You are here:
NRAO Public Wiki
>
HPC Web
>
CasaParallelization
>
CasaParallelMinutes20110912
(2011-10-03,
JamesRobnett
)
Edit
w
iki text
Edit
Attach
P
rint version
Casa Parallelization meeting minutes
Monday September 12th Room 317, 3:30pm MDT
Attendees: Sanjay, Brian, Bryan, Jim, Jeff, James, Kumar
Targets/tasks for September 12 - 18th
Discussion/Agenda
Lustre file I/O failure
Jim/James
Revisit async iterator for writing
Jim/Gusto
Move subtables to in-memory storage manager
Jim
Status
Now put in calibrator tool
Now put in flagging infrastructure (Gusto might do)
Examine async thread failure problem and memory leak
Jim/James
On hold for in-memory storage manager
Seems stable in recent tests
pcube does show thread failure
Work toward implementing streaming framework in applycal
Jim
postpone till after release
Needs testing
Needs flagger added
Spectral imaging
Kumar
Parallelization status
Should be in release
Masking issue with pcube for making a task
Imaging advances
Add in weights to pcube and pcont (mosaicing) is in and may make release
Add in stopping threshold to both
in place
Complete parallel user interface frame work
Jeff/Honglin
Setjy taking longer than the serial case, seems to be read seek problem
Pending James looking at
Refine and distribute cluster scheduler interface
James
In progress, working with Kscott on multiple queue options
Awaiting proto parallel script
Need 400+GB continuum case with complex field
Sanjay
Formalized reduction status
Scripted reduction status
Internal users
Miriam is working on a parallel Casa guide
Deferred Topics
Test version of auto-flagging
deferred
Few weeks from suitable for testing
Parallel gridder testing
James
deferred
MS-MFS performance vs image size
James
Deferred
Appears to be an L1-L2 cache issue on older systems (newer Nehalems have one cache line per core)
Consider other parallelization approaches
Priorities based on 3.3 release plans
Parallel framework
BDF size independent filler aka streaming filler
Async I/O
Multims spectral, continuum imaging
auto-flagging
ARDG Targets
What is negative side effect of CVel in filler, non-reversible
What needs to be done to acceptably implement Auto-boxing with large number of channels
Broader parallelization of minor cycle for MS-MFS
--
JamesRobnett
- 2011-10-03
E
dit
|
A
ttach
|
P
rint version
|
H
istory
: r1
|
B
acklinks
|
V
iew wiki text
|
Edit
w
iki text
|
M
ore topic actions
Topic revision: r1 - 2011-10-03,
JamesRobnett
HPC
Log In
Register
HPC Web
Create New Topic
Index
Search
Changes
Notifications
Statistics
Preferences
Webs
ALMA
NAASC
SCIIPT
CDL
CICADA
Ccs
Littlethings
Cville
DSAA
EVLA
FASR
GB
Computing
Data
Dynamic
Electronics
Gbtpipeline
Knowledge
Mechanical
Observing
WbandVLBACal
Obsreports
Operate
PTCS
OOF
ServoImprovementsHome
ServoSiteAcceptTestProcs
Pennarray
Projects
Recreation
Scicenter
Skynet
Software
CLEO
StaffEvents
TACTool
HPC
JVLA
KPAF
Library
Main
Metrics
NGVLA
NM
Computing
Electronics
OSAA
OSX
SRDP
Software
Algorithms
CASA
Splat
System
VLBA
Copyright © by the contributing authors. All material on this collaboration platform is the property of the contributing authors.
Ideas, requests, problems regarding NRAO Public Wiki?
Send feedback