Rising Stars 2020:

Qijing Jenny Huang

PhD Candidate

University of California, Berkeley

Areas of Interest

  • Artificial Intelligence
  • Computer Architecture and Engineering


Co-optimization of Algorithms, Hardware, and Scheduling for Deep Learning Applications


In the past few years, researchers have increased the complexity of DNN models to achieve higher accuracy. Meanwhile, many-core architectures based around on-chip and on-package networks (NoC/NoP) continue to grow in capacity to meet the compute requirements of DNN workloads. Careful scheduling and mapping of complex DNN models on parallel hardware architectures have become a crucial step in achieving high performance and energy efficiency. However, there are significant challenges in jointly considering algorithms, scheduling, and hardware designs to achieve optimal solutions for accelerating deep learning tasks. On the algorithm side, we see the need to design more hardware-friendly models. On the hardware side, we see a need to shorten the hardware design cycle to keep up with the algorithm changes. In between, we see a need for optimal scheduling and scheduling-informed hardware design.

My research aims to co-optimize the full DNN acceleration stack through a three-pronged approach: 1) algorithm-hardware codesign, 2) a high-level synthesis (HLS) based hardware design methodology, and 3) hardware-constraint-driven scheduling and scheduling-informed hardware design. Our results demonstrate significant improvements in the end-to-end system performance while maintaining competitive model accuracy and with less design effort than would otherwise be needed.


Qijing Jenny Huang is a PhD student at the University of California, Berkeley, advised by Prof. John Wawrzynek. Her interests are in computer architecture, computer aided design, reconfigurable computing, and machine learning. She has been working on building efficient FPGA accelerators for emerging ML applications, HLS-based hardware/software flow, and ML-assisted HLS and compiler transformation. Her thesis work focuses on novel design and scheduling techniques for accelerating machine learning algorithms on heterogeneous spatial architecture. She received her B.A.Sc. in Electrical and Computer Engineering at the University of Toronto, where she was granted the University of Toronto Excellence Awards for her undergraduate research.

Personal home page