Laxmikant "Sanjay" Kale
- Email: firstname.lastname@example.org
- Registered on: 02/11/2013
- Last connection: 04/11/2017
- 03:21 PM Charm++ Feature #870: SDAG methods marked as [sync] should only return when run to completion
- Two contradictory thoughts: (a) should we allow a a threaded method to be also an sdag method? Seems odd.. not quite ...
- 12:12 PM Charm++ Cleanup #453: Remove unused data members from classes and structs used in the RTS
- We need to make sure the extra fields are not added for cache alignment. This is rare, and only happens in message en...
- 03:25 PM Charm++ Bug #250: Uniquely tag each chare array broadcast to enable true unique delivery
- After this bug is fixed, add a test to nightly build (megatest?) to check it continues to work.
- 02:36 PM Charm++ Bug #806: CkReduction::set breaks CkMulticast section reductions
- Sam: I listed (a) as a quickfix. You should do it so your app can continue. If it seems easy enough to do (b) (add th...
- 02:28 PM Charm++ Bug #806: CkReduction::set breaks CkMulticast section reductions
- The only information available at the place where the check is made (near line 1328 in ckmulticast.c) is a a pointer ...
- 12:42 PM Charm++ Bug #807 (Rejected): redo performance comparison
- SInce its an old bug, its worthwhile re-doing a perfoemance comparison.
- 10:12 AM Charm++ Feature #174: objid_t: Distributed lookup protocol
- "a solution" => please record what the solution is in redmine.
- 02:17 PM Charm++ Feature #174: objid_t: Distributed lookup protocol
- A solution is to add an extra bit to the message that provides Index and asks for Location and ID. This bit could be ...
- 02:17 PM Charm++ 0.20 hour (Feature #174 (Merged): objid_t: Distributed lookup protocol)
- 12:16 AM Charm++ Bug #358: PAMI SMP Memory fragmentation / leak
- So, what possible recourse do we have?
Also available in: Atom