Skip to Content
My MSU

Registration services will be closed on Monday, Dec 15th at 11:59 PM and will reopen on Wednesday, Dec 17th, at 12:01 AM. This pause is necessary to ensure data integrity during Canvas roster maintenance.



Idris Somoye

Idris Somoye

Assistant Professor,

Office: Scheafer 233
idris.somoye@morgan.edu

View More

Education:

Dr. Somoye is an assistant professor at Morgan State University. He received his B.S in electrical and computer engineering from Morgan State University, his M.S. in electrical engineering from the Georgia Institute of Technology, and his PhD in computer engineering from the University of New Mexico.

He has expertise in digital design and verification for ASIC and FPGA platforms with a focus on high-speed links and multi-sensor integration. Dr. Somoye has extensive experience in creating advanced digital designs for government agencies and contractors, with prior performance supporting programs such as digital controllers for non-conventional weapons, low-latency PCIe designs, multi-gigabit Ethernet designs, and side-channel resistant cryptographic cores.

Additionally, Dr. Somoye is highly skilled in ASIC physical design and layout, adept at efficient implementation of complex digital architectures in manufacturable silicon solutions, and has experience utilizing EDA tools across the entire design flow, from RTL to GDSII. His research interests include AI/ML hardware acceleration and emulation-based hardware verification & security.

Dr. Somoye founded and leads the Open Hardware Acceleration Lab (HAL-O) at Morgan State. HAL-O's key mission is to remove the barriers between AI researchers and the real-time implementation of their ideas. An initial component of this effort is the development of an open-source PCIe Gen1 endpoint controller designed specifically for GPU acceleration on Edge computing platforms. This controller enables efficient high-speed data transfer between Accelerators and host systems, making it a critical enabler for deploying AI models at the edge with minimal latency.