You are here:
NRAO Public Wiki
>
HPC Web
>
CasaParallelization
>
CasaParallelMinutes20110711
(2011-07-18,
JamesRobnett
)
Edit
w
iki text
Edit
Attach
P
rint version
Casa Parallelization meeting minutes
Monday July 11thth Room 317, 3:30pm MDT
Attendees: James, Jeff, Sanjay, Kumar, Bryan, Simon Radcliffe
Targets/tasks for June 11th - July 17th
Discussion/Agenda
Simon Radcliffe from SKA sitting in
Workiing with Sanjay on GPU implementations
A/W projection and gridding
First target is getting convolution server working
Examine async thread failure problem
Jim/James
Memory resident subtables may help
Move subtables to in memory storage rather than storage manager
Jim
Work toward implementing streaming framework in applycal
Jim
deferred for subtable storage manager rework
Spectral imaging
Kumar
Parallelization status
Generates correct results
Performance issue putting images back together plane by plane is slow
Fixed
Issue with more processes than number of MSes
Complete parallel user interface frame work
Jeff/Honglin
In testing: flagging, calibration seem to work
Confusion with respect to memory consumption in pcont
Shoot for end of month to have a proto parallel script
Refine and distribute cluster scheduler interface
James
Re-addressing this week (this time for real), needs to be ready for proto parallel script above
Potentially use OODT on order of a month
Need 400+GB continuum case with complex field
Sanjay
3c147 in L band 8 hour observation set up by
Sanjay
Will still try to observe but may get replaced with a night time observation
Michel Brenjens may generate scheduling block
Test version of auto-flagging
Few weeks from suitable for testing
Parallel gridder testing
James
MS-MFS performance vs image size
James
Defer for now
Appears to be an L1-L2 cache issue on older systems (newer Nehalems have one cache line per core)
Consider other parallelization approaches
Fits to MS to Fits tile shape
Drop
Tsys table in uvexportfits brought up
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
- 2011-06-20
--
JamesRobnett
- 2011-07-18
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 - 2011-07-18,
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