On Mon, 2008-06-16 at 19:08 +0300, Sasha Khapyorsky wrote: > On 09:06 Mon 16 Jun , Hal Rosenstock wrote: > > > > If 16K array of pointers is OK, is a 48K array ? If so, then this should > > be straightforward to change. > > Looks like a good idea for me.
It would need to be based on min of the switch LFT sizes rather than max LID in use/persistent as it is now. Also, max_unicast_lid_ho similar to max_multicast_lid_ho exists and is supported now so the actual max optimization could be applied although from a practical standpoint this doesn't have any benefit in most if not all subnets (whereas the multicast arch max is not currently implemented). -- Hal > Sasha > _______________________________________________ > general mailing list > [email protected] > http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general > > To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general _______________________________________________ general mailing list [email protected] http://lists.openfabrics.org/cgi-bin/mailman/listinfo/general To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
