Skip to main content
Video s3
    Details
    Presenter(s)
    Yang-Ming Yeh Headshot
    Display Name
    Yang-Ming Yeh
    Affiliation
    Affiliation
    National Taiwan University
    Country
    Author(s)
    Display Name
    Shih-Shiuan Weng
    Affiliation
    Affiliation
    National Taiwan University
    Display Name
    Yang-Ming Yeh
    Affiliation
    Affiliation
    National Taiwan University
    Display Name
    Yu-Cheng Li
    Affiliation
    Affiliation
    Academia Sinica
    Display Name
    Yi-Chang Lu
    Affiliation
    Affiliation
    National Taiwan University
    Abstract

    The Zuker algorithm is a widely-adopted method in rapid prediction of RNA secondary structure. In this work, we present a new hardware architecture based on the algorithm and implement its accelerator using TSMC 40-nm technology. The proposed architecture is capable of handling more dangling types than previous hardware work. Besides, with better data re-use, the idling time and memory usage of our hardware modules can be effectively reduced, and thus a higher processing speed can be achieved. Compared to the well-known software approach, RNAstructure, our 16-PE design has an 11X speedup for RNA sequences around 3000 bases.

    Slides
    • An Alignment-Based Hardware Accelerator for Rapid Prediction of RNA Secondary Structures (application/pdf)