I just tried to simulate this by using Remote Desktop, and BOINC was still able to correctly detect the memory information for the Nvidia GPU.
----- Rom -----Original Message----- From: boinc_dev-boun...@ssl.berkeley.edu [mailto:boinc_dev-boun...@ssl.berkeley.edu] On Behalf Of Raistmer Sent: Friday, October 16, 2009 5:52 PM To: David Anderson (BOINC) Cc: boinc_dev@ssl.berkeley.edu Subject: Re: [boinc_dev] BOINC 6.10.14 re missing GPU Don't know if it will work always but in case of "disappeared" GPU cuMemGetInfo(&free,&total); returns zero in both fields. Zero in total memory could be sign of error... ----- Original Message ----- From: "David Anderson" <da...@ssl.berkeley.edu> To: "Raistmer" <raist...@mail.ru> Cc: <boinc_dev@ssl.berkeley.edu> Sent: Saturday, October 17, 2009 1:37 AM Subject: Re: [boinc_dev] BOINC 6.10.14 re missing GPU > That's what we're doing. > We have this working for ATI: the CAL init function fails > if the GPU is not usable. > We haven't figured how to tell if an NVIDIA GPU is still working; > none of the obvious things works. > We're waiting to hear from NVIDIA on this. > > -- David > > Raistmer wrote: > >> If you really want to improve BOINC's awareness of coprocessor presence - >> check this presence itself, not factor that could hide GPU - there are >> many such factors. >> BTW, checking for GPU at moment of schedule decision (if not too costly >> by itself) could have additional benefit (additional to correctly >> handling RDP and fast user switching). >> There are some situations when GPU just "disappears". Maybe overheating >> maybe some another reason, but I see such behavior on one of my nVidia >> GPUs, 9400GT. >> This cause CUDA MB to fallback to CPU processing cause it ordered to run >> on GPU but its own check shows no such GPU. This is worse than it just >> suspend its work (CPU part of current CUDA MB much worse than standalone >> opt CPU MB, hence CPU fallback not only doesn't use GPU, it uses CPU in >> inefficient way). >> If BOINC could check GPU availability before actual task scheduling it >> could prevent this situation also. >> >> _______________________________________________ >> boinc_dev mailing list >> boinc_dev@ssl.berkeley.edu >> 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 boinc_dev@ssl.berkeley.edu 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 boinc_dev@ssl.berkeley.edu http://lists.ssl.berkeley.edu/mailman/listinfo/boinc_dev To unsubscribe, visit the above URL and (near bottom of page) enter your email address.
