Paper by U-M researchers recognized in IEEE Micro Top Picks
A paper authored by recent alum Tanvir Ahmed Khan (PhD CSE 2023) and Professor Baris Kasikci (now at University of Washington) has been recognized as one of IEEE Micro Top Picks from all of the computer architecture conference papers of 2022.
In OCOLOS: Online COde Layout OptimizationS, the authors propose OCOLOS, the first online code layout optimization system for unmodified applications written in unmanaged languages. The system allows “profile-guided optimization to be performed on a running process, instead of being performed offline and requiring the application to be relaunched.”
OCOLOS’s design can perform run-time code replacement safely for unmanaged programs, with essentially only fixed costs paid at code replacement time. By operating at run time, OCOLOS always profiles the most up-to date and relevant behavior of the program, and avoids problems with mapping the profile to a target binary that can frustrate offline profile-guided optimizations.
Top Picks is an annual special edition of IEEE Micro magazine that acknowledges the 10-12 most significant research papers from computer architecture conferences in the past year based on novelty and potential for long-term impact.
The authors included Khan and Kasikci, as well as Yuxuan Zhang (University of Pennsylvania), Giles Pokam (Intel Labs), Heiner Litz (University of California, Santa Cruz), and Joseph Devietti (University of Pennsylvania).