On behalf of the entire Program Committee, it is our pleasure to present the final program of papers selected for CGO 2010. This year we received a total of 70 submissions. Program Committee members were provided the opportunity to "bid" on the papers to review. Each paper was assigned to 4 PC members, with an additional review assigned to an expert solicited by the Program Chairs. Each paper received on average 4.94 reviews. The entire review process was double-blind. Papers receiving reviews with large deviations were discussed by PC members through email prior to the Program Committee Meeting.
The CGO 2010 Program Committee Meeting was held in Boston, MA on Saturday November 7th. 27 of the 31 PC members attended in-person, with one person attending electronically. We particularly want to acknowledge those PC members that traveled long distances and internationally to be present at the meeting.
This year CGO received a high number of quality papers. 29 papers were selected for the final program. CGO continues to draw a high percentage of international submissions; 44.3% of the submissions had at least one author from outside of the US. CGO also maintained its tradition of drawing contributions from industry, with 14.3% of the submissions having at least one author from industry.
We are also happy to present two stimulating keynote talks from industry leaders. Ben Zorn from Microsoft Research will talk to us about a new definition of performance for future applications. CJ Newburn from Intel will present his perspectives on heterogeneous computing systems, and specifically the role that Intel technology will play. We thank our keynotes for agreeing to spend their time sharing their thoughts with the CGO community.
Performance is dead, long live performance!
In a world of social networking, security attacks, and hot mobile phones, the importance of application performance appears to have dimin-ished. My own research agenda has shifted from looking at the performance of memory allocation to building runtime ...
There are at least two sides to every heterogeneous system
Since there are at least two sides to every heterogeneous system, optimizing for heterogeneous systems is inherently an exercise in manag-ing complexity, balanced trade-offs and layering. Efforts to make the hardware simple may result in software ...