Staff Priorities - Scott: Difference between revisions

Revision as of 18:04, 9 November 2012

Work on ExtractMPI
Create presentation about parallel simulated annealing for HPC booth, get feedback from Kevin and Phil
Plot lines of best fit on Kraken runs to use better runtime estimates in DAX generator to improve load balancing

@@ Line 1: / Line 1: @@
 == Yesterday ==
-*Tested buffering code, got better performance:
+*Talked with David about MMI code
-**read_sgt decreased from 21.1 avg to 15.8;  max from 5322 to 1404
+*Coordinated with Efecan to divide up the work on ExtractMPI, started coding
-**sgt_subset improved but could still be better:  avg from 1327 to 664, max from 6773 to 5443
+*Monitored production runs
-**overall down to 5400 SUs/run
-*Corresponded with Maren and David about generating seismogram data products for EEW
 == Today ==
-*Testing 2 simultaneous workflows for SU burn
+*Work on ExtractMPI
-*Email Lonnie Crosby about Kraken I/O
+*Create presentation about parallel simulated annealing for HPC booth, get feedback from Kevin and Phil
-*Test PMC on HPC to get comparison for Gideon
+*Plot lines of best fit on Kraken runs to use better runtime estimates in DAX generator to improve load balancing
-*Investigate changing order of points in SGT
-*Work on new PGI seg fault
-*ucvm2query
 == Blocked ==
@@ Line 18: / Line 13: @@
 == Follow-ups ==
-*David
+*No