Article
Computer Science, Information Systems
Md Rafiul Kabir, Bhagawat Baanav Yedla Ravi, Sandip Ray
Summary: A virtual prototyping environment called ViVE is developed for the modeling and simulation of vehicular systems. This platform emphasizes coordination and communication among various vehicular components and allows exploration of system-level interactions. It demonstrates its utility in real-time in-vehicle communication optimization and vehicular security analysis.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Artificial Intelligence
Peisong Wang, Fanrong Li, Gang Li, Jian Cheng
Summary: In this article, the advantages of extremely sparse networks with binary connections for image classification through software-hardware codesign are investigated. A binary augmented extremely pruning method is proposed to achieve high sparsity with minimal accuracy degradation, and a hardware architecture based on the resulting sparse and binary networks is designed to explore the benefits of extreme sparsity with negligible consumption. Experiments on ImageNet classification and FPGA demonstrate a significant tradeoff between accuracy and efficiency in the proposed software-hardware architecture.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Xin Zheng, Junwei Wu, Xian Lin, Huaien Gao, Suting Cai, Xiaoming Xiong
Summary: This paper proposes a virtual prototype with integrated cryptographic accelerators for a cryptographic SoC based on RISC-V, to accelerate the functional and performance simulation of the SoC. The virtual prototype is designed using an efficient HW/SW co-design approach and features flexible interface and core timing model, achieving simulation speeds much faster than RTL simulation.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS II-EXPRESS BRIEFS
(2023)
Article
Computer Science, Hardware & Architecture
Cuong Pham-Quoc, Xuan-Quang Nguyen, Tran Ngoc Thinh
Summary: In recent years, AI-based applications have become more prevalent in various fields. However, the computing power required for AI applications exceeds the capabilities of most edge computing systems. This research proposes a hardware/software co-design framework that utilizes FPGA technology to accelerate CNN-based edge computing applications. Experimental results show significant speed-ups compared to traditional processors.
MOBILE NETWORKS & APPLICATIONS
(2022)
Article
Engineering, Electrical & Electronic
He Li, Yongming Tang, Zhiqiang Que, Jiliang Zhang
Summary: Advances in quantum information processing technology have led to the emergence of advanced cryptography in the post-quantum era. Next generation cryptographic techniques aim to resist known attacks related to quantum computing and be easily implemented on traditional hardware platforms. This article surveys recent developments in FPGA-based implementations of post-quantum cryptography and highlights the challenges and potential research directions in this promising field.
IEEE TRANSACTIONS ON NANOTECHNOLOGY
(2022)
Article
Computer Science, Hardware & Architecture
Iulian Brumar, Georgios Zacharopoulos, Yuan Yao, Saketh Rama, David Brooks, Gu-Yeon Wei
Summary: Post-Moore's law systems rely on accelerators for performance enhancements. AccelMerger is an automated methodology that creates coarse-grained, merged accelerators with control and data flow. It uses sequence alignment matching and neural networks to identify functions to accelerate and merge accelerators within an area budget.
ACM TRANSACTIONS ON EMBEDDED COMPUTING SYSTEMS
(2023)
Article
Automation & Control Systems
Xiaoxuan Yang, Changming Wu, Mo Li, Yiran Chen
Summary: This review discusses the current approaches to tolerating noise effects in processing-in-memory (PIM) systems. PIM architecture is considered a promising solution for reducing communication cost between storage and computing units, but noises generated from memory and peripheral circuits pose challenges. The review explains noise-tolerant strategies for PIM systems based on resistive random-access memory (ReRAM) and presents case studies for generative adversarial networks and physical neural networks.
ADVANCED INTELLIGENT SYSTEMS
(2022)
Article
Computer Science, Hardware & Architecture
Sivert T. Sliper, William Wang, Nikos Nikoleris, Alex S. Weddell, Anand Savanth, Pranay Prabhat, Geoff V. Merrett
Summary: Intermittent computing is essential for the Internet of Things, allowing devices to perform computation using harvested energy when available. Nonvolatile memory is crucial for retaining computational progress across power cycles. MEMIC is a memory architecture designed for intermittent computing devices, combining volatile and nonvolatile memory efficiently to maximize computational performance per joule. MEMIC's instruction and data cache greatly reduce workload completion time under intermittent operation.
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS
(2023)
Article
Engineering, Electrical & Electronic
Suren Jayasuriya, Odrika Iqbal, Venkatesh Kodukula, Victor Torres, Robert LiKamWa, Andreas Spanias
Summary: Huge advancements have been made in modern image-sensing hardware and visual computing algorithms. However, there is still a gap between hardware and software design in imaging systems, which limits collaboration between research domains. This survey explores existing works that use software-defined imaging (SDI) to replace conventional hardware components, allowing users to program image sensors according to their needs. The scope of the survey covers various imaging systems and discusses the components and future research directions of SDI.
PROCEEDINGS OF THE IEEE
(2023)
Article
Computer Science, Hardware & Architecture
Lars Hanschke, Christian Renner
Summary: The rise of Energy Harvesting Wireless Sensor Networks has led to increasing demands on energy management efficiency and configurability. EmRep addresses the issue of "over-provisioning" in energy management, improving energy storage utilization and optimizing for platforms with small energy storage.
IET COMPUTERS AND DIGITAL TECHNIQUES
(2022)
Article
Computer Science, Information Systems
Md Rafiul Kabir, Sandip Ray
Summary: Modern technological industries fused with the Internet-of-Things (IoT) have rapidly advanced, reshaping modeling and simulation techniques into the virtualization of physical systems through the joint usage of several technologies. Virtual prototyping has emerged as a significant development in distributed IoT applications, providing early exploration, optimization, and security assessments. Various industries employ different types of prototyping such as virtual platforms, digital twins, and application-specific virtualization techniques to meet their development needs. This survey clarifies concepts and distinctions, comprehensively reviews various prototyping technologies, and discusses the transformative role of virtualization technologies in intelligent cyber-physical systems.
Article
Computer Science, Information Systems
Erez Manor, Shlomo Greenberg
Summary: In recent years, the demand for efficient deployment of neural networks on edge devices has been increasing. However, the high computational demand prevents direct software deployment on resource-constrained edge devices. Various custom hardware accelerators have been proposed to enable real-time machine learning inference on low-power edge devices. This paper presents an efficient hardware-software framework, MCU-NPU, for accelerating machine learning inference on edge devices. The proposed framework supports weight compression and model pruning to reduce computational complexity and achieve high performance and low power consumption.
Article
Computer Science, Information Systems
Edel Diaz, Raul Mateos, Emilio J. Bueno, Ruben Nieto
Summary: The current trend is to increase the number of cores per chip in Multi-Processor System-On-Chips (MPSoC), which presents challenges in system verification. Hardware/software co-simulation virtual platforms have been proposed as a solution, but there is no current solution to synchronize QEMU with the hardware simulator in parallel mode.
Article
Engineering, Mechanical
Song Bai, Yan-Feng Li, Hong-Zhong Huang, Aodi Yu, Ying Zeng
Summary: As electronic systems become more complex, accurate fault analysis methods are becoming increasingly important. This paper proposes a hybrid fault mode and presents a fault analysis framework based on an improved Petri net. The research shows that considering the interaction between hardware and software in fault analysis of electronic systems is particularly effective.
ENGINEERING FAILURE ANALYSIS
(2021)
Article
Computer Science, Hardware & Architecture
Hongfei Wang, Zhanfei Wu, Xiangwei Wang, Longyun Bian, Hai Jin
Summary: The paper proposes a GBM reduction framework for the first time, which supports automatic hardware implementation of regression tree ensembles. Experimental results demonstrate that the method reduces area utilization and power consumption while maintaining performance compared to the original ensembles.
IEEE TRANSACTIONS ON COMPUTER-AIDED DESIGN OF INTEGRATED CIRCUITS AND SYSTEMS
(2023)