Transformative Computer Systems and Architecture Research Lab (TeCSAR)
With the continuous growth in the complexity of deep learning and machine learning algorithms, the demand for novel computer architecture and system-level design paradigms is a most. At TeCSAR, we focus on transformative design methodologies, system-level modeling and computer hardware design for emerging machine learning and deep learning algorithms. The general roadmap of TeCSAR is algorithm/architecture codesign by offering novel scalable design tools and methodologies to bring algorithm-awareness in hardware design and enable rapid architecture design space exploration and prototyping. At the same time, we develop novel domain-specific computer architecture to reconcile the hardware programming flexibility and execution efficiency. At TeCSAR lab, Faculty, researchers, and students enable high-performance energy-efficient execution of a broad range of data-intensive numerical problems including scientific computing, graph processing, computer vision, and deep learning.
Primary Faculty: Hamed Tabkhi
Collaborators: Arun Ravindran (ECE), Andrew Willis (ECE), Babak Parkhideh (ECE), Omid Shoghli (ETCM), James Conrad (ECE), Amirhossein Ghassemi (MEES) and Gunar Schirner (ECE, Northeastern University)
Location: EPIC 2143
Website: https://coefs.uncc.edu/htabkhiv/