the access grid at vislab chris willing [email protected] vislab university of sydney,...
TRANSCRIPT
Today
• Background
• Differences to “traditional” vc
• Vislab Implementation – ATP
• Vislab Implementation – Physics
• Virtual Venues
• Differences to ANL implementation
• Future Work
Background
• VISLAB – visualisation, high perf. Computing
• Labs at Physics, ATP
• Bernard Pailthorpe at SDSC in 2000– High resolution displays– AG node
• Start April 2001 for SCGlobal, November 2001
Hyogo Prefecture (Japan) Police Hyogo Prefecture (Japan) Police Command Center - reference siteCommand Center - reference site
Tiled rear projection array of 6 Model 200 ILA Projectors
SmartSpaces, Stanford
Courtesy of Pat Hanrahan, CS - Stanford
PowerWall, Princeton
Courtesy of Kai Li, CS - Princeton
8x commodity projectors
High Density Tiled Display, SDSC
3x3 array with common light source
http://vis.sdsc.edu/research/tileddisplay.html
(Background)
• VISLAB – visualisation, high perf. Computing
• Labs at Physics, ATP
• Bernard Pailthorpe at SDSC in 2000– High resolution displays– AG node
• Start April 2001 for SCGlobal, November 2001
Display, VisLab 2001
3x1 array,
3840x1024 pixels,
single light source
Application in archaeology: Angkor
(Today)
• Background
• Differences to “traditional” vc
• Vislab Implementation – ATP
• Vislab Implementation – Physics
• Virtual Venues
• Differences to ANL implementation
• Future Work
Differences – 1. traditional
• Each node sends image stream(s) to MCU which decides what is output to each node
• TV style
Differences – 2. access grid
• Each node sends image streams to a multicast group address
• Each node sees all other sources
but if
“Each node sees all other sources”
then
screen overload
e.g.
10 other sites, each with 3 cameras
=> 30 video streams
Normal screen
First Access Grid session at USyd on 29 Aug, 2001
Widescreen 5120x1024
Normal screen
1280x1024
Summary of Differences
• limited vs. rich user experience
• complex (studio) vs. simple (pc)
• proprietary vs. open
• expensive vs. cheap
• but richness requires pixels
Technology diversion 1
Unicast
3 streams to 7 sites = 21 video streams
Efficient but who pays?
Multicast3 streams to 7 sites = 3 streams (mostly)
Today
• Background
• Differences to “traditional” vc
• Vislab Implementation – ATP
• Vislab Implementation – Physics
• Virtual Venues
• Differences to ANL implementation
• Future Work
Vislab Implementation (ATP)
display
video
audio
Gentner
cameras
mics PA
projectors(monitor)
Access Grid Sydney
Preparing for SC-Global: test “cruises” + A/G-Sydney
ATP display
Mon.
display
network
Projected display 3840x1024
ATP video capture
video
network
table
screen
mon.
camera
projectors
ATP audio capture
Gentner
Rx
audio
network
1x Radio mic
2x PZM
mon.
PA
Gentner – echo control
Site A Site B
echo delay due to - distance
- application buffering
Vislab Implementation (Physics)
Mon.
network
Projected display 2560x1024
2x cameras
Polycom
Soundstation
1x video
Virtual Venues
• ANL runs Virtual Venues Server
• APAG server at http://venues.ap-accessgrid.org
• Virtual rooms characterised by facilities– Video multicast group address– Audio multicast group address– MUD location (back channel link for participants)
• Linux only– stability– sync with vvd (not CORBA event handler)– potential for compute clustering (openMosix)
• Graphics cards (nVidia Quadro4)– use “well known” visualisation apps
e.g. performer, openInventor, openDX– potential for video clustering (chromium)
Differences to ANL
Video clustered AG
display
video
audio
Gentner
cameras 1
mics PA
2
3
monitor projectors
Performer with AG
High Resolution with AG
Future
• Video clustering, stereo viewing
• Shared event stream
• Higher resolution (PAL, HDTV)– H263, hardware MJPEG
• External machine capture
• Coexistence with H323 (via VRVS)
Links
•http://www.vislab.usyd.edu.au/research/accessgrid/•http://www.vislab.usyd.edu.au/research/display/•http://www.accessgrid.org•http://www.scglobal.org•http://vis.sdsc.edu/research/tileddisplay.html