Dan Lo

Dan Lo

Auto-generated profile, based on publicly available information

Dan Lo

CS, Kennesaw State University, Marietta, USA

Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

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

Representative Publications

View All Publications
18 April 2024
Verified
Conference Paper
Open access
NDNobel Dhar
Nobel Dhar
BDBobin Deng
Bobin Deng
DLDan Lo
Dan Lo
XWXiaofeng Wu
Xiaofeng Wu
Liang ZhaoLiang Zhao
Liang Zhao
KSKun Suo
Kun Suo
The success of ChatGPT is reshaping the landscape of the entire IT industry. The large language model (LLM) powering ChatGPT is experiencing rapid development, marked by enhanced features, improved accuracy, and reduced latency. Due to the execution overhead of LLMs, prevailing commercial LLM products typically manage user queries on remote servers. However, the escalating volume of user queries and the growing complexity of LLMs have led to servers becoming bottlenecks, compromising the quality of service (QoS). To address this challenge, a potential solution is to shift LLM inference services to edge devices, a strategy currently being explored by industry leaders such as Apple, Google, Qualcomm, Samsung, and others. Beyond alleviating the computational strain on servers and enhancing system scalability, deploying LLMs at the edge offers additional advantages. These include real-time responses even in the absence of network connectivity and improved privacy protection for customized or personal LLMs. This article delves into the challenges and potential bottlenecks currently hindering the effective deployment of LLMs on edge devices. Through deploying the LLaMa-2 7B model with INT4 quantization on diverse edge devices and systematically analyzing experimental results, we identify insufficient memory and/or computing resources on traditional edge devices as the primary obstacles. Based on our observation and empirical analysis, we further provide insights and design guidance for the next generation of edge devices and systems from both hardware and software directions.

14 September 2024 in ACM Transactions on Architecture and Code Optimization
Verified
Journal Article
Open access
BDBobin Deng
Bobin Deng
BNBhargava Nadendla
Bhargava Nadendla
KSKun Suo
Kun Suo
YXYixin Chloe Xie
Yixin Chloe Xie
DLDan Chia-Tien Lo
Dan Chia-Tien Lo
Residue Number Systems (RNS) demonstrate the fascinating potential to serve integer addition/ multiplication-intensive applications. The complexity of Artificial Intelligence (AI) models has grown enormously in recent years. From a computer system’s perspective, ensuring the training of these large-scale AI models within an adequate time and energy consumption has become a big concern. Matrix multiplication is a dominant subroutine in many prevailing AI models, with an addition/multiplication-intensive attribute. However, the data type of matrix multiplication within machine learning training typically requires real numbers, which indicates that RNS benefits for integer applications cannot be directly gained by AI training. The state-of-the-art RNS real-number encodings, including floating-point and fixed-point, have defects and can be further enhanced. To transform default RNS benefits to the efficiency of large-scale AI training, we propose a low-cost and high-accuracy RNS fixed-point representation: Single RNS Logical Partition (S-RNS-Logic-P) representation with Scaling-down Postprocessing Multiplication (SD-Post-Mul) . Moreover, we extend the implementation details of the other two RNS fixed-point methods: Double RNS Concatenation and S-RNS-Logic-P representation with Scaling-down Preprocessing Multiplication . We also design the architectures of these three fixed-point multipliers. In empirical experiments, our S-RNS-Logic-P representation with SD-Post-Mul method achieves less latency and energy overhead while maintaining good accuracy. Furthermore, this method can easily extend to the Redundant Residue Number System to raise the efficiency of error-tolerant domains, such as improving the error correction efficiency of quantum computing.

18 February 2025
Verified
Conference Paper
Open access
YSYong Shi
Yong Shi
DLDan Lo
Dan Lo
FUFlorida A&M university
Florida A&M university
APAndrew Polisetty
Andrew Polisetty
KSKun Suo
Kun Suo
Tu NguyenTu Nguyen
Tu Nguyen
Quantum-based Machine Learning (QML) combines quantum computing (QC) with machine learning (ML), which can be applied in various sectors, and there is a high demand for QML professionals. However, QML is not yet in many schools' curricula. We design labware for the basic concepts of QC, ML, and QML and their applications in science and engineering fields in Google Colab, applying a three-stage learning strategy for efficient and effective student learning.

24 April 2025
Verified
Conference Paper
Open access
SKShrikar Kolla
Shrikar Kolla
DLDan Lo
Dan Lo
CZChen Zhao
Chen Zhao

25 August 2016
Verified
Conference Paper
Closed access
YSYong Shi
Yong Shi
DLDan Lo
Dan Lo
KQKai Qian
Kai Qian
Cloud Computing is growing very fast and many universities are offering Cloud Computing courses on undergraduate and graduate levels, however, most of them are seminar type courses without hands-on learning experience for students. Hands-on learning, i.e. learning by doing is very crucial to help students understand better on the concepts of cloud computing such as security, task scheduling and network topology. In this paper, we propose to enhance Cloud Computing education with open source simulation tools such as CloudSim. We apply CloudSim to create labware for students to gain hands-on experience and understand different aspects of Cloud Computing more efficiently and effectively. The preliminary feedback on student learning outcomes is very encouraging.

1 July 2019
Verified
Conference Paper
Closed access
DLDan Lo
Dan Lo
KTKarl Kevin Tiba
Karl Kevin Tiba
SBSergiu Buciumas
Sergiu Buciumas
FZFrank Ziller
Frank Ziller
The maturity of the Big Data analytics allows enterprises to enhance their business processes using a data-driven approach. From retailers, E-commerce, risk analysis to pharmaceuticals, Bioinformatics, healthcare informatics, and others, business owners are thinking about mining business data into information for making better decisions to drive business value. However, the lack of reverse engineers and data analysts makes it harder for enterprises to apply Big Data analytics in their business data with a goal to enhance their operational processes. Ultimately, these processes can be automated to reduce human errors. In this paper, we study an empirical dataset containing real world service desk tickets using machine learning with a goal to automate and improve business processes, which will benefit to enterprises and customers in increasing quality of service.