Z
Zhenhong Liu
Researcher at University of Illinois at Urbana–Champaign
Publications - 8
Citations - 231
Zhenhong Liu is an academic researcher from University of Illinois at Urbana–Champaign. The author has contributed to research in topics: Multiplier (economics) & Efficient energy use. The author has an hindex of 6, co-authored 8 publications receiving 168 citations. Previous affiliations of Zhenhong Liu include University of Wisconsin-Madison & Wisconsin Alumni Research Foundation.
Papers
More filters
Journal ArticleDOI
Energy-Efficient Approximate Multiplication for Digital Signal Processing and Classification Applications
TL;DR: This brief proposes multiplier architectures that can tradeoff computational accuracy with energy consumption at design time and demonstrates that such a small computational error does not notably impact the quality of DSP and the accuracy of classification applications.
Journal ArticleDOI
SiMul: An Algorithm-Driven Approximate Multiplier Design for Machine Learning
TL;DR: The proposed approximate multiplier, SiMul, features user-controlled precision that exploits the common characteristics of ML algorithms, and supports a tradeoff between compute precision and energy consumption at runtime, reducing the energy consumption of the accelerator while satisfying a desired inference accuracy requirement.
Proceedings ArticleDOI
G-Scalar: Cost-Effective Generalized Scalar Execution Architecture for Power-Efficient GPUs
TL;DR: G-Scalar is a cost-effective generalized scalar execution architecture for GPUs that improves power efficiency and power efficiency by 24% and 15%, respectively, at a negligible cost.
Journal ArticleDOI
Ultra-low-power image signal processor for smart camera applications
TL;DR: This chapter starts with the intuition that the perceptive quality of images is not strongly correlated with the accuracy of object detection algorithms and proposes three techniques that require only minor modifications to the baseline ISP but dramatically reduce the ISP energy consumption in object detection mode for smart camera applications.
Proceedings ArticleDOI
Load-Triggered Warp Approximation on GPU
TL;DR: This work proposes Lock 'n Load (LnL) which triggers approximate execution of code regions by only checking similarity of values returned from load instructions and fuses multiple approximated warps into a single warp.