That sounds plausible. There's a note on thread priority here: http://boinc.berkeley.edu/trac/wiki/CudaApps#Threadpriority -- David
On 04-Jan-2011 8:02 AM, Richard Haselgrove wrote: > I think this might be a thread (as opposed to application) priority issue. > Compare these two Process Explorer screenshots: > http://img834.imageshack.us/img834/9496/einsteincudapriority.png > http://img703.imageshack.us/img703/3087/seticudapriority.png > (both taken from the same computer, during the same BOINC session) > The worker thread for the Einstein application is running at priority one, > whereas the equivalent thread for SETI is running at priority six. (The main > application thread is running at priority six in both cases) > The SETI application in the screenshot is the original > setiathome_6.08_windows_intelx86__cuda.exe written by NVidia for SETI's cuda > launch in January 2009, so NVidia should be able to explain how to work round > the discrepancy. Note that thread priority is (AFAIK) a Windows-only concept, > so > this probably won't help you Linux/Mac issues. > > ----- Original Message ----- > *From:* Oliver Bock <mailto:[email protected]> > *To:* David Anderson <mailto:[email protected]> ; boinc_dev > <mailto:[email protected]> ; Boinc Projects > <mailto:[email protected]> > *Sent:* Monday, December 20, 2010 11:12 AM > *Subject:* [boinc_dev] CUDA task scheduling > > Hi everyone, > > We just deployed a new CUDA application (called BRP3) as part of the > einst...@home <mailto:einst...@home> project. This app roughly up to 75% > of > a GPU and 3-30% of > a CPU, depending on the GPU model/performance. Thus our scheduler > currently issues these tasks with the following settings: > > hu.avg_ncpus = 0.2 > hu.ncudas = 1 > > Please note that BOINC (e.g. sched/sched_customize) revision 22832 is > used in this case. > > The problem is that with the settings above BOINC starts CUDA tasks in > addition to CPU tasks that already occupy all existing CPU cores. This > means on a system having four CPU cores and two CUDA devices, four CPU > tasks and two CUDA tasks are launched. Although this behavior is > intended, it doesn't really work out for us because the performance of > the CUDA tasks is degraded significantly - GPU usage goes down to less > than 10%, increasing the runtime by the same factor. Although the CUDA > tasks run with slightly higher priority (below normal on Windows) than > the CPU tasks (low on Windows) they are limited by the already > fully-occupied CPU cores which are still required for up to 30% of the > computation. > > Since we couldn't yet release a Linux or Mac OS version we don't know > whether this is a Windows time-slicing issue or not. Are there any other > projects running CUDA tasks in a comparable way? > > The only workaround in sight would be to acquire a full CPU core once > again but that's certainly not ideal. > > Any ideas are welcome! > > > Cheers, > Oliver > _______________________________________________ > boinc_dev mailing list > [email protected] <mailto:[email protected]> > http://lists.ssl.berkeley.edu/mailman/listinfo/boinc_dev > To unsubscribe, visit the above URL and > (near bottom of page) enter your email address. _______________________________________________ boinc_dev mailing list [email protected] http://lists.ssl.berkeley.edu/mailman/listinfo/boinc_dev To unsubscribe, visit the above URL and (near bottom of page) enter your email address.
