About

I am a second-year PhD student in the Electrical Engineering program at Drexel University.

My research focus is on "FPGA Virtualization for Neuromorphic Computing". FPGA accelerators are gaining increasing popularity in both cloud and edge computing because of their hardware flexibility, high computational throughput, and low power consumption. The virtualization of FPGAs becomes extremely important to create a useful abstraction of the hardware suitable for application development teams. Partial reconfiguration (PR) is a key technique for FPGA Virtualization. Partial Reconfiguration technology enables the inclusion of mutually exclusive functions during system operation at run-time in a single device. I believe that hardware-software co-design is the future of reconfigurable computing. I am gaining the most knowledge here, especially in neuromorphic computing, which is considered a niche area. From my perspective, my main motivation is that technology scaling is changing in fundamental ways. The overriding concern is power consumption, which will lead to more power-gating and more heterogeneous hard blocks in FPGAs. Thus, virtualized hardware can be created at this point, especially multi-FPGA virtualization to multiple users to program and use these computers simultaneously, with fairness and isolation guaranteed, setting user-specific priorities and policies in resource and memory management and porting applications developed on one hardware to new or future hardware, which may still be in development and not available. Virtualization of the hardware enables me to accomplish these goals, whereby hardware is partitioned into virtual machines (VMs), each with its own system software to perform scientific computations.