<coprocs><coproc_cuda><count>1</count><name>GeForce 9800 GT</name><available_ram>882518016.000000</available_ram><have_cuda>1</have_cuda><have_opencl>0</have_opencl><peak_flops>462000000000.000000</peak_flops><cudaVersion>6000</cudaVersion><drvVersion>0</drvVersion><totalGlobalMem>1073020928.000000</totalGlobalMem><sharedMemPerBlock>16384.000000</sharedMemPerBlock><regsPerBlock>8192</regsPerBlock><warpSize>32</warpSize><memPitch>2147483647.000000</memPitch><maxThreadsPerBlock>512</maxThreadsPerBlock><maxThreadsDim>512 512 64</maxThreadsDim><maxGridSize>65535 65535 1</maxGridSize><clockRate>1375000</clockRate><totalConstMem>65536.000000</totalConstMem><major>1</major><minor>1</minor><textureAlignment>256.000000</textureAlignment><deviceOverlap>1</deviceOverlap><multiProcessorCount>14</multiProcessorCount><pci_info><bus_id>4</bus_id><device_id>0</device_id><domain_id>0</domain_id>

This is what the cpproc_info.xml file shows. I cant get cuda to work not getting any gpu work .

---

Linux does not have a default app for CUDA yet, it is only available via the anonymous platform.

http://jgopt.org/download.html

---

Thank you for responding. I have been trying to install Nividia toolkit. I'm successful to a point when I sudo install cuda it says cant find cuda package.This is step 5 to get to this point. I was hoping that someone that has been able to install and run cuda on linux could help . I'm running Ubuntu 14.04 32 bit . I have seen posts on running Fedora 20.0 and yum but was hoping for fix with ubuntu.

---

Hi .. i face the same problem here..
running Ubuntu on a 64bit-system
Linux xxxx 3.13.0-63-generic #103-Ubuntu SMP Fri Aug 14 21:42:59 UTC 2015 x86_64 x86_64 x86_64 GNU/Linux
with a Nvidia Geforce 8800GTS using the nvidia-340-drivers.



my stdoutdae.txt states:

12-Oct-2015 15:37:47 [---] Starting BOINC client version 7.2.42 for x86_64-pc-linux-gnu
12-Oct-2015 15:37:47 [---] log flags: file_xfer, sched_ops, task
12-Oct-2015 15:37:47 [---] Libraries: libcurl/7.35.0 OpenSSL/1.0.1f zlib/1.2.8 libidn/1.28 librtmp/2.3
12-Oct-2015 15:37:47 [---] Data directory: /var/lib/boinc-client
12-Oct-2015 15:37:47 [---] CUDA: NVIDIA GPU 0: GeForce 8800 GTS (driver version unknown, CUDA version 6.5, compute capability 1.0, 640MB, 592MB available, 342 GFLOPS peak)
12-Oct-2015 15:37:47 [---] OpenCL: NVIDIA GPU 0: GeForce 8800 GTS (driver version 340.93, device version OpenCL 1.0 CUDA, 640MB, 592MB available, 342 GFLOPS peak)
12-Oct-2015 15:37:47 [SETI@home] Found app_info.xml; using anonymous platform
12-Oct-2015 15:37:47 [---] Processor: 4 GenuineIntel Intel(R) Core(TM)2 Quad CPU Q8300 @ 2.50GHz [Family 6 Model 23 Stepping 10]

but it will only request new Tasks for the CPU.

http://www.dunadd.co.uk/seti/forum/viewtopic.php?f=139&t=2493 I found this to be very helpful. Just follow the format. Updating the mega pack to the newest cuda and drivers made the video crash. This version worked for my video card :
boinc-client-nvidia-cuda 7.6.2+dfsg-0~1343~ubuntu14.04.1 Metapackage for Cuda-savvy Boinc client and manager. I dowloaded from software center. Then the libraries then the mbprobe and it worked. So now its crunching Astropulse on nividia gpu. Hope this helps.

---

Here is the last comment;

Summary: drivers starting from 340.52 through 341.44 (not including) are inappropriate for using with pre-FERMI devices and OpenCL AstroPulse.
Either use older driver or upgrade to 341.44.
~Raistmer

http://setiathome.berkeley.edu/forum_thread.php?id=75633&postid=1655670#1655670