HD5970 MultiGPU drop in performance issues

Discussion created by afo on Nov 1, 2010
Latest reply on Dec 5, 2010 by himanshu.gautam
What could be done to mitigate it?


As it was discussed in other threads, it's possible to enable the second GPU in a HD5970 board, but when we do so, we find that there is a performance drop; instead of a value near the theoretical 2x in kernel execution, we have a value around 1.4 times improvement, so my question is: Is something that we can do to mitigate it? I.e. It should be better to do a memory tranfer + kernel invocation for each GPU in order; or it could be better to do the memory transfers for each GPU, wait to them to finish, and then start calling the kernels? Does it make a difference? thanks a lot for any insight about this.

best regards,