CyLab Student Seminar

  • Robert Mehrabian Collaborative Innovation Center
  • 2201
  • Ph.D. Student
  • Department of Electrical and Computer Engineering
  • Carnegie Mellon University

Synchronization-based GPU Access Control

GPUs and other shared hardware accelerators are being increasingly used in computationally-intensive real-time and multimedia systems. Access control to the shared resource is a key aspect of system efficiency, and synchronization protocols such as the Multiprocessor Priority Ceiling Protocol (MPCP) and the FIFO-based Multiprocessor Locking Protocol (FMLP) have been found to be reasonably feasible in practice. However, these protocols assume that tasks may not suspend during execution on shared external resources such as a GPU. In such cases, busy-waiting for the entire critical-section duration significantly compromises CPU utilization. To avoid this problem, it is becoming useful in practice to extend synchronization protocols to allow suspensions within critical sections. In this paper, we extend MPCP to this particular context. We examine the feasibility and benefits of suspension-based MPCP over the original busy-waiting approach by presenting a case study on an NVIDIA TX2 embedded platform using real-world vision applications. Experimental results indicate that suspension-based MPCP can offer significantly lower response-times than the busy-waiting approach in practice, especially for lower-priority tasks, as it allows other tasks to use the CPU during critical section execution.

Iljoo Baek is a 2nd year Ph.D. student in the Department of ECE. His adviser is Prof. Ragunathan "Raj" Rajkumar. He currently researches Cooperative GPGPU Management for Real-Time Performance Efficiency and Predictability, and his research is supported by General Motors. He is also working on a Computer vision-based real-time perception system for CMU’s autonomous vehicle.  He has an MS in Robotics from RI CMU, as well as a Master's Concentration in wireless sensor network studies from Seoul National University.He worked more than 3 years for LG Electronics, conducting research in South Korea, on a perception system for autonomous vehicles.

This is a practice talk for his ECE Ph.D. Qualifying Exam talk.

For More Information, Please Contact: