Anway Mukherjee
I am a senior embedded software engineer at Lucid Motors based in Newark, CA. I am working with the ADAS team to implement an over-the-air secure update framework through trusted execution environments (TEEs) in their flagship EV, Lucid Air, scheduled for release in February 2021.

I received my PhD from Virginia Tech, USA in 2019. I also worked under Dr. Tam Chantem as a Postdoctoral Associate at the RT-X Lab in Virginia Tech, Arlington, VA. Before that, I received my Bachelors degree in Electronics and Communication Engineering from West Bengal University of Technology, India. My research focused on energy-aware and resource-aware hardware-software co-design of real-time embedded systems, and embedded software and system security through TEEs.

Resume     Google Scholar     Github     LinkedIn


smartphones
Energy Management in Smartphones
While simultaneous side-by-side execution of multiple applications in split-screen mode on smartphones improves quality-of-service (QoS) for end-users, it also results in increased power consumption and reduced battery lifetime. Saving energy when multiple concurrent applications run side-by-side is extremely challenging since applications often utilize the same shared system resources at the same time, and resource needs change over time. We study and predict application usage patterns in smartphones (through static/dynamic profiling and ML techniques), and implement novel energy-aware resource management techniques through holistic DVFS frameworks in Android OS. [ES Week '18] [ICESS '20]
Top


smartphones
Optimizing Trusted Execution in Real-Time Systems
Trusted execution environments (TEE) provide industry standard security and isolation in IoTs but its implementation through secure monitor calls (SMC) attribute to large time overhead and weakened temporal predictability, potentially prohibiting the use of TEE in hard real-time systems. We explore solutions where multiple trusted execution sections are fused together to amortize TEE execution overhead and improve predictability through minimized I/O traffic and reduced switching between normal mode and TEE mode of execution. We also present techniques to enforce the correct timing requirement of a task, along with a sufficient test for schedulability in uniprocessors. [RTNS '19]
Top


smartphones

Resource-Aware Parallel Execution in Real-Time Systems
The federated scheduling framework is a popular multicore scheduling policy for parallel periodic real-time tasks that are often modeled as directed acyclic graphs (DAGs). However, it often over-estimates the processing requirements of parallel task execution, resulting in acute resource under-utilization of available processing capacity in an already resource-constrained system. We experiment to reduce resource under-utilization by proposing a task transformation mechanism where compatible DAG tasks are fused and transformed to opportunistically reclaim the usable utilization of the system. [ICESS '20]
Top

+1-435-881-4828     anwaym@vt.edu
© Anway Mukherjee, 2020