Offloading Java to Graphics Processors

Add to your list(s) Download to your calendar using vCal

• Pete Calvert, Computer Laboratory
• Tuesday 07 September 2010, 14:00-14:30
• FW26, Computer Laboratory.

If you have a question about this talk, please contact Alan Mycroft.

Please note unusal time/place

Massively-parallel graphics processors have been largely inaccessible from higher-level languages such as Java. This work extracts and compiles portions of Java bytecode by making use of annotations to specify loops for parallel GPU execution. Data copying to and from the GPU is handled automatically. Evaluation shows that significant speedups could be achieved which were similar to those claimed by other less-automated work.

This is a practice talk for PACT 2010 .

This talk is part of the Computer Laboratory Programming Research Group Seminar series.

This talk is included in these lists:

• All Talks (aka the CURE list)
• Cambridge talks
• Computer Laboratory Programming Research Group Seminar
• Department of Computer Science and Technology talks and seminars
• FW26, Computer Laboratory
• Interested Talks
• School of Technology
• Trust & Technology Initiative - interesting events
• bld31

Note that ex-directory lists are not shown.