Forum > GPU crunching

Fighting the CUDA bug

<< < (2/4) > >>

Raistmer:

--- Quote from: popandbob on 30 Jun 2009, 03:36:01 pm ---I believe the problem is caused by boinc's safeguard against non check pointing apps. If an application doesn't reach a checkpoint it will be left in memory regardless of what settings have been set.
Bob

--- End quote ---
CUDA MB does checkpoint. So not the case unfortunately...

Richard Haselgrove:
DA has recently 'checked in' (i.e. modified the source code, but not yet compiled a new version) a change: previously/currently, BOINC would leave a CUDA app in memory if it was preempted before the first checkpoint. In future, it will be cleaned out even if it has never checkpointed - so application developers, get your checkpointing code working early on in the development process.

Raistmer:

--- Quote from: Richard Haselgrove on 30 Jun 2009, 04:26:25 pm --- so application developers, get your checkpointing code working early on in the development process.

--- End quote ---
Or make your tasks so fast that they will never need to checkpoint ;D ;D ;D

sunu:

--- Quote from: Richard Haselgrove on 30 Jun 2009, 04:26:25 pm ---DA has recently 'checked in' (i.e. modified the source code, but not yet compiled a new version) a change: previously/currently, BOINC would leave a CUDA app in memory if it was preempted before the first checkpoint. In future, it will be cleaned out even if it has never checkpointed - so application developers, get your checkpointing code working early on in the development process.

--- End quote ---

Yes, currently, if the cuda app is preempted in the first 30sec or so of its initialisation in cpu, it is left in memory, no matter what settings you've got.

Jason G:

--- Quote from: Raistmer on 30 Jun 2009, 04:30:29 pm ---Or make your tasks so fast that they will never need to checkpoint ;D ;D ;D

--- End quote ---

That's no joke.  I had this in mind for multithreaded apps, triggered by Alex's treatment of spike finding code on Macs.  Goodbye 80% of BoincAPI if the tasks can be fast enough to not need to bother checkpointing.

Navigation

[0] Message Index

[#] Next page

[*] Previous page

Go to full version