/2010 6:39:38 AM OS: Microsoft Windows 7: Ultimate x64 Edition, (06.01.7600.00)
7/10/2010 6:39:38 AM Memory: 5.99 GB physical, 11.98 GB virtual
7/10/2010 6:39:38 AM Disk: 558.76 GB total, 496.75 GB free
7/10/2010 6:39:38 AM Local time is UTC -4 hours
7/10/2010 6:39:38 AM NVIDIA GPU 0: GeForce GTX 480 (driver version 25721, CUDA version 3010, compute capability 2.0, 1503MB, 778 GFLOPS peak)

Take care and have a good day.

Rich

I just picked up a GTX480 to try the thing out on SETI. The BOINC manager gets stuck at ~4.4% while downloading cufft32_30_14.dll. At the advice of another thread, I came here and attempted to download the files above by hand. All but cufft32_30_14.dll will download. It gets to about 370K and then stalls.

Is there an alternate location for this .dll or is there some setting in BOINC or SETI that I can set that might be interfering with the simple download?

Try it from the Beta project: http://boinc2.ssl.berkeley.edu/beta/download/cufft32_30_14.dll

or the Main Project: http://boinc2.ssl.berkeley.edu/sah/download_fanout/cufft32_30_14.dll

Claggy

Edit: I've just downloaded it succesfully from the Beta project using Getright, it'll resume downloads if they stall.

Good morning.

I just picked up a GTX480 to try the thing out on SETI. The BOINC manager gets stuck at ~4.4% while downloading cufft32_30_14.dll. At the advice of another thread, I came here and attempted to download the files above by hand. All but cufft32_30_14.dll will download. It gets to about 370K and then stalls.

Is there an alternate location for this .dll or is there some setting in BOINC or SETI that I can set that might be interfering with the simple download?

I would prefer not running optimized in the beginning, so that I can see what success looks like. But for now that is where I am stuck. Any help would be appreciated.

Take care and have a good day.

Rich

Polite questions get quick answers!

It should be possible to get the CUDA DLLs by simple browser download, either from the main project download fanout (which is where BOINC will be looking), or from the Beta site I linked in that opening post. If it doesn't work try, try, and try again.

Alternatively, the DLLs are in the NVidia CUDA 3.0 toolkit (big download, but a more reliable server). I think this is the one:

http://www.nvidia.com/object/thankyou.html?url=/compute/cuda/3_0/toolkit/cudatoolkit_3.0_win_32.exe

Success!

Thank-you both very much for your help. I must have a Windows issue, as all three links that Claggy proposed, did not complete a download; however, the NVidia link worked without issues and I was able to located the necessary files.

I have to run to work now, but will put it all together tonight and hopefully start exercising this GPU.

Take care and thanks again.

Rich

Is there a way to allow the CPU->GPU rescheduling if you don't have an app_info.xml file? Can you create a minimal app_info.xml that contains only the one alias, or do I need to somehow get the entries for the rest of the (stock) apps as well?

-Scott