Fast Object Tracking on a Many-Core Neural Network Chip

On-chip Network-enabled Many-core Architectures

On-Chip Network Designs for Many-Core Computational Platforms

Processor designers have been utilizing more processing elements (PEs) on a single chip to make efficient use of technology scaling and also to speed up system performance through increased parallelism. Networks on-chip (NoCs) have been shown to be promising for scalable interconnection of large numbers of PEs in comparison to structures such as point-to-point interconnects or global buses. Thi...

Convolutional Gating Network for Object Tracking

Object tracking through multiple cameras is a popular research topic in security and surveillance systems especially when human objects are the target. However, occlusion is one of the challenging problems for the tracking process. This paper proposes a multiple-camera-based cooperative tracking method to overcome the occlusion problem.  The paper presents a new model for combining convolutiona...

PHENIC: Towards Photonic 3D-Network-on-Chip Architecture for High-throughput Many-core Systems-on-Chip

Network-on-chip architectures can improve the scalability, performance, and power efficiency of general multiprocessor systems and application-specific heterogeneous multicore and many-core SoCs (MCSoCs). This interconnection paradigm when combined with 3D integration technology offers advantages over 2D NoC design, such as shorter wire length, higher packing density, and smaller footprint. How...

FAME: Financial Application with Many-core-on-a-chip architecturE

Research in financial derivatives is one of the important areas in computational finance. The computational requirements for solving models of financial derivatives such as the option pricing problem are huge and demand efficient algorithms and high performance computing capabilities. In this paper, we focus on the development of a Monte-Carlo algorithm with historic volatility and GARCH fitted...