|
Fault-tolerant
On-chip Interconnects (2D/3D-ICs,
Si-Photonics, Hybrid)
Complex signal
processing systems-on-chip contain dozens
of components made of processor cores,
DSPs, memory, accelerators, and I/Os, all
integrated into a single die area of just
a few square millimeters. Such complex
systems need a novel on-chip interconnect
closer to a sophisticated network than
current bus-based solutions. This network
must provide high throughput and low
latency while keeping area and power
consumption low. We research
advanced interconnect technology for
embedded multicore SoCs targeting both FPGA
and ASIC platforms. In
particular, we investigate 3D-TVS
integration, fault tolerance methods,
photonic communication protocols,
low-power mapping techniques, and
low-latency adaptive routing.
Neuromorphic Algorithms
and Systems
Neuromorphic
computing uses spiking neuron network
models to solve machine learning problems
in a more power/energy-efficient way when
compared to the conventional artificial
neural networks.We research adaptive
low-power spiking neuromorphic systems and
SoCs empowered with our earlier developed
fault-tolerant three-dimensional on-chip
interconnect technology. In particular, we
investigate innovative
algorithms
and neuromorphic systems,
including adaptive configuration methods
to enable the reconfiguration of
different network parameters (spike
weights, routing, hidden layers,
topology, etc.), fault-tolerance,
thermal-aware mapping methods, and
on-line learning algorithms.
Applications of this research range from
a new brain-inspiring computing paradigm
to robotics
and edge
computing.
AI-Enabled Edge
& Automotive Computing
Driven
by the advances in AI, computer
architecture, and sensor technologies,
automobiles, including electric vehicles
(EVs) and self-driving cars, are
transforming into sophisticated automotive
computing platforms. As the advancement of
these computing systems accelerates, they
will be running a wide variety of
applications, including sensing,
navigation, etc., using specialized deep
neural network systems and complex
communication protocols (i.e., Ethernet,
SDVs) with safety and reliability support.
We study advanced low-power computing
systems and devices, including FPGA-AI-Chip based EV
energy management systems , EV campus energy
trading platform, and smart
programmable SoC and low-power
processors for edge and automotive
computing.
|
