We investigate innovative computing systems and technologies that deliver high-performance, energy-efficiency, and adaptivity for various application domains and social needs. In particular, we develop algorithms and techniques for run-time decision-making targeting various optimization goals such as energy/power-efficiency, reliability, or compute performance, and considering various architectural platforms, such as high-performance compute nodes, reconfigurable systems, and power-constrained edge computing technologies. Our most recent research focuses on neuromorphic computing systems and platforms to support innovative brain-inspired computational paradigms. We currently conduct cutting-edge research encompassing the following:
- Adaptive neuromorphic computing systems
- Scalable fault-tolerant on-chip interconnects
- Reliable edge systems
- The use of modern machine learning techniques for designing fault-tolerant multicore architectures
- Heterogeneous architectures for acceleration-rich applications
- Future computing architectures and models, including deep neural networks, cognitive and edge computing.