Research

I’m interested in the design and implementation of compilers and runtime systems for high level languages. My research spans memory management, concurrency, compilers, virtual machines, static analysis, and programming models. My advisors are Antony L. Hosking and Mathias Payer.


Projects:

Android Memory Management

Applications running on mobile devices, such as those based on the Android operating system and using the Dalvik virtual machine and Android RunTime , increasingly rely on automatic memory management. Most prior work on memory management for virtual-machine based systems has focused on server environments and workloads.

Mobile devices must conserve power while still providing the desired responsiveness and throughput. This offers new dimensions for the evaluation of the Virtual Machine (VM) for devices that rely on a managed run-time. Garbage collection (GC) significantly contributes to total on-chip energy consumption. The work being funded by Qualcomm develops tools for understanding the memory behavior of Android apps, and for characterizing the performance of the VM memory managers, leading to development of new techniques for memory management that address both energy constraints  and opportunities for improved performance.

Slides TechReport 2015


Publications:

  • “One Process to Reap Them All: Garbage Collection as-a-Service”. Hussein, A., Payer, M., Hosking, A. L., & Vick, C. A. In proceedings of the 13th ACM SIGPLAN/SIGOPS International Conference on Virtual Execution Environments (VEE’17). Xi’an, China.
    ISBN: 978-1-4503-4948-2/17/04

    DOI  Slides
  • “Impact of GC Design on Power and Performance for Android”. Hussein, A., Payer, M., Hosking, A. L., & Vick, C. A. In ACM International Systems and Storage Conference. Haifa, Israel. 2015.
    PDF DOI
  • “Don’t Race the Memory Bus: Taming the GC Leadfoot”. Hussein, A., Hosking, A. L., Payer, M., & Vick, C. A. In proceedings of the ACM SIGPLAN International Symposium on Memory Management. Portland, Oregon. 2015.
    PDF DOI Slides
  • “X10 on the Single-Chip Cloud Computer”. Chapman, K., Hussein, A., & Hosking, A. L. In PLDI X10 Workshop (pp. 7:1–8). San Jose, California. 2011.
    PDF DOI
Advertisements