About

Tony Givargis is a Professor and Department Chair in the Department of Computer Science at UC Irvine's Donald Bren School of Information & Computer Sciences. He conducts research in the area of software for embedded systems, focusing on issues related to Realtime Operating System (RTOS) synthesis, serializing compilers, and code transformation techniques for efficient software to hardware migration. He holds a Ph.D. in Computer Science from UC Riverside. His work involves studying various aspects of computer system definition, design, and optimization, contributing to the advancement of embedded systems and computing technologies.

Research topics

• Computer Science
• Artificial Intelligence
• Machine Learning
• Engineering
• Internal medicine
• Theoretical computer science
• Medicine
• Pathology
• Computer Security
• Human–computer interaction
• Systems engineering
• Software engineering
• World Wide Web
• Embedded system
• Communication
• Radiology
• Programming language
• Multimedia
• Mathematical optimization
• Distributed computing
• Computer network
• Intensive care medicine
• Psychology
• Mathematics

Selected publications

• Approximating Tensor Network Contraction with Sketches

  ArXiv.org · 2026-03-08

  articleOpen access

  Tensor network contraction is a fundamental mathematical operation that generalizes the dot product and matrix multiplication. It finds applications in numerous domains, such as database systems, graph theory, machine learning, probability theory, and quantum mechanics. Tensor network contractions are computationally expensive, in general requiring exponential time and space. Sketching methods include a number of dimensionality reduction techniques that are widely used in the design of approximation algorithms. The existing sketching methods for tensor network contraction, however, only support acyclic tensor networks. We present the first method capable of approximating arbitrary tensor network contractions, including those of cyclic tensor networks. Additionally, we show that the existing sketching methods require a computational complexity that grows exponentially with the number of contractions. We present a second method, for acyclic tensor networks, whose space and time complexity depends only polynomially on the number of contractions.

  PublisherOA PDF

• Approximating Tensor Network Contraction with Sketches

  Open MIND · 2026-03-08

  preprint

  Tensor network contraction is a fundamental mathematical operation that generalizes the dot product and matrix multiplication. It finds applications in numerous domains, such as database systems, graph theory, machine learning, probability theory, and quantum mechanics. Tensor network contractions are computationally expensive, in general requiring exponential time and space. Sketching methods include a number of dimensionality reduction techniques that are widely used in the design of approximation algorithms. The existing sketching methods for tensor network contraction, however, only support acyclic tensor networks. We present the first method capable of approximating arbitrary tensor network contractions, including those of cyclic tensor networks. Additionally, we show that the existing sketching methods require a computational complexity that grows exponentially with the number of contractions. We present a second method, for acyclic tensor networks, whose space and time complexity depends only polynomially on the number of contractions.

  DOI

• Always-Sparse Training by Growing Connections with Guided Stochastic Exploration

  2025-06-30 · 1 citations

  article

  The excessive computational requirements of modern artificial neural networks (ANNs) are posing limitations on the machines that can run them. Sparsification of ANNs is often motivated by time, memory and energy savings only during model inference, yielding no benefits during training. A growing body of work is now focusing on providing the benefits of model sparsification also during training. While these methods greatly improve the training efficiency, the training algorithms yielding the most accurate models still materialize the dense weights, or compute dense gradients during training. We propose an efficient, always-sparse training algorithm with excellent scaling to larger and sparser models, supported by its linear time complexity with respect to the model width during training and inference. Moreover, our guided stochastic exploration algorithm improves over the accuracy of previous sparse training methods. We evaluate our method on the CIFAR-10/100 and ImageNet classification tasks using ResNet, VGG, and ViT models, and compare it against a range of sparsification methods<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">3</sup>.

  PublisherDOI

• Learning encoding phasors with fractional power encoding

  2025-03-28

  articleSenior author

  Hyperdimensional Computing (HDC), also Hyperdimensional Computing (HD), also known as Vector Symbolic Architectures (VSA), operates in high-dimensional vector spaces for symbolic processing. Within HD, Fractional Power Encoding (FPE), also referred to as Random Fourier Features, is a method that creates randomized data representations by exponentiating random base vectors. In this paper, we evaluate the application of FPE for classification tasks. We focus on the Fourier Holographic Reduced Representation (FHRR) within this framework. We investigate the use of various probability distributions for sampling to generate the basis hypervectors for FPE. Our findings indicate that distributions from the generalized hyperbolic family, such as Laplace, Cauchy, Student-t, and Gaussian, are more effective in capturing information during encoding. Furthermore, we propose two novel models for classification. Each model begins by determining an optimal bandwidth to achieve high accuracy. The first model, inspired by Fourier Series, generates an encoding by accumulating different bandwidths. Both models employ Stochastic Gradient Descent (SGD) to learn encodings tailored to specific applications. This approach enables the models to generate application-specific kernels, resulting in higher accuracy. Our models outperforms the current state-of-the-art in Hyperdimensional Computing in 121 datasets on accuracy, memory usage, training time and inference time allowing for achieving better results in embedded devices. Furthermore our results outperform Support Vector Machines (SVM) on accuracy.

  PublisherDOI

• FlashMap: A Flash Optimized Key-Value Store

  ArXiv.org · 2025-11-11

  preprintOpen accessSenior author

  Key-value stores are a fundamental class of NoSQL databases that offer a simple yet powerful model for data storage and retrieval, representing information as pairs of unique keys and associated values. Their minimal structure enables exceptionally fast access times, scalability, and flexibility in storing diverse data types, making them ideal for high-performance applications such as caching, session management, and distributed systems. As modern computing increasingly demands responsiveness and scalability, key-value stores have become a critical component of the data infrastructure in both industry and research contexts. In this work, we present FlashMap, a high-performance key-value store optimized for Flash-based solid-state drives (SSDs). Experiments show that FlashMap achieves outstanding throughput, averaging 19.8 million inserts and 23.8 million random lookups per second with a 100-byte payload, all on a single data center-grade server.

  PublisherOA PDFDOI

• Classification using hyperdimensional computing: a review with comparative analysis

  Artificial Intelligence Review · 2025-03-17 · 11 citations

  reviewOpen access

  Abstract Hyperdimensional computing (HD), also known as vector symbolic architectures (VSA), is an emerging and promising paradigm for cognitive computing. At its core, HD/VSA is characterized by its distinctive approach to compositionally representing information using high-dimensional randomized vectors. The recent surge in research within this field gains momentum from its computational efficiency stemming from low-resolution representations and ability to excel in few-shot learning scenarios. Nonetheless, the current literature is missing a comprehensive comparative analysis of various methods since each of them uses a different benchmark to evaluate its performance. This gap obstructs the monitoring of the field’s state-of-the-art advancements and acts as a significant barrier to its overall progress. To address this gap, this review not only offers a conceptual overview of the latest literature but also introduces a comprehensive comparative study of HD/VSA classification methods. The exploration starts with an overview of the strategies proposed to encode information as high-dimensional vectors. These vectors serve as integral components in the construction of classification models. Furthermore, we evaluate diverse classification methods as proposed in the existing literature. This evaluation encompasses techniques such as retraining and regenerative training to augment the model’s performance. To conclude our study, we present a comprehensive empirical study. This study serves as an in-depth analysis, systematically comparing various HD/VSA classification methods using two benchmarks, the first being a set of seven popular datasets used in HD/VSA and the second consisting of 121 datasets being the subset from the UCI Machine Learning repository. To facilitate future research on classification with HD/VSA, we open-sourced the benchmarking and the implementations of the methods we review. Since the considered data are tabular, encodings based on key-value pairs emerge as optimal choices, boasting superior accuracy while maintaining high efficiency. Secondly, iterative adaptive methods demonstrate remarkable efficacy, potentially complemented by a regenerative strategy, depending on the specific problem. Furthermore, we show how HD/VSA is able to generalize while training with a limited number of training instances. Lastly, we demonstrate the robustness of HD/VSA methods by subjecting the model memory to a large number of bit-flips. The results illustrate that the model’s performance remains reasonably stable until the occurrence of 40% of bit flips, where the model’s performance is drastically degraded. Overall, this study performed a thorough performance evaluation on different methods and, on the one hand, a positive trend was observed in terms of improving classification performance but, on the other hand, these developments could often be surpassed by off-the-shelf methods. This calls for better integration with the broader machine learning literature; the developed benchmarking framework provides practical means for doing so.

  PublisherOA PDFDOI

• ANON: A Task Scheduler in Source Code for Teaching and Implementing Concurrent or Real-Time Software

  2024-02-06

  articleSenior author

  Abstract We describe the design and decade-long use of an approach for executing concurrent tasks on a microprocessor without the need for a real-time operating system. We wrote a lightweight non-preemptive task scheduler, called RIOS. The task scheduler is written in C, but that can be implemented in languages like C++, Java, Python, Javascript, etc., rather than in assembly as is commonplace. As such, RIOS can be copy-pasted directly into a project's source code, and modified as desired. The scheduler code includes a structure to hold features of a periodic task like its period and elapsed time since previous execution, an array to hold all tasks, a technique for using a timer and interrupt-service routine (ISR) to keep time, and code to actually call each task at the appropriate time. We describe the core features of RIOS, and its successful usage in embedded systems courses, enabling students to build powerful concurrent-tasks systems correctly and quickly. Students can extend RIOS to further learn real-time concepts, such as including a deadline per task, or creating alternative scheduling algorithms such as rate monotonic, earliest-deadline-first scheduling, or round-robin scheduling. Students can also add functionality to analyze task execution behavior, such as calculating processor utilization or task jitter. As such, students can learn first-hand how the scheduler piece of a real-time operating system operates. Via aggressive code rewriting and minimization over several years, we reduce RIOS's entire code size to just a few dozen lines. RIOS is currently used by dozens of universities to teach real-time software concepts, reaching thousands of students per year. RIOS is also used by hundreds of practicing embedded systems engineers as well, resulting in faster implementation time and much smaller code size than the alternative of linking in a real-time operating system. RIOS is downloadable for free at https://www.cs.ucr.edu/~vahid/rios/.

  PublisherDOI

• Molecular Classification Using Hyperdimensional Graph Classification

  2024-06-30 · 4 citations

  article

  Our work introduces an innovative approach to graph learning by leveraging Hyperdimensional Computing. Graphs serve as a widely embraced method for conveying information, and their utilization in learning has gained significant attention. This is notable in the field of chemoinformatics, where learning from graph representations plays a pivotal role. An important application within this domain involves the identification of cancerous cells across diverse molecular structures. We propose an HDC-based model that demonstrates comparable Area Under the Curve results when compared to state-of-the-art models like Graph Neural Networks (GNNs) or the Weisfieler-Lehman graph kernel (WL). Moreover, it outperforms previously proposed hyperdimensional computing graph learning methods. Furthermore, it achieves noteworthy speed enhancements, boasting a 40x acceleration in the training phase and a 15x improvement in inference time compared to GNN and WL models. This not only underscores the efficacy of the HDC-based method, but also highlights its potential for expedited and resource-efficient graph learning.

  PublisherDOI

• Molecular Classification Using Hyperdimensional Graph Classification

  arXiv (Cornell University) · 2024-03-18 · 2 citations

  preprintOpen access

  Our work introduces an innovative approach to graph learning by leveraging Hyperdimensional Computing. Graphs serve as a widely embraced method for conveying information, and their utilization in learning has gained significant attention. This is notable in the field of chemoinformatics, where learning from graph representations plays a pivotal role. An important application within this domain involves the identification of cancerous cells across diverse molecular structures. We propose an HDC-based model that demonstrates comparable Area Under the Curve results when compared to state-of-the-art models like Graph Neural Networks (GNNs) or the Weisfieler-Lehman graph kernel (WL). Moreover, it outperforms previously proposed hyperdimensional computing graph learning methods. Furthermore, it achieves noteworthy speed enhancements, boasting a 40x acceleration in the training phase and a 15x improvement in inference time compared to GNN and WL models. This not only underscores the efficacy of the HDC-based method, but also highlights its potential for expedited and resource-efficient graph learning.

  PublisherOA PDFDOI

• Smartwatch-Based Prediction of Transdermal Alcohol Levels Using Hyperdimensional Computing

  2024-11-10

  article

  Excessive alcohol consumption was responsible for 6% of global deaths in 2023. To encourage healthier drinking habits and enhance user awareness of their current condition, just-in-time interventions prove to be a suitable approach for informing users about their current state of intoxication. Current methods for determining blood alcohol content are intrusive and many also invasive, requiring users to use breathalizers or actively engage in urine or blood tests. In this study, we introduce an application utilizing Hyperdimensional Computing to predict if a user is under the influence of alcohol, achieving an accuracy of 93.5% on average. Furthermore, this application is designed to run on both smartphones and smartwatches, enabling full on device computation and online learning through a C implementation utilizing vectorial operations. The application has shown to be very efficient, having a training time per instance of 13.2 and 1.25ms on smartwatch and smartphone respectively and inference time of 6.8 and 1.1ms. Moreover the energy consumption of the running application is negligible compared to the energy usage of the idle device.

  PublisherDOI

Recent grants

• CSR: Small: Collaborative Research: Synthesis of Time-Controllable Digital Mockups of Physical Systems

  NSF · $200k · 2010–2014

• Collaborative Research: Integrating Time-Oriented Embedded System Programming into a Computing Curriculum

  NSF · $70k · 2009–2011

• SGER: A Virtual Target For Next Generation Hardware Accelerated Multi-Core Systems

  NSF · $200k · 2008–2009

Frequent coauthors

• Frank Vahid

  University of California, Riverside

  59 shared

• Alexandru Nicolau

  23 shared

• Steffen Peter

  University of California, Irvine

  21 shared

• Mike Heddes

  18 shared

• Jörg Henkel

  14 shared

• Bailey Miller

  University of California, Riverside

  11 shared

• André C. Nácul

  University of California, Irvine

  9 shared

• Pere Vergés

  9 shared