Journal of Systems Architecture最新文献

{"title":"Synchronous VS asynchronous reconfiguration of Memory Bandwidth Management Schemes: A comparative analysis","authors":"Andrea Serafini ,&nbsp;Alessandro Biasci ,&nbsp;Bruno Morelli ,&nbsp;Paolo Valente ,&nbsp;Andrea Marongiu","doi":"10.1016/j.sysarc.2025.103483","DOIUrl":"10.1016/j.sysarc.2025.103483","url":null,"abstract":"<div><div>Memory bandwidth contention may severely inflate the execution time of tasks co-running on modern Commercial Off-The-Shelf (COTS) multicores. An effective and widely deployed solution to mitigate the problem is <em>bandwidth regulation</em>, a technique to limit the available memory bandwidth for those cores that are not executing time-critical <em>tasks</em>. The granularity at which time-critical activities can be identified at the core level can be in fact even finer than a whole task, and just span smaller <em>memory-critical section</em> (MCS) therein. As the co-presence of MCS and non-critical task portions in the system dynamically changes over time, <em>bandwidth regulators</em> require more or less frequent <em>reconfiguration</em> of their parameters. Similar <em>reconfiguration techniques</em> thus represent a central component of dynamic <em>Memory Bandwidth Management Schemes</em> (MBMS). In particular, the overhead and latency of such a component determine the feasibility and control granularity of the overall bandwidth-regulation solution. The literature extensively covers low-level bandwidth regulation mechanisms and – to some extent – their integration in wider MBMSs, yet no in-depth analysis is currently available of the impact of <em>reconfiguration techniques</em>. This paper addresses this issue by proposing a comparative analysis of the two basic approaches to <em>reconfiguring</em> bandwidth regulators in a system: <em>synchronous</em> and <em>asynchronous</em> schemes. The analysis, performed on a real-world setup with both synthetic and real-world benchmarks, shows that the asynchronous technique improves the control granularity of a bandwidth regulator by a factor of up to 19x, moving from the <em>ms</em> to the <span><math><mi>μ</mi></math></span><em>s</em> scale.</div></div>","PeriodicalId":50027,"journal":{"name":"Journal of Systems Architecture","volume":"167 ","pages":"Article 103483"},"PeriodicalIF":3.7,"publicationDate":"2025-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144313789","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A secure data sharing scheme based on searchable public key encryption for authorized multi-receiver","authors":"Huan Li ,&nbsp;Lunzhi Deng ,&nbsp;Yating Gu ,&nbsp;Na Wang ,&nbsp;Yanli Chen ,&nbsp;Siwei Li","doi":"10.1016/j.sysarc.2025.103489","DOIUrl":"10.1016/j.sysarc.2025.103489","url":null,"abstract":"<div><div>To ensure data confidentiality, data sharers usually choose to encrypt the data before uploading it to cloud storage. Data sharing is an important way to realize the value of data. Therefore, how to share encrypted data stored in the cloud among authorized users is a pressing issue that needs to be addressed. Public key encryption schemes with keyword search provide an effective solution to this problem. In this paper, we first analyze Yang et al.’ scheme Yang et al. (2023), and point out that the scheme does not realize the indistinguishability of ciphertext and trapdoor. Then, we propose a new data sharing scheme with searchable public key encryption for authorized multi-receiver (SDS-SPKE), which not only realizes the search function, but also realizes the key update, user revocation. Additionally, we provide the security proofs of the scheme, which reveals that our scheme realizes the indistinguishability of ciphertext and trapdoor, and solves the problem of single-key-exposure. Finally, we compare the performance of SDS-SPKE with five other searchable encryption schemes, and the experimental results show that our scheme offers superior efficiency.</div></div>","PeriodicalId":50027,"journal":{"name":"Journal of Systems Architecture","volume":"167 ","pages":"Article 103489"},"PeriodicalIF":3.7,"publicationDate":"2025-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144307666","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"DTB+: An enhanced data management strategy for efficient RMW reduction in IMR drives","authors":"Fangxing Yu ,&nbsp;Chi Zhang ,&nbsp;Menghan Li ,&nbsp;Zhike Li ,&nbsp;Shiqiang Nie ,&nbsp;Weiguo Wu","doi":"10.1016/j.sysarc.2025.103479","DOIUrl":"10.1016/j.sysarc.2025.103479","url":null,"abstract":"<div><div>The emerging Interlaced Magnetic Recording (IMR) technology not only achieves higher storage density than SMR, but also significantly reduces rewrite overhead by dividing tracks into bottom and top tracks and organizing them in an interlaced fashion. However, frequent updates to the bottom track can trigger a large number of Read-Modify-Write (RMW) operations during high disk space utilization, which can severely degrade the I/O performance. Addressing this issue, this paper proposes an interlaced translation layer named DTB+ to improve the write performance of IMR disks. Firstly, a workload-sensitive track heat analysis mechanism is introduced to intelligently place data to reduce track rewrite probability. Simultaneously, the zero-incremental cost region is selectively used to construct a twin-buffer architecture to reduce RMW operations. In addition, an adaptive space allocation engine based on reinforcement learning was developed to flexibly allocate and reclaim space within the twin-buffer, improving disk resource utilization. Finally, establish a flexible evicted-data transfer zone to delay the writeback operations of interference data, further reducing the additional overhead. Experimental results indicate that compared with the state-of-the-art studies, DTB+ can reduce RMWs by 63.00% and additional I/O operations by 57.41%, decrease the average write latency by 37.77%, and lower the tail latency by 53.95%.</div></div>","PeriodicalId":50027,"journal":{"name":"Journal of Systems Architecture","volume":"167 ","pages":"Article 103479"},"PeriodicalIF":3.7,"publicationDate":"2025-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144280196","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Mul_STK: Efficient and privacy-preserving query with spatio-temporal-keyword multiple attributes in cloud computing","authors":"Lu Xing ,&nbsp;Haiyong Bao ,&nbsp;Menghong Guan ,&nbsp;Jing Wang ,&nbsp;Qinglei Kong ,&nbsp;Hong-Ning Dai ,&nbsp;Cheng Huang","doi":"10.1016/j.sysarc.2025.103490","DOIUrl":"10.1016/j.sysarc.2025.103490","url":null,"abstract":"<div><div>With the explosive growth of spatio-temporal-keyword data and the popularity of cloud computing, data owners often encrypt and outsource massive data to cloud servers to provide secure query services. To improve query efficiency, cloud servers typically optimize the organization of massive spatio-temporal data for efficient keyword-based query. However, for the multi-attribute query, the existing works lack an integrated coding theory, which cannot realize a parallelized and efficient query. Moreover, the existing serialized query for each attribute is inefficient and leads to users’ privacy leakage. To address these issues, we propose a privacy-preserving and efficient multi-attribute query scheme in cloud computing for massive data scenarios (Mul_STK), which can realize the following two guarantees for outsourced computing. Firstly, to realize the parallelized and efficient query with multiple attributes, we design a multi-attribute unified encoding technique to encode multiple attributes into unified vectors and construct an STK-BH tree structure. We further design an efficient filtration-verification query algorithm based on the STK-BH tree to fully utilize the characteristics of multi-dimensional attributes and realize parallelized dynamic pruning query. Secondly, to realize a secure multi-attribute query, three secure atomic predicate encryption protocols are constructed based on techniques of improved symmetric homomorphic encryption (iSHE), advanced encryption standard (AES), and lightweight matrix encryption. In addition, we combine these secure protocols with the efficient filtration-verification algorithm to propose Mul_STK, which guarantees the balance between efficiency and privacy-preservation in cloud computing environments. Security analysis and experiments show that Mul_STK achieves high query efficiency in cloud computing while ensuring data privacy, query privacy, and access pattern privacy.</div></div>","PeriodicalId":50027,"journal":{"name":"Journal of Systems Architecture","volume":"167 ","pages":"Article 103490"},"PeriodicalIF":3.7,"publicationDate":"2025-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144321800","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Engineering SRAM-PUF on Arduino microcontroller","authors":"Mario Barbareschi ,&nbsp;Franco Cirillo ,&nbsp;Christian Esposito ,&nbsp;Nicola Mazzocca","doi":"10.1016/j.sysarc.2025.103466","DOIUrl":"10.1016/j.sysarc.2025.103466","url":null,"abstract":"<div><div>The emergence of the Internet of Things (IoT) enables both people and devices to access services, data, and actuator control from remote locations, even spanning thousands of miles. Ensuring authentication, communication integrity, and confidentiality for IoT devices is essential for systems security and still an open challenge too. In this context, Physical Unclonable Functions (PUFs) have gained significant attention due to their ability to generate stable, tamper-resistant, and random fingerprints that can be successfully exploited to provide cryptography keys or to implement authentication schemes. However, PUFs necessitate dedicated hardware, making them costly and available only in specific designs, thereby impeding their broader adoption. In this paper, we enable the usage of static random access memory (SRAM)-based PUF on Arduino UNO device, an open-source board implemented upon an ATMega328P, without requiring special hardware. We analyze SRAM PUF quality parameters and how to reconstruct a reliable cryptography key by engineering a fuzzy extractor. Additionally, we design a secure bootloader as root-of-trust and, as a case study, we detail how to authenticate Arduino Sketches and how to implement an authentication scheme.</div></div>","PeriodicalId":50027,"journal":{"name":"Journal of Systems Architecture","volume":"167 ","pages":"Article 103466"},"PeriodicalIF":3.7,"publicationDate":"2025-06-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144298563","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"IATS: Information-age aware task scheduling for vehicle-road-cloud cooperative systems","authors":"Sijie Lin ,&nbsp;Liying Li ,&nbsp;Jining Chen ,&nbsp;Peijin Cong ,&nbsp;Tian Wang ,&nbsp;Junlong Zhou","doi":"10.1016/j.sysarc.2025.103480","DOIUrl":"10.1016/j.sysarc.2025.103480","url":null,"abstract":"<div><div>As the Internet of Things (IoT) continues to evolve at an unprecedented pace, smart vehicles can now support various real-time applications like object detection that require timely situational awareness. The freshness of state information is critical for these time-sensitive applications, as it directly affects the timeliness and accuracy of situational awareness. Fresh state information enables smart vehicles to make correct decisions in dynamic environments. However, this aspect is often ignored in prior work. Besides, these applications are typically computation-intensive, posing a challenge to resource-limited smart vehicles. Considering that the state information’s freshness can be characterized using the age of information (AoI) and the vehicle-road-cloud computing architecture is effective in integrating the resources of roadside units and the cloud to assist with processing tasks for vehicles, to minimize the system’s long-term average AoI without violating delay and energy constraints, this paper explores the AoI-aware task scheduling problem in a vehicle-road-cloud cooperative system. To achieve this goal, we first develop an AoI model tailored for smart vehicles within the cooperative system and formulate an AoI optimization problem. In order to tackle the proposed issue, we design a multi-agent reinforcement learning-based task scheduling method that can perform task scheduling in complex, dynamic, and decentralized decision-making environments. The algorithm iteratively trains the network continuously such that all agents obtain the optimal scheduling strategy. Finally, we implement extensive simulations and testbed-based experiments to validate our method. The results indicate that our method reduces the average AoI by 81.91% on average and 95.23% at the highest compared to benchmarking approaches.</div></div>","PeriodicalId":50027,"journal":{"name":"Journal of Systems Architecture","volume":"167 ","pages":"Article 103480"},"PeriodicalIF":3.7,"publicationDate":"2025-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144298562","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Dynamic task offloading and resource allocation for energy-harvesting end–edge–cloud computing systems","authors":"Xiaozhu Song ,&nbsp;Qianpiao Ma ,&nbsp;Gan Zheng ,&nbsp;Liying Li ,&nbsp;Peijin Cong ,&nbsp;Junlong Zhou","doi":"10.1016/j.sysarc.2025.103469","DOIUrl":"10.1016/j.sysarc.2025.103469","url":null,"abstract":"<div><div>In end–edge–cloud (EEC) computing, end devices (EDs) offload compute-intensive tasks to nearby edge servers or the cloud server to alleviate processing burdens and enable a flexible computing architecture. However, resource constraints and dynamic environments pose significant challenges for EEC task offloading and resource allocation, including real-time requirements, unreliable task execution, and limited battery energy, especially in energy harvesting (EH) systems, in which battery energy remains unstable due to its inherent fluctuations. Existing task offloading and resource allocation approaches often fail to address these challenges holistically, leading to degraded performance and potential task execution failures. In this paper, we propose a novel task offloading and resource allocation method for EH EEC computing, aiming to optimize long-term performance by minimizing delay and energy consumption while ensuring task execution reliability and battery energy stability. Specifically, we formulate task offloading and resource allocation as a cost optimization problem under constraints such as ED capacity, task reliability, and energy consumption. To solve this problem, we first leverage Lyapunov optimization to decouple the original time-dependent problem. Then we derive optimal closed-form solutions for computation and transmission power resource allocation. Based on these solutions, we propose a multiple discrete particle swarm optimization algorithm to determine task offloading decision. Extensive experiments demonstrate the superiority of our method in balancing delay, execution reliability, and energy stability under varying conditions.</div></div>","PeriodicalId":50027,"journal":{"name":"Journal of Systems Architecture","volume":"167 ","pages":"Article 103469"},"PeriodicalIF":3.7,"publicationDate":"2025-06-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144291268","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"FPGA-based CNN accelerator using Convolutional Processing Element to reduce idle states","authors":"Mohammad Dehnavi ,&nbsp;Aran Ghasemi ,&nbsp;Bijan Alizadeh","doi":"10.1016/j.sysarc.2025.103468","DOIUrl":"10.1016/j.sysarc.2025.103468","url":null,"abstract":"<div><div>Object detection has been a significant challenge in machine vision systems from the past to the present. Various hardware-based accelerators have been utilized to enhance speed efficiency. The primary objective of most of these accelerators is to minimize idle states in DSP blocks. In this paper, a new architecture based on Convolutional Processing Elements (CPEs) is proposed, wherein weights are stored, circularly shifted in an internal CPE buffer and used to generate output feature maps. In this way, the idle states of DSPs are reduced by increasing data reuse in CPEs and decreasing external memory accesses. The number of CPEs used to accelerate a CNN depends on the required speed and available hardware resources; configurations of 16, 32, 64, 128, and 256 CPEs can be utilized to accelerate a desired Convolutional Neural Network (CNN). To demonstrate the effectiveness of the proposed architecture, it is applied to the YOLOv3-Tiny object detection CNN. Experimental results show that our proposed architecture with 128 CPE cores can operate at 62.8 frames per second on an FPGA Xilinx XCKU060 with a working frequency of 200 MHz, using 16-bit fixed-point representation. This approach results in only a 1% drop in mAP while utilizing 43.2K LUTs, 94.4K FFs, 26.73 Mbits of RAM, and 1364 DSPs. Furthermore, the number of external memory chips is reduced by 67% compared to the state-of-the-art systems.</div></div>","PeriodicalId":50027,"journal":{"name":"Journal of Systems Architecture","volume":"167 ","pages":"Article 103468"},"PeriodicalIF":3.7,"publicationDate":"2025-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144240327","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Novel hybrid probabilistic–statistical error metrics for approximate adders","authors":"Vishesh Mishra ,&nbsp;Sparsh Mittal ,&nbsp;Urbi Chatterjee","doi":"10.1016/j.sysarc.2025.103467","DOIUrl":"10.1016/j.sysarc.2025.103467","url":null,"abstract":"<div><div>Approximate computing (AxC) has emerged as a promising approach for improving error-tolerant applications’ performance and energy efficiency. The approximate adder designs provide disproportionate energy and performance gains at the cost of a bounded loss in precision. The existing error metrics provide limited insights into error generation and propagation and correlate poorly with end-application quality-of-result (QoR). In this paper, we propose four novel error metrics for approximate adders that bring together the best of statistical and probabilistic approaches. These metrics are based on the probabilistic adder-dependent error-generation vector (<span><math><mrow><mover><mrow><mi>A</mi><mi>G</mi><mi>V</mi></mrow><mo>⃗</mo></mover><mo>,</mo></mrow></math></span>) and the input-dependent error-propagation vector (<span><math><mover><mrow><mi>I</mi><mi>P</mi><mi>V</mi></mrow><mo>⃗</mo></mover></math></span>). Our proposed metrics decouple error generation from propagation and model the impact of both adder characteristics and (application-dependent) input distribution. Extensive evaluation with 28 approximate adders over three real-world applications (Gaussian Smoothing, Support Vector Machine, and Neural Network evaluated on datasets such as MNIST, CIFAR-10, and ImageNet) shows that our metrics are more strongly correlated with application QoR than conventional metrics such as mean relative error distance (MRED), worst-case error (WCE) or error-rate (ER). Our metrics also help identify suitable adder designs for different applications. We will open-source our code.</div></div>","PeriodicalId":50027,"journal":{"name":"Journal of Systems Architecture","volume":"167 ","pages":"Article 103467"},"PeriodicalIF":3.7,"publicationDate":"2025-06-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144221446","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Generative AI-based pipeline architecture for increasing training efficiency in intelligent weed control systems","authors":"Sourav Modak,&nbsp;Anthony Stein","doi":"10.1016/j.sysarc.2025.103464","DOIUrl":"10.1016/j.sysarc.2025.103464","url":null,"abstract":"<div><div>In automated crop protection tasks, deep learning has demonstrated significant potential. However, these advanced models rely heavily on high-quality, diverse datasets, which are often scarce and costly to obtain in agricultural settings. Traditional data augmentation techniques, while useful for increasing the volume of the dataset, often fail to capture the real-world variability needed for robust model training. In this paper, we present a novel method for generating synthetic images to enhance the training of deep learning-based object detection models for intelligent weed control, aiming to improve data efficiency. The architecture of our GenAI-based image generation pipeline integrates the Segment Anything Model (SAM) for zero-shot domain adaptation with a text-to-image Stable Diffusion Model, enabling the creation of synthetic images that can accurately reflect the idiosyncratic properties and appearances of a variety of real-world conditions. We further assess the application of these synthetic datasets on edge devices by evaluating state-of-the-art lightweight YOLO models, measuring data efficiency by comparing mAP50 and mAP50-95 scores among different proportions of real and synthetic training data. Incorporating these synthetic datasets into the training process has been found to result in notable improvements in terms of data efficiency. For instance, most YOLO models that are trained on a dataset consisting of 10% synthetic images and 90% real-world images typically demonstrate superior scores on mAP50 and mAP50-95 metrics compared to those trained solely on real-world images. The integration of this approach opens opportunities for achieving continual self-improvement of perception modules in intelligent technical systems.</div></div>","PeriodicalId":50027,"journal":{"name":"Journal of Systems Architecture","volume":"167 ","pages":"Article 103464"},"PeriodicalIF":3.7,"publicationDate":"2025-06-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144221447","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}