Post Date
Mar 7 2021

Dynamic Sharing is Caring

You must have heard parents teach their younger children that sharing is caring. Well, let’s just modify this a little bit to make it more relevant to our story: dynamic sharing is caring! But what is this all about!? Read on to find out!

We’re sure you’ve heard from that one friend about how powerful their shiny new computer is. Terms like processor, cores and multicore serve all but one purpose; to indicate speed and power of the system. However, the flaunt of a powerful system on paper renders useless when the distress of underperformance ensues. This is where the focus and attention shift from cosmetics of a product to its underlying ‘tech underbelly’, where the balance between performance and energy efficiency is the name of the game. One of the challenges in a computing system is to manage its cache effectively, so as to minimize energy utilization without affecting too much performance. Under the guidance of Dr. Muhammad Adeel Pasha (PhD advisor),Dr. Saad Zia Sheikh’s work focuses on these underlying details of a computing system.

Dr. Saad’s work mainly deals with management of shared caches, specifically devising a holistic solution for cache-aware system-level energy minimization while ensuring the schedulability for periodic tasks. Additionally, his work proposes a dynamic cache-partition schedulability analysis for multicore partitioned scheduling. This work hopes to manage the shared cache problem while also optimizing the energy consumed by the entire system.

We extend our heartiest congratulations to Dr. Saad Zia and his PhD advisor, Dr. Muhammad Adeel Pasha for this work. The following is a list of Dr. Saad’s published work.

 

Journal Papers:

  • S. Z. Sheikh and M. A. Pasha, "Energy-Efficient Multicore Scheduling for Hard RealTime Systems: A Survey," 2018, ACM Transactions in Embedded Computing Systems (TECS) 17, 6, Article 94, 26 pages. DOI: https://doi.org/10.1145/3291387
  • S. Z. Sheikh and M. A. Pasha, " Energy-efficient Real-time Scheduling on Multicores: A Novel Approach to Model Cache Contention,” 2020, ACM Transactions in Embedded Computing Systems (TECS). 19, 4, Article 28 ,25 pages. DOI: https://doi.org/10.1145/3399413
  • S. Z. Sheikh and M. A. Pasha, "Cache-Aware Energy-Efficient Scheduling on Heterogeneous Multicores" IEEE Transactions in Parallel and Distributed Systems (TPDS)
  • [Under Review]
  • S. Z. Sheikh and M. A. Pasha, "Dynamic Cache-Partition Schedulability Analysis for Partitioned Scheduling on Multicore Real-Time Systems. IEEE Letters of Computer Society (LOCS) [Early Access Available: https://ieeexplore.ieee.org/document/9162466]

 

Conference Papers:

  • S. Z. Sheikh and M. A. Pasha, "An Improved Model for System-Level Energy Minimization on Real-Time Systems," 2019, IEEE 27th International Symposium on Modeling, Analysis, and Simulation of Computer and Telecommunication Systems (MASCOTS), Rennes, FR, 2019, pp. 276-282. DOI: 10.1109/MASCOTS.2019.00039 [https://ieeexplore.ieee.org/document/8843101]