Michael> I have implemented a small test for the rdma
Michael> functionality. I based it on the pingpong test, the main
Michael> change being polling on data instead of completions (but
Michael> I also changed the clock sampling to use the realtime
Michael> clock from -lrt, since it gives a more consistent timing
Michael> results on my system).
Sounds great, thanks.
Michael> Do you want such stuff under libibverbs/examples, or
Michael> somewhere else?
Please generate a patch putting it under libibverbs/examples. If it
makes sense to share code from pingpong.c, feel free to split
pingpong.c into multiple source files and share the code.
Thanks,
Roland
_______________________________________________
openib-general mailing list
[email protected]
http://openib.org/mailman/listinfo/openib-general
To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
