Journal of Systems Architecture最新文献

{"title":"Data clustering on hybrid classical-quantum NISQ architecture with generative-based variational and parallel algorithms","authors":"Julien Rauch ,&nbsp;Damien Rontani ,&nbsp;Stéphane Vialle","doi":"10.1016/j.sysarc.2025.103431","DOIUrl":"10.1016/j.sysarc.2025.103431","url":null,"abstract":"<div><div>Clustering is a well-established unsupervised machine-learning approach to classify data automatically. In large datasets, the classical version of such algorithms performs well only if significant computing resources are available (e.g., GPU). A distinct computational framework compared to classical methods relies on integrating a <em>quantum processing unit</em> (QPU) to alleviate the computing cost. This is achieved through the QPU’s ability to exploit quantum effects, such as superposition and entanglement, to natively parallelize computation or approximate multidimensional distributions for probabilistic computing (Born rule).</div><div>In this paper, we propose first a clustering algorithm adapted to a hybrid CPU–QPU architecture while considering the current limitations of <em>noisy intermediate-scale quantum</em> (NISQ) technology. Secondly, we propose a quantum algorithm that exploits the probabilistic nature of quantum physics to make the most of our QPU’s potential. Our approach leverage on ideas from generative machine-learning algorithm and <em>variational quantum algorithms</em> (VQA) to design an hybrid QPU–CPU algorithm based on a mixture of so-called <em>quantum circuits Born machines</em> (QCBM). We implemented and tested the quality of our algorithm on an IBM quantum machine, then parallelized it to make better use of quantum resources and speed up the execution of quantum-based clustering algorithms.</div><div>Finally, summarize the lessons learned from exploiting a CPU–QPU architecture on NISQ for data clustering.</div></div>","PeriodicalId":50027,"journal":{"name":"Journal of Systems Architecture","volume":"165 ","pages":"Article 103431"},"PeriodicalIF":3.7,"publicationDate":"2025-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144071813","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":"Breathing new life into compression: Resolving the dilemma of LFS with compression on flash storage","authors":"Yunpeng Song,&nbsp;Yiyang Huang,&nbsp;Dingcui Yu,&nbsp;Liang Shi","doi":"10.1016/j.sysarc.2025.103432","DOIUrl":"10.1016/j.sysarc.2025.103432","url":null,"abstract":"<div><div>State-of-the-art storage systems have widely adopted log-structured file systems (LFS) with unique append–write capability, making them ideal for supporting compression. Compression is a recognized way of reducing data-occupied space and extending the lifetime of flash. However, implementing file system-level compression faces a dilemma that hampers its adoption. Two significant issues are responsible for this. Firstly, the software stack overhead resulting from compression is costly. Due to its location on the critical path for reads and writes, compression will block the user’s I/O requests. Secondly, compressing as much space as possible to enjoy the benefits of compression in terms of space will inevitably introduce compression overhead. This paper proposes a novel no-critical path compression scheme that significantly eliminates compression’s current dilemma. The basic idea is to perform non-critical path compression, minimizing the performance impact and maximizing the benefits of compression in space by disengaging compression from the critical paths of reads and writes. To achieve this, a critical path detachment scheme is first proposed to detach the compression from the critical path based on the properties of the non-critical path compression. Furthermore, a contention-avoiding scheduling scheme is proposed to minimize the impact on CPU costs. Finally, a reserve space (RS)-oriented allocation scheme is proposed to exploit the benefits of compression in space to optimize the cleaning cost of LFS. Through careful design and evaluation on a real platform, we demonstrate that the proposed scheme, NCPC, achieves encouraging performance and lifetime optimizations compared to state-of-the-art solutions.</div></div>","PeriodicalId":50027,"journal":{"name":"Journal of Systems Architecture","volume":"165 ","pages":"Article 103432"},"PeriodicalIF":3.7,"publicationDate":"2025-05-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143913144","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":"Analysis and optimization of communication delay in multi-subscriber environments of ROS 2","authors":"Xiantong Luo ,&nbsp;Xu Jiang ,&nbsp;Yue Tang ,&nbsp;Haochun Liang ,&nbsp;Nan Guan ,&nbsp;Wang Yi","doi":"10.1016/j.sysarc.2025.103428","DOIUrl":"10.1016/j.sysarc.2025.103428","url":null,"abstract":"<div><div>ROS 2 is one of the most popular robotic software development frameworks. ROS 2 employs a publish–subscribe paradigm for data exchanges, which can effectively address the diverse real-time requirements from the publisher side by various policies provided in the underlying communication layer. However, it remains unclear whether it adequately meets the various real-time requirements of subscribers. In this paper, we formally analyze the communication delay where a single message is published to multiple subscribers. In particular, we have identified a problem in the transmission of a message to multiple subscribers, where a subscriber with the highest priority may receive its message as late as the subscriber with the lowest priority. We propose policies to solve this problem and optimize the communication delay. Comprehensive experiments are conducted to validate and evaluate the proposed methods.</div></div>","PeriodicalId":50027,"journal":{"name":"Journal of Systems Architecture","volume":"164 ","pages":"Article 103428"},"PeriodicalIF":3.7,"publicationDate":"2025-05-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143903382","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":"PaLLOC: Pairwise-based low-latency online coordinated resource manager of last-level cache and memory bandwidth on multicore systems","authors":"Yang Bai,&nbsp;Yizhi Huang,&nbsp;Si Chen,&nbsp;Renfa Li","doi":"10.1016/j.sysarc.2025.103427","DOIUrl":"10.1016/j.sysarc.2025.103427","url":null,"abstract":"<div><div>Modern advanced multicore CPUs integrate large last-level caches (LLC) and provide high memory bandwidth, which are generally shared among cores. In many scenarios, isolated resources are required among co-running applications with dynamic changes. This drives the need for online partitioning of these shared hardware resources to accommodate applications’ different and varying resource demands. However, dynamically managing LLC and memory bandwidth without prior knowledge faces numerous searches for resource configurations to gather sufficient information and find the partition solution, which may cause long management latency and limit system performance. To address this problem, we first identify several workload-independent observations and insights through a comprehensive exploration of the configuration space across various benchmarks, which can help reduce the need for configuration searches greatly. Guided by these findings, we propose a method that integrates two-step allocation with pairwise search techniques to maximize system instructions per cycle (IPC) throughput. Building on this method, we design and implement PaLLOC, a novel low-latency online coordinated resource manager of LLC and memory bandwidth on multicore systems. Comprehensive evaluations on an Intel commodity server demonstrate that PaLLOC consistently exhibits significant performance advantage across various system workloads with diverse resource requirements, achieving 1.14x-1.47x speedup in system IPC throughput over the state-of-the-art online partitioning method, with a management latency of approximately 300ms under a monitoring period of 10 ms.</div></div>","PeriodicalId":50027,"journal":{"name":"Journal of Systems Architecture","volume":"164 ","pages":"Article 103427"},"PeriodicalIF":3.7,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143902588","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 traceable and revocable attribute-based encryption scheme with escrow-free in cloud storage","authors":"Na Wang,&nbsp;Dehua Zhou,&nbsp;Yuchien Huang,&nbsp;Caiwen Liu","doi":"10.1016/j.sysarc.2025.103426","DOIUrl":"10.1016/j.sysarc.2025.103426","url":null,"abstract":"<div><div>Cloud storage not only saves the cost of local storage space but also facilitates data sharing. In the context of smart healthcare, electronic health records (EHR) are shared in plaintext across various healthcare systems. These systems also store EHR data in cloud servers, which makes it easy to leak user information and brings many security and privacy issues. In addition, malicious users might, for reasons such as personal gain, leak their keys through various means. Ciphertext-Policy Attribute-Based Encryption (CP-ABE) is ideal for enabling detailed access control to cloud storage and protecting user data privacy. However, the extended CP-ABE has a key escrow problem, where some ciphertexts may be decrypted by authorities without user approval. To achieve privacy protection and effectively track malicious users, to revoke user access promptly, and to solve the key escrow challenge in smart healthcare systems, we introduce a privacy-preserving, traceable, revocable, key-escrow-free CP-ABE scheme. Ultimately, through security analysis, security proofs, and experimental results, we validate that the solution is both secure and effective.</div></div>","PeriodicalId":50027,"journal":{"name":"Journal of Systems Architecture","volume":"165 ","pages":"Article 103426"},"PeriodicalIF":3.7,"publicationDate":"2025-04-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143917773","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":"Edge-enabled IAM for IoTs with edge-based access management and context-driven syncservice","authors":"Yiting Wang,&nbsp;José-Fernán Martínez-Ortega,&nbsp;Pedro Castillejo,&nbsp;Mario San Emeterio de la Parte","doi":"10.1016/j.sysarc.2025.103430","DOIUrl":"10.1016/j.sysarc.2025.103430","url":null,"abstract":"<div><div>The number of edge IoT services is experiencing explosive growth. As an entry point for network services, Identity and Access Management (IAM) effectively prevents unauthorized access and blocks most cyber-attacks. However, most edge systems still rely on remote, cloud-based IAM for permission verification. The few edge-enabled IAM solutions that do exist operate on the assumption that attribute values are always up-to-date and provided by a completely trustworthy source, which make access decisions questionable in highly dynamic and distributed IoT environments. To address these challenges, this work proposes EIAM-IoT, an edge-enabled IAM architecture, and an improved Local Authentication and Authorization (LAA) method. The LAA evaluates multi-factor attributes, incorporating the freshness of attribute values and the trustworthiness of attribute providers, to achieve reliable access control. Additionally, the identity information required for LAA is synchronized and stored in the edge database by a context-aware synchronization strategy, which selectively and timely extends relevant identity data based on edge context, optimizing the trade-off between local data management costs and LAA performance. The performance and security analyses show that the LAA does not introduce significant overhead to traditional attribute-based solutions while enabling more fine-grained access control, increasing decision reliability, and offering additional features, such as local verification and federated identity management. While the LAA relies on cloud-extended local data, the system ensures greater availability and resilience to connectivity issues in edge-to-cloud setups. EIAM-IoT is particularly more suitable for dynamic, multi-authority, and edge-native IoT applications to achieve secure, low-latency, offline access to edge IoT services.</div></div>","PeriodicalId":50027,"journal":{"name":"Journal of Systems Architecture","volume":"165 ","pages":"Article 103430"},"PeriodicalIF":3.7,"publicationDate":"2025-04-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143907490","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":"Efficient and provably secure privacy-preserving two-factor authentication and key-agreement using blockchain and TEE for IoV environments","authors":"Qihang Hou ,&nbsp;Chingfang Hsu ,&nbsp;Man Ho Au ,&nbsp;Honglang Hu ,&nbsp;Zhuo Zhao ,&nbsp;Zeyu Wu","doi":"10.1016/j.sysarc.2025.103422","DOIUrl":"10.1016/j.sysarc.2025.103422","url":null,"abstract":"<div><div>With the rapid advancement of wireless communication and cloud computing technologies, the Internet of Vehicles (IoV), which enables information sharing between vehicles, cloud servers, and infrastructure to support intelligent driving and road safety functionalities, has seen widespread adoption. However, transmitting information through public channels in IoV introduces significant privacy and security risks. For example, vehicle location trajectories and road users’ identity information are vulnerable to leakage, and the communication process may be subject to various forms of attacks. To address these issues, extensive research has focused on authentication and key agreement (AKA) protocols for intelligent vehicles and cloud servers in IoV. However, existing solutions have several drawbacks, including excessive reliance on third-party entities, such as registration authorities, high computational overhead, inadequate security features, and multiple interactions, all of which fail to meet the resource constraints and real-time communication requirements of IoV. To overcome these limitations, this paper introduces, for the first time, the Trusted Execution Environment (TEE) into IoV authentication and proposes an efficient and provably secure privacy-preserving two-factor authentication and key agreement scheme based on blockchain and TEE, called BPAKA. Compared to existing methods, BPAKA offers several significant improvements: First, it leverages TEE to eliminate the need for trusted third parties, enabling mutual anonymous authentication between intelligent vehicles and cloud servers in IoV scenarios, while ensuring a comprehensive set of security properties. Second, BPAKA incorporates a blockchain-based data-sharing framework, ensuring lightweight computational overhead. The AKA process requires only a single round of interaction, thereby fulfilling IoV’s real-time requirements and mitigating the impact of network fluctuations. Third, the security of BPAKA is formally proven using provable security techniques, demonstrating its robustness against various potential threats. Furthermore, performance evaluations show that, compared to existing IoV schemes, BPAKA achieves lower overall computational overhead. In addition, when compared with the state-of-the-art TEE-based scheme, the computation overhead in TEE of BPAKA is only 50.1% of that of the latter, while maintaining feasible communication and storage costs.</div></div>","PeriodicalId":50027,"journal":{"name":"Journal of Systems Architecture","volume":"164 ","pages":"Article 103422"},"PeriodicalIF":3.7,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143894400","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 survey on routing algorithm and router microarchitecture of three-dimensional Network-on-Chip","authors":"Yuan Zhang ,&nbsp;Zewei Jing ,&nbsp;Qinghai Yang ,&nbsp;Nan Cheng ,&nbsp;Huaxi Gu ,&nbsp;Kyung Sup Kwak","doi":"10.1016/j.sysarc.2025.103429","DOIUrl":"10.1016/j.sysarc.2025.103429","url":null,"abstract":"<div><div>The continuous advancement of modern integrated circuits has facilitated the emergence of three-dimensional Networks-on-Chip (3D NoC), characterized by their direct vertical inter-layer electrical connections, which significantly enhance interconnect density. The performance and efficiency of 3D NoC architectures are jointly influenced by routing algorithms and router microarchitectures, which exhibit a symbiotic and complementary relationship. Routing algorithms are instrumental in determining the pathways for data packet transmission, profoundly influencing network latency, throughput, and reliability. Meanwhile, the router executes these algorithms, optimizing overall system efficiency through judicious resource allocation and effective data processing management. In this survey, we categorize routing algorithms according to various criteria, providing a detailed analysis of oblivious, adaptive, and hybrid oblivious-adaptive algorithms based on their degrees of adaptivity. Furthermore, we examine router microarchitectures, classifying them into buffered, bufferless, and hybrid buffered-bufferless designs, depending on whether buffering mechanisms are employed. This survey offers a comprehensive analysis of the co-evolution and co-design of routing algorithms and router microarchitectures, emphasizing that the alignment of an optimal routing algorithm with the appropriate microarchitecture is critical for better 3D NoC performance.</div></div>","PeriodicalId":50027,"journal":{"name":"Journal of Systems Architecture","volume":"164 ","pages":"Article 103429"},"PeriodicalIF":3.7,"publicationDate":"2025-04-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143894398","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":"The online reconfiguration of a distributed on-board computer: The time and network behaviour of a dependable scheduling algorithm","authors":"Glen te Hofsté ,&nbsp;Andreas Lund ,&nbsp;Alexandra Coroiu ,&nbsp;Marco Ottavi ,&nbsp;Daniel Lüdtke","doi":"10.1016/j.sysarc.2025.103420","DOIUrl":"10.1016/j.sysarc.2025.103420","url":null,"abstract":"<div><div>On-board Computers (OBCs) are at the centre of space-faring systems. With the increasing demand for cost-effective computing power in space, using high-performance commercial-off-the-shelf (COTS) components for OBCs has gained significant traction. COTS components, however, do not provide the necessary fault tolerance mechanisms. The ScOSA (Scalable On-board computing for Space Avionics) architecture uses COTS components in a distributed system to provide more computing performance and dependability. The effects of node failures are mitigated by removing the failed node from the system through reconfiguration. A reconfiguration is performed by using a set of predetermined configurations, which hinders system scalability due to exponentially increasing memory consumption depending on the number of nodes.</div><div>This paper continues the work on the ScOSA online reconfiguration algorithm as a solution to this scalability problem. The online reconfiguration algorithm, which has been integrated into a scheduler, makes task scheduling decisions at run-time, eliminating the need for predetermined configurations. The six-phase scheduling mechanism uses the real-time state of the system and is a step towards higher dependability in distributed on-board computing. New test scenarios have been introduced to provide insight into the temporal and network behaviour of online reconfiguration. By evaluating in terms of <em>time</em>, <em>network traffic</em> and <em>memory usage</em>, it is shown that online reconfiguration is not only capable of dynamically generating configurations but also providing a solution to the scalability problem for systems with varying numbers of both nodes and tasks.</div></div>","PeriodicalId":50027,"journal":{"name":"Journal of Systems Architecture","volume":"164 ","pages":"Article 103420"},"PeriodicalIF":3.7,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143878515","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":"μScope: Evaluating storage stack robustness against SSD’s latency variation","authors":"Linxiao Bai ,&nbsp;Shanshan Li ,&nbsp;Zhouyang Jia ,&nbsp;Yu Jiang ,&nbsp;Yuanliang Zhang ,&nbsp;Zichen Xu ,&nbsp;Bin Lin ,&nbsp;Si Zheng ,&nbsp;Xiangke Liao","doi":"10.1016/j.sysarc.2025.103405","DOIUrl":"10.1016/j.sysarc.2025.103405","url":null,"abstract":"<div><div>The rapid development of Solid State Disks (SSDs) drastically reduces device latency from <span><math><mrow><mn>100</mn><mspace></mspace><mi>μ</mi><mi>s</mi></mrow></math></span> to around <span><math><mrow><mn>10</mn><mspace></mspace><mi>μ</mi><mi>s</mi></mrow></math></span>. However, performance advertised is not always performance delivered. Background operations (e.g., garbage collection and wear leveling) inside the SSDs now may severely influence the performance. In addition, SSDs are also susceptible to fail-slow failures. Traditionally, studying SSD-based stack focuses on understanding the SSD internal behaviors or discussing the impacts of software stack on throughput.</div><div>In this paper, we conduct an extensive study on software stack atop the low-latency SSDs, especially under device latency variations. We build <span><math><mi>μ</mi></math></span>Scope to overcome two major challenges, including achieving fine-grained latency injection and low-overhead monitoring, in profiling. Via <span><math><mi>μ</mi></math></span>Scope, we manage to obtain three major lessons in access patterns, consistency trade-offs and consecutive performance variations which shall benefit developers for further optimizations.</div></div>","PeriodicalId":50027,"journal":{"name":"Journal of Systems Architecture","volume":"164 ","pages":"Article 103405"},"PeriodicalIF":3.7,"publicationDate":"2025-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143868277","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}