Ziru Li

Ziru Li

Auto-generated profile, based on publicly available information

Ziru Li

Department of Electrical and Computer Engineering, Duke University, Durham, NC, USA

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
6 February 2025 in IEEE Circuits and Systems Magazine
Verified
Journal Article
Closed access
CGCong Guo
Cong Guo
FCFeng Cheng
Feng Cheng
ZDZhixu Du
Zhixu Du
JKJames Kiessling
James Kiessling
JKJonathan Ku
Jonathan Ku
YCYiran Chen
Yiran Chen
The rapid development of large language models (LLMs) has significantly transformed the field of artificial intelligence, demonstrating remarkable capabilities in natural language processing and moving towards multi-modal functionality. These models are increasingly integrated into diverse applications, impacting both research and industry. However, their development and deployment present substantial challenges, including the need for extensive computational resources, high energy consumption, and complex software optimizations. Unlike traditional deep learning systems, LLMs require unique optimization strategies for training and inference, focusing on system-level efficiency. This paper surveys hardware and software co-design approaches specifically tailored to address the unique characteristics and constraints of large language models. This survey analyzes the challenges and impacts of LLMs on hardware and algorithm research, exploring algorithm optimization, hardware design, and system-level innovations. It aims to provide a comprehensive understanding of the trade-offs and considerations in LLM-centric computing systems, guiding future advancements in AI. Finally, we summarize the existing efforts in this space and outline future directions toward realizing production-grade co-design methodologies for the next generation of large language models and AI systems.

19 April 2022 in IEEE Transactions on Circuits and Systems II: Express Briefs
Verified
Journal Article
Closed access
BTBrady Taylor
Brady Taylor
QZQilin Zheng
Qilin Zheng
ZLZiru Li
Ziru Li
SLShiyu Li
Shiyu Li
YCYiran Chen
Yiran Chen
Due to the need for computing models that can process large quantities of data efficiently and with high throughput in many state-of-the-art machine learning algorithms, the processing-in-memory (PIM) paradigm is emerging as a potential replacement for standard digital architectures on these workloads. In this tutorial, we review the progress of PIM technology in recent years, at both the circuit and architecture level. We further present an analysis of when and how PIM technology surpasses the performance of conventional architectures. Finally, we outline our vision for the future of PIM technology.

16 March 2020 in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
Verified
Journal Article
Closed access
ZLZiru Li
Ziru Li
BLBing Li
Bing Li
ZFZichen Fan
Zichen Fan
HLHai Li
Hai Li

4 September 2024 in IEEE Transactions on Circuits and Systems for Artificial Intelligence
Verified
Journal Article
Closed access
ZLZiru Li
Ziru Li
QZQilin Zheng
Qilin Zheng
JKJonathan Ku
Jonathan Ku
BTBrady Taylor
Brady Taylor
HLHai Helen Li
Hai Helen Li
Spiking neural networks (SNNs) have shown high efficiency in information processing. Time-to-first-spike (TTFS) coding, which encodes the information to the times of first spikes, has been introduced in SNNs due to its simple data representation. However, there is a lack of studies in synapse mapping and neuron circuits for compute-in-memory (CIM) neuromorphic design for low-power TTFS-based SNN inference. This work presents a CIM neuromorphic processing engine for TTFS-based SNNs, which comprises a 64x64 8T-SRAM array for synapse storage and current-based post-neuron circuits. We propose to map the positive and negative synaptic weights to adjacent columns in the SRAM array and accumulate the membrane potential in the dedicated post-neuron circuits. Two techniques are presented through hardware-software co-design: ”Multi-Level Firing Threshold Adjustment” to mitigate the impact of process variations, and “Timing Threshold Adjustment” to further speed up the computation. The proposed processing engine achieves the energy efficiency 249.8 TOPS/W under 8-bit inputs and signed 4-bit weights.

10 January 2023 in IEEE Transactions on Circuits and Systems II: Express Briefs
Verified
Journal Article
Closed access
ZLZiru Li
Ziru Li
QZQilin Zheng
Qilin Zheng
YCYiran Chen
Yiran Chen
HLHai Li
Hai Li
In-sensor-processing (ISP) paradigm has been exploited in state-of-the-art vision system designs to pave the way towards power-efficient sensing and processing. The redundant data transmission between sensors and processors is significantly minimized by local computation within each pixel. However, existing ISP designs suffer from limited frame rates and degraded fill factors. In this paper, we introduce a low-latency in-sensorintelligence neuromorphic vision system using neuromorphic spiking neurons, namely SpikeSen. SpikeSen directly operates on the photocurrents and executes the computation in the frequency domain, reducing the long exposure time and speeding up the computation. Experiments show that SpikeSen can achieve more than 6.1× computation speedup compared to existing ISP designs with competitive energy consumption per pixel.

23 June 2024
Verified
Conference Paper
Open access
QZQilin Zheng
Qilin Zheng
ZLZiru Li
Ziru Li
JKJonathan Ku
Jonathan Ku
YWYitu Wang
Yitu Wang
BTBrady Taylor
Brady Taylor
YCYiran Chen
Yiran Chen
Analog in-memory-computing (IMC) is an attractive technique with a higher energy efficiency to process machine learning workloads. However, the analog computing scheme suffers from large interface circuit overhead. In this work, we propose a macro with a hybrid analog-digital mode computation to reduce the precision requirement of the interface circuit. Considering the distribution of the multiplication and accumulation (MAC) value, we propose a nonlinear transfer function of the computing circuits by only accurately computing low MAC value in the analog domain with a digital mode to deal with the high MAC value with smaller possibility. Silicon measurement results show that the proposed macro could achieve 160 GOPS/mm2 area efficiency and 25.5 TOPS/W for 8b/8b matrix computation. The architectural-level evaluation for real workloads shows that the proposed macro can achieve up to 2.92× higher energy efficiency than conventional analog IMC designs.