Data Cache Research Articles

PR-LRU: partial random LRU technique for performance improvement of last level cache

As chip multiprocessors (CMP) have become eminent in all areas of computing, it is inevitable for the operating system to schedule processes efficiently on different cores. These multi-cores pose different challenges of which shared resource contention is the dominant one, as cores share resources like last level cache (LLC) and main memory. This can lead to poor and unpredictable performance of the threads running on the system. The cache replacement policy of LLC becomes critical in managing the cache data in an efficient way. Though prominent, least recently used (LRU) algorithm has some issues with applications which do not follow the temporal locality pattern. This study proposes a modification to the LRU algorithm where a random selection of the victim from 'N' LRU blocks yields better results than the conventional method. The evaluation of the algorithm is carried out using Multi2sim simulator using Parsec and Splash2 benchmarks. The results show an overall performance improvement in hit ratio up to 6% and 2% over LRU for PARSEC and SPLASH2 benchmarks respectively.

AccConF: An Access Control Framework for Leveraging In-Network Cached Data in the ICN-Enabled Wireless Edge

The fast-growing Internet traffic is increasingly becoming content-based and driven by mobile users, with users more interested in data rather than its source. This has precipitated the need for an information-centric Internet architecture. Research in information-centric networks (ICNs) have resulted in novel architectures, e.g., CCN/NDN, DONA, and PSIRP/PURSUIT; all agree on named data based addressing and pervasive caching as integral design components. With network-wide content caching, enforcement of content access control policies become non-trivial. Each caching node in the network needs to enforce access control policies with the help of the content provider. This becomes inefficient and prone to unbounded latencies especially during provider outages. In this paper, we propose an efficient access control framework for ICN, which allows legitimate users to access and use the cached content directly, and does not require verification/authentication by an online provider authentication server or the content serving router. This framework would help reduce the impact of system down-time from server outages and reduce delivery latency by leveraging caching while guaranteeing access only to legitimate users. Experimental/simulation results demonstrate the suitability of this scheme for all users, but particularly for mobile users, especially in terms of the security and latency overheads.

ICRA: index based cache replacement algorithm for cloud storage

Meteorological dataset is usually big and has a clear field. Due to its text form, each read and display will take up more system resources. In addition, the loading speed of the webpage also affects the user's online experience. According to these problems, we proposed a cache replacement algorithm combined with indexing algorithm called index cache replacement algorithm. The main innovation of this paper is that the index is created while reading the document and the page data at the first time and analyse, sort, and cache the indexing data at the same time. When users browse the same page, we can directly index file to query and return the corresponding data. Thus, it enhances the effectiveness of cached data and cache query and improves the query file and byte hit rate which finally improve the performance of the network.

Hybrid Remote Access Protocol

The invalidation-based cache coherence protocols used in current CMPs result in inefficient utilization of cache hierarchy in the presence of heavy sharing, since a significant percentage of shared cached data is invalidated soon after it is brought into the private cache. This work presents an analysis of a shared memory cache coherence protocol; based on novel insights from the analysis, we advocate direct remote reads/writes at the shared last-level cache for heavily contended data. Evaluation of our proposed protocol with the Splash2x kernels shows 17 percent geometric mean speedup over traditional MESI coherence and 8.5 percent better performance than prior remote-access proposals.

ICRA: index based cache replacement algorithm for cloud storage

Meteorological dataset is usually big and has a clear field. Due to its text form, each read and display will take up more system resources. In addition, the loading speed of the webpage also affects the user's online experience. According to these problems, we proposed a cache replacement algorithm combined with indexing algorithm called index cache replacement algorithm. The main innovation of this paper is that the index is created while reading the document and the page data at the first time and analyse, sort, and cache the indexing data at the same time. When users browse the same page, we can directly index file to query and return the corresponding data. Thus, it enhances the effectiveness of cached data and cache query and improves the query file and byte hit rate which finally improve the performance of the network.

PR-LRU: partial random LRU technique for performance improvement of last level cache

As chip multiprocessors (CMP) have become eminent in all areas of computing, it is inevitable for the operating system to schedule processes efficiently on different cores. These multi-cores pose different challenges of which shared resource contention is the dominant one, as cores share resources like last level cache (LLC) and main memory. This can lead to poor and unpredictable performance of the threads running on the system. The cache replacement policy of LLC becomes critical in managing the cache data in an efficient way. Though prominent, least recently used (LRU) algorithm has some issues with applications which do not follow the temporal locality pattern. This study proposes a modification to the LRU algorithm where a random selection of the victim from 'N' LRU blocks yields better results than the conventional method. The evaluation of the algorithm is carried out using Multi2sim simulator using Parsec and Splash2 benchmarks. The results show an overall performance improvement in hit ratio up to 6% and 2% over LRU for PARSEC and SPLASH2 benchmarks respectively.

Design and Analysis of an Effective Two-Step Clustering Scheme to Optimize Prefetch Cache Technology

In most antivirus products, the local cache mechanism is implemented for the purpose of reducing the time of the file scan. However, the database designed to store cache is limited, a lot of times, that most of the cache data have been purged during the file scanning since it cannot store too many CRC files in the local cache. Traditional methods of building and forming cache cannot effectively solve the problem of low cache utilization. Whereas a client with a traditional cache mechanism needs to send out multiple queries in order to accumulate a usable cache one-by-one, which causes the waste of database and time. In this paper, we first gather the current feedback data and analyze the data, and then, we explore an effective Two-Step clustering scheme to implement for the optimization of the prefetch cache strategy. Our scheme can avoid the cache being cleared prematurely and increase the probability of cache hits. Extensive experimental results demonstrate that our proposed scheme could save 11.76% time during file scanning.

SCORE

Technology scaling and program/erase cycling result in an increasing bit error rate in NAND flash storage. Some solid state drives (SSDs) adopt overlong error correction codes (ECCs) , whose redundancy size exceeds the spare area limit of flash pages, to protect user data for improved reliability and lifetime. However, the read performance is significantly degraded, because a logical data page and its ECC redundancy are stored in two flash pages. In this article, we find that caching ECCs has a large potential to reduce flash reads by achieving higher hit rates, compared to caching data. Then, we propose a novel <underline>s</underline>cheme to efficiently <underline>c</underline>ache <underline>o</underline>ve<underline>r</underline>long <underline>E</underline>CCs, called SCORE , to improve the SSD performance. Exceeding ECC redundancy (called ECC residues ) of logically consecutive data pages are grouped into ECC pages . SCORE partitions RAM to cache both data pages and ECC pages in a workload-adaptive manner. Finally, we verify SCORE using extensive trace-driven simulations. The results show that SCORE obtains high ECC hit rates without sacrificing data hit rates, thus improving the read performance by an average of 22% under various workloads, compared to the state-of-the-art schemes.

Analysis of the method of optimized data caching in the Content Delivery Network

Concept of Content Delivery Network (CDN) system and methods of caching data on edge servers were considered in this paper. The main task of the CDN network is providing the qualitative information delivery to the end user. Content Delivery Network is a geographically distributed network, that contain a number of content servers and routers. As a rule, it consists of a main node (Origin), and caching nodes (Edges) – points of presence, which can be located in various parts of the world. All content is stored and updated on the Origin server. The structural scheme of organizing the work of the CDN network, consisting of three complementary planes, was presented. Each plane performs special functions and has its own implementation features. Access Plane provides end-user access to content and the interaction of caching servers among themselves and on other planes. The load balancing plane is organized according to the principle of the DNS service and allows to redirect the user's requests to the nearest caching servers. This plane also inter-acts with the metric plane, which contains up-to-date information of the status of all servers involved in delivery and caching of data. As part of this paper, we proposed a method for optimized caching of data in the CDN network. The algorithm of this method is presented. Dependencies that make it possible to evaluate the work of this method in comparison with existing methods are given. The proposed method allows to significantly improve the Hit Ratio, and thus ensure efficient use of cached data and reduce the load on servers of origin.

AVPP

Value prediction improves instruction level parallelism in superscalar processors by breaking true data dependencies. Although this technique can significantly improve overall performance, most of the state-of-the-art value prediction approaches require high hardware cost, which is the main obstacle for its wide adoption in current processors. To tackle this issue, we revisit load value prediction as an efficient alternative to the classical approaches that predict all instructions. By speculating only on loads, the pressure over shared resources (e.g., the Physical Register File) and the predictor size can be substantially reduced (e.g., more than 90% reduction compared to recent works). We observe that existing value predictors cannot achieve very high performance when speculating only on load instructions. To solve this problem, we propose a new, accurate and low-cost mechanism for predicting the values of load instructions: the Address-first Value-next Predictor with Value Prefetching (AVPP). The key idea of our predictor is to predict the load address first (which, we find, is much more predictable than the value) and to use a small non-speculative Value Table (VT)—indexed by the predicted address—to predict the value next. To increase the coverage of AVPP, we aim to increase the hit rate of the VT by predicting also the load address of a future instance of the same load instruction and prefetching its value in the VT. We show that AVPP is relatively easy to implement, requiring only 2.5% of the area of a 32KB L1 data cache. We compare our mechanism with five state-of-the-art value prediction techniques, evaluated within the context of load value prediction, in a relatively narrow out-of-order processor. On average, our AVPP predictor achieves 11.2% speedup and 3.7% of energy savings over the baseline processor, outperforming all the state-of-the-art predictors in 16 of the 23 benchmarks we evaluate. We evaluate AVPP implemented together with different prefetching techniques, showing additive performance gains (20% average speedup). In addition, we propose a new taxonomy to classify different value predictor policies regarding predictor update, predictor availability, and in-flight pending updates. We evaluate these policies in detail.

Extending NUMA-BTLP Algorithm with Thread Mapping Based on a Communication Tree

The paper presents a Non-Uniform Memory Access (NUMA)-aware compiler optimization for task-level parallel code. The optimization is based on Non-Uniform Memory Access—Balanced Task and Loop Parallelism (NUMA-BTLP) algorithm Ştirb, 2018. The algorithm gets the type of each thread in the source code based on a static analysis of the code. After assigning a type to each thread, NUMA-BTLP Ştirb, 2018 calls NUMA-BTDM mapping algorithm Ştirb, 2016 which uses PThreads routine pthread_setaffinity_np to set the CPU affinities of the threads (i.e., thread-to-core associations) based on their type. The algorithms perform an improve thread mapping for NUMA systems by mapping threads that share data on the same core(s), allowing fast access to L1 cache data. The paper proves that PThreads based task-level parallel code which is optimized by NUMA-BTLP Ştirb, 2018 and NUMA-BTDM Ştirb, 2016 at compile-time, is running time and energy efficiently on NUMA systems. The results show that the energy is optimized with up to 5% at the same execution time for one of the tested real benchmarks and up to 15% for another benchmark running in infinite loop. The algorithms can be used on real-time control systems such as client/server based applications which require efficient access to shared resources. Most often, task parallelism is used in the implementation of the server and loop parallelism is used for the client.

Hardware Design of Multichannel Video Acquisition System Based on FPGA

A hardware design of multi-channel video acquisition system is designed, we propose system based on FPGA Cyclone V chip, The A/D conversion of analog video signal is accomplished through high-speed parallel AD chip LTC2202 of LINEAR Company. In the process of image data acquisition, SDRAM is used for data caching in image processing. From capacity and reading and writing speed analysis, 2 pieces of MICRON Company’s 32 bit wide MT48LC2M32B2B5 are selected, and the capacity is 64Mb, The Cameralink interface is selected as the interface between FPGA and image data transmission of external system. There is reserved communication with external control signals, sending control signals by TI Company DS90LV047. The system collects the image data from the front end through the A/D, caches the SDRAM and outputs the image through Cameralink to achieve the high speed and high efficiency of the data transmission. The hardware realizes the data acquisition and transmission of the multi-channel target image.

A Column-aware Data Caching Method and System

A Column-aware Data Caching Method and System

Analyzing Data Cache Related Preemption Delay With Multiple Preemptions

Timing analysis of real-time tasks under preemptive scheduling must take cache-related preemption delay (CRPD) into account. Typically, a task may be preempted more than once during the execution in each period. To bound the total CRPD of ${k}$ preemptions, existing CRPD analysis techniques estimate the CRPD at each program point, and use the sum of the ${k}$ -largest CRPD among all program points as the total CRPD upper bound. In this paper, we disclose that the above-mentioned approach, although works well for instruction caches, leads to significant overestimation when dealing with data caches. This is because on data caches, the CRPD of preemptions at different program points may have correlations, and the total CRPD of multiple preemptions is in general smaller than the simple sum of the worst-case CRPD of each preemption. To address this problem, we propose a new technique to efficiently explore the correlation among the CRPD of different preemptions, and thus more precisely calculate the total CRPD. Experiments with benchmark programs show that the proposed technique leads to substantially tighter total CRPD estimation with multiple preemptions comparing with the state-of-the-art.

Information-Centric Networking Security

The selected articles cover topics including security mechanisms overview for named data networking (NDN), security for an edge named function environment, secure NDN with attribute- based cryptography and software-defined networking (SDN), content protection for NDN, and the design of a security monitoring plane in NDN. Over the last few decades, the sum of all forms of video data has grown explosively and is expected to reach 90 percent of all Internet traffic in the near future. Meanwhile, new applications, such as the Internet of Things (IoT), augmented reality, and automatic driving, are emerging as the major trends for the next evolution of the digital society, resulting in the generation and sharing of vast amounts of data. The existing Internet-based technologies, such as peer-to-peer networks, content distribution networks, and cloud computing, will be unable to handle such large amounts of data and provide the necessary quality of service (QoS) to the applications. In this context, information-centric networking (ICN), characterized by name-based data retrieval and in-network data caching, has emerged as a promising candidate for future networks. It provides access to named data as first-order network service, providing a built-in mechanism for data provenance and greater potential for optimizing forwarding behavior compared to the traditional host-centric communication systems — the Internet today.

Automatic Orbit Selection for a Radio Interferometric Spacecraft Constellation

A constellation of radio telescope spacecraft can leverage interferometry to accurately image distant objects throughout the universe, but mission design must balance among many interrelated constraints. In particular, the number of spacecraft and their time-varying orbital parameters determine what interferometric baselines are feasible for each target, which in turn drives the imaging capabilities of the constellation. The large combinatorics of dynamic constellation configuration and the numerous competing engineering concerns present a challenge that is not well addressed by labor-intensive manual mission design processes. This paper describes search-based optimization methods that direct mission design effort toward promising constellation geometries: those that achieve broad interferometric coverage but remain cost-effective and resilient to failures. Six families of automatic optimization algorithms with complementary search strategies were created to explore among explicit constellation configuration plans. Evaluation of each candidate constellation plan was accelerated by efficiently combining precomputed caches of orbital and interferometric data. Comparative results indicate that leveraging automated optimization for constellation mission design is practical and useful. Optimized constellations demonstrated target image reconstruction errors 10% better than a manually designed constellation and up to 35% better than random solutions.

Analysis and approximation of optimal co-scheduling on cmp

In recent years, the increasing design complexity and the problems of power and heat dissipation have caused a shift in processor technology to favor Chip Multiprocessors. In Chip Multiprocessors (CMP) architecture, it is common that multiple cores share some on-chip cache. The sharing may cause cache thrashing and contention among co-running jobs. Job co-scheduling is an approach to tackling the problem by assigning jobs to cores appropriately so that the contention and consequent performance degradations are minimized. This dissertation aims to tackle two of the most prominent challenges in job co-scheduling. The first challenge is in the computational complexity for determining optimal job co-schedules. This dissertation presents one of the first systematic analyses on the complexity of job co-scheduling. Besides proving the NP completeness of job co-scheduling, it introduces a set of algorithms, based on graph theory and Integer/Linear Programming, for computing optimal co-schedules or their lower bounds in scenarios with or without job migrations. For complex cases, it empirically demonstrates the feasibility for approximating the optimal schedules effectively by proposing several heuristics-based algorithms. These discoveries facilitate the assessment of job co-schedulers by providing necessary baselines, and shed insights to the development of practical co-scheduling systems. The second challenge resides in the prediction of the performance of processes co-running on a shared cache. This dissertation explores the influence on co-run performance prediction imposed by co-runners, program inputs, and cache configurations. Through a sequence of formal analysis, we derive an analytical co-run locality model, uncovering the inherent statistical connections between the data references of programs single-runs and their co-run locality. The model offers theoretical insights on co-run locality analysis and leads to a lightweight approach for fast prediction of shared cache performance. We demonstrate the effectiveness of the model in enabling proactive job co-scheduling. Together, the two-dimensional findings open up many new opportunities for cache management on modern CMP by laying the foundation for job co-scheduling, and enhancing the understanding to data locality and cache sharing significantly.

Spatial Intelligence toward Trustworthy Vehicular IoT

Spatial challenges for the vehicular Internet of Things come from mobility, high density, sparse connectivity, and heterogeneity. In this article, we propose two techniques, namely decentralized moving edge and multi-tier multi-access edge clustering, to handle these challenges. The “vehicle as an edge” concept of the decentralized moving edge provides a more suitable solution to meet the throughput and latency performance requirements by conducting distributed communication, data caching, and computing tasks at vehicles. Multi-tier multi-access edge clustering generates different levels of clusters for more efficient integration of different types of access technologies including licensed/unlicensed long-range low-throughput communications and unlicensed short-range high-throughput communications. We employ fuzzy logic to jointly consider multiple inherently contradictory metrics and use Q-learning to achieve a self-evolving capability. Realistic computer simulations are conducted to show the advantage of the proposed protocols over alternatives, and several open research problems are discussed.

Dynamic Network Formation Game With Social Awareness in D2D Communications

The benefit of having a complementary network such as device-to-device (D2D) communications underlaying cellular systems lies in alleviating the traffic overloading burdens at base stations (BSs). This is critical in modern-day scenarios, e.g., in offloading and caching of mobile data traffic, and delivery of popular Internet contents to users. In this paper, we are chiefly interested in the establishment of D2D networks and how such a network evolves dynamically over time as D2D links are continuously formed and broken. Another important yet challenging research opportunity, i.e., the leverage of human users’ social ties for D2D communications, will also be addressed in this paper. To investigate the D2D network formation problem, we look at a game-theoretic framework where the utility function is designed to balance the physical and social domains—where we systematically extract social tie strengths from a real-world data set. To study the evolution of such D2D networks through time in a dynamic stochastic context, we propose a dynamic potential game and show that its equilibrium behaviors can be achieved through some strategy and payoff learning mechanisms. Simulation results verify our analysis. Using a content delivery application to assess the performance of our proposed scheme, it can be shown that major improvements can be obtained in terms of network delay, content accessibility, and BS load reduction.

Adaptive multilevel fuzzy-based authentication framework to mitigate Cache side channel attack in cloud computing

Cloud computing supports multitenancy to satisfy the users’ demands for accessing resources and simultaneously it increases revenue for cloud providers. Cloud providers adapt multitenancy by virtualizing the resources, like CPU, network interfaces, peripherals, hard drives and memory using hypervisor to fulfill the demand. In a virtualized environment, many virtual machines (VMs) can run on the same core with the help of the hypervisor by sharing the resources. The VMs running on the same core are the target for the malicious or abnormal attacks like side channel attacks. Among various side channel attacks in cloud computing, cache-based side channel attack is one that leaks private information of the users based on the shared resources. Here, as the shared resource is the cache, a process can utilize the cache usage of another by cache contention. Cache sharing provides a way for the attackers to gain considerable information so that the key used for encryption can be inferred. Discovering this side channel attack is a challenging task. This requires identification of a feature that influences the attack. Even though there are various techniques available in the literature to mitigate such attacks, an effective solution to reduce the cache-based side channel attack is still an issue. Therefore, a novel fuzzy rule-based mechanism is integrated to detect the cache side channel attackers by monitoring the cache data access (CDA). The factor that determines the attack is CDA in a log file created by the framework during authorization. The proposed framework also utilizes certain security properties including ECC and hashing for the privacy preservation and the decision is made with the aid of a fuzzy logic system.