cancel
Turn on suggestions
Auto-suggest helps you quickly narrow down your search results by suggesting possible matches as you type.
Showing results for 
Search instead for 
Did you mean: 

Archives Discussions

edwen
Journeyman III
‎08-31-2010 12:08 AM

multiple GPUs problem

The GPUs stop working in parallel while the kernel gets more complicated

There are two kernels in my program, with the second one more complicated than the first one. I am trying to use 3 GPUs in parallel execution. From the results, the first kernal runs normally, with the total time slightly longer than that of each individual GPU. However, the total execution time of the second kernel is longer than the sum of all 3 GPUs. Can anyone help explain what may cause the problem? Here are the results:

First Kernel...

v  =    224.06217957
Elapsed time (without Greeks): 0.140319 sec

Profiling Information for GPU Processing:

Device 0 : Tesla T10 Processor
  Reduce Kernel     : 0.13262s

Device 1 : Tesla T10 Processor
  Reduce Kernel     evice 2 : Tesla T10 Processor
  Reduce Kernel     : 0.13462 s

Device 2 : Tesla T10 Processor
  Reduce Kernel     : 0.13322 s

Second Kernel...

v  =    224.06217957
Lb  =     21.34053040
Elapsed time (with Greeks): 1.558295 sec

Profiling Information for GPU Processing:

Device 0 : Tesla T10 Processor
  Reduce Kernel     : 0.51363 s

Device 1 : Tesla T10 Processor
  Reduce Kernel     : 0.51602 s

Device 2 : Tesla T10 Processor
  Reduce Kernel     : 0.51722 s


By the way, I am using Tesla C1060 and I modified my program according to the sample program "oclsimpleMultiGPU" provided in Nvidia OpenCL SDK sample codes. I am working under Linux. Thanks,

0 Likes
3 Replies
davibu
Journeyman III
‎08-31-2010 06:07 AM

Originally posted by: edwenBy the way, I am using Tesla C1060 and I modified my program according to the sample program "oclsimpleMultiGPU" provided in Nvidia OpenCL SDK sample codes. I am working under Linux. Thanks,

 

 

I'm confused, are you reporting a NVIDIA GPUs (i.e. Tesla C1060) bug here ? You can get some better answer here: http://forums.nvidia.com/index.php?s=eac990d0bd3c8c65c3dc7fd5559046f5&showforum=134

If you are running on AMD's GPUs, it could be the same bug I have reported here: http://forums.amd.com/devforum/messageview.cfm?catid=390&threadid=138807&enterthread=y

 

0 Likes
nou
In response to davibu
Exemplar
‎08-31-2010 08:55 AM

he reported it here. http://forums.nvidia.com/index.php?showtopic=179137

0 Likes
edwen
In response to davibu
Journeyman III
‎09-01-2010 06:18 AM

Originally posted by: davibu
Originally posted by: edwen 

 

I'm confused, are you reporting a NVIDIA GPUs (i.e. Tesla C1060) bug here ? You can get some better answer here: http://forums.nvidia.com/index.php?s=eac990d0bd3c8c65c3dc7fd5559046f5&showforum=134

If you are running on AMD's GPUs, it could be the same bug I have reported here: http://forums.amd.com/devforum/messageview.cfm?catid=390&threadid=138807&enterthread=y

 

I posted on Nvidia forum, too. But have yet got any solutions so far. My situation is slightly different from yours, though. The GPUs works fine in parallel until the kernel gets more complicated. That's really confusing.

0 Likes