Hi,

> This is horribly non-portable.  How much of a performance difference
> does it make?  How does it do on ppc64 systems where the cacheline
> size is not 32?

Yes, if anything we should catch cacheline aligned, multiple cacheline
sized zeroing in memset. 

Anton
_______________________________________________
openib-general mailing list
[email protected]
http://openib.org/mailman/listinfo/openib-general

To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general

Reply via email to