Analyzing Data Access Characteristics of AIoT Workloads for Efficient Write Buffer Management

The accelerating convergence of artificial intelligence (AI) and Internet of Things (IoT) has sparked a recent wave of interest in Artificial Intelligence of Things (AIoT). By exploiting the novel paradigm of edge intelligence, emerging computational intensive and resource demanding AIoT applications can be efficiently supported at the network edge. However, due to the limited resource capacity and/or power budget of the edge node, AIoT applications typically deploy compressed AI models to achieve the goal of low-latency and energy-efficient model inference. However, compressed models inherently suffer from the curse of data drift, i.e., the inference data at the deployment stage diverges from the training data at the training stage, leading to reduced model inference accuracy. To handle this issue, continuous learning has been proposed to periodically retrain the AI models on new data in an incremental manner. In this article, we investigate how to coordinate the edge and the cloud resources to perform cost-efficient continuous learning, with the goal of simultaneously optimizing the model performance (in terms of accuracy and robustness) and resource cost. Leveraging the Lyapunov optimization theory, we design and analyze a cost-efficient optimization framework for making online decisions upon admission control, transmission scheduling, and resource provisioning, for the dynamically arrived new data samples of various AIoT applications. We examine the effectiveness of the proposed framework on navigating the performance–cost tradeoff theoretically and empirically through trace-driven simulations.

PurposeThe purpose of this paper Computing is a recent emerging cloud model that affords clients limitless facilities, lowers the rate of customer storing and computation and progresses the ease of use, leading to a surge in the number of enterprises and individuals storing data in the cloud. Cloud services are used by various organizations (education, medical and commercial) to store their data. In the health-care industry, for example, patient medical data is outsourced to a cloud server. Instead of relying onmedical service providers, clients can access theirmedical data over the cloud.Design/methodology/approachThis section explains the proposed cloud-based health-care system for secure data storage and access control called hash-based ciphertext policy attribute-based encryption with signature (hCP-ABES). It provides access control with finer granularity, security, authentication and user confidentiality of medical data. It enhances ciphertext-policy attribute-based encryption (CP-ABE) with hashing, encryption and signature. The proposed architecture includes protection mechanisms to guarantee that health-care and medical information can be securely exchanged between health systems via the cloud. Figure 2 depicts the proposed work's architectural design.FindingsFor health-care-related applications, safe contact with common documents hosted on a cloud server is becoming increasingly important. However, there are numerous constraints to designing an effective and safe data access method, including cloud server performance, a high number of data users and various security requirements. This work adds hashing and signature to the classic CP-ABE technique. It protects the confidentiality of health-care data while also allowing for fine-grained access control. According to an analysis of security needs, this work fulfills the privacy and integrity of health information using federated learning.Originality/valueThe Internet of Things (IoT) technology and smart diagnostic implants have enhanced health-care systems by allowing for remote access and screening of patients’ health issues at any time and from any location. Medical IoT devices monitor patients’ health status and combine this information into medical records, which are then transferred to the cloud and viewed by health providers for decision-making. However, when it comes to information transfer, the security and secrecy of electronic health records become a major concern. This work offers effective data storage and access control for a smart healthcare system to protect confidentiality. CP-ABE ensures data confidentiality and also allows control on data access at a finer level. Furthermore, it allows owners to set up a dynamic patients health data sharing policy under the cloud layer. hCP-ABES proposed fine-grained data access, security, authentication and user privacy of medical data. This paper enhances CP-ABE with hashing, encryption and signature. The proposed method has been evaluated, and the results signify that the proposed hCP-ABES is feasible compared to other access control schemes using federated learning.

We study the replication transition problem (RTP) in the Grid systems. Most distributed systems replicate data to increase data access efficiency. A replication strategy dictates where the replicas are stored in respond to data access pattern, and a good strategy can improve data access efficiency. However, the access pattern in a distributed system is constantly changing. As a result a good replication strategy must evolve accordingly. The replication transition problem is to seek an efficient transition from one replication strategy to another in order to cope with the dynamic data access pattern. This paper focuses on the RTP problem for Grid systems in four communication models that have different communication capabilities, i.e., whether message forwarding is allowed and whether network capacity is uniform among different links. We show that there exists a polynomial time algorithm that provides optimal solution for the RTP problem when forwarding is not allowed and the communication links are uniform. We also propose heuristic algorithms for solving variants of the RTP problem and conduct experiments to evaluate their performances. The experimental results indicate that our proposed heuristics are very effective.

Large scientific collaborations often have multiple scientists accessing the same set of files while doing different analyses, which create repeated accesses to the large amounts of shared data located far away. These data accesses have long latency due to distance and occupy the limited bandwidth available over the wide-area network. To reduce the wide-area network traffic and the data access latency, regional data storage caches have been installed as a new networking service. To study the effectiveness of such a cache system in scientific applications, we examine the Southern California Petabyte Scale Cache for a high-energy physics experiment. By examining about 3TB of operational logs, we show that this cache removed 67.6% of file requests from the wide-area network and reduced the traffic volume on wide-area network by 12. 3TB (or 35.4%) an average day. The reduction in the traffic volume (35.4%) is less than the reduction in file counts (67.6%) because the larger files are less likely to be reused. Due to this difference in data access patterns, the cache system has implemented a policy to avoid evicting smaller files when processing larger files. We also build a machine learning model to study the predictability of the cache behavior. Tests show that this model is able to accurately predict the cache accesses, cache misses, and network throughput, making the model useful for future studies on resource provisioning and planning.

We address in this paper data management techniques for efficiently retrieving requested subsets of large datasets stored on mass storage devices. This problem represents a major bottleneck that can negate the benefits of fast networks, because the time to access a subset from a large dataset stored on a mass storage system is much greater that the time to transmit that subset over a network. This paper focuses on very large spatial and temporal datasets generated by simulation programs in the area of climate modeling, but the techniques developed can be applied to other applications that deal with large multidimensional datasets. The main requirement we have addressed is the efficient access of subsets of information contained within much larger datasets, for the purpose of analysis and. interactive visualization. We have developed data partitioning techniques that partition datasets into ``clusters`` based on analysis of data access patterns and storage device characteristics. The goal is to minimize the number of clusters read from mass storage systems when subsets are requested. We emphasize in this paper proposed enhancements to current storage server protocols to permit control over physical placement of data on storage devices. We also discuss in some detail the aspects of the interface between the application programs and the mass storage system, as well as a workbench to help scientists to design the best reorganization of a dataset for anticipated access patterns.

Recent advances in unsteady flow visualization

Understanding the inherent system characteristics is crucial to the design and optimization of cloud storage system, and few studies have systematically investigated its data characteristics and access patterns. This paper presents an analysis of file system snapshot and five-month access trace of a campus cloud storage system that has been deployed on Tsinghua campus for three years. The system provides online storage and data sharing services for more than 19,000 students and 500 student groups. We report several data characteristics including file size and file type, as well as some access patterns, including read/write ratio, read-write dependency and daily traffic. We find that there are many differences between cloud storage system and traditional file systems: our cloud storage system has larger file sizes, lower read/write ratio, and smaller set of active files than those of a typical traditional file system. With a trace-driven simulation, we find that the cache efficiency can be improved by 5 times using the guidance from our observations.

Machine learning for Big Data analytics in plants.

The performance achieved by an application is limited by architectural features such as program data access and processing patterns. Parallelization approaches exhibit dissimilar performance and have a direct impact in application execution time. Additionally, developing parallel code involves additional complexity and productivity for programmers to accelerate or rewrite the program. In this paper, we present a comparative performance evaluation of a CPU, GPU, and many-core (Xeon Phi KNL) architectures for the Non-Local Means filter. We asses the effect of different data access and processing patterns in two computational optimizations developed for the aforementioned filter. We follow a top-down approach in terms of the parallelization approach chosen, starting from performance primitives as a first step to give easy drop-in acceleration and then compiler directives with frameworks such as OpenMP and OpenACC as an intermediate step to map computing tasks to the underlying hardware. Results show that both libraries and directives are effective at accelerating code with a combination of both being necessary to overcome performance bottlenecks.

In modern computer architectures, access latency varies considerably between different levels in the memory hierarchy. Consequently, applications with data access patterns that don't reuse much data in fast levels of the hierarchy incur additional delays. To improve the performance of complex, data-intensive applications, developers need tools that help them understand the causes of poor memory hierarchy utilization. While most performance tools associate metrics with functions or statements, in this paper we explore data-centric analyses that associate metrics not only with data accesses but also with data objects themselves. Our contributions are three-fold. First, we propose several refinements to existing data-centric techniques that enable accurate and low-overhead measurements. Second, we combine data-centric analysis with call path profiling; this combination of techniques relates inefficient access patterns back to data objects across complete dynamic call chains. Third, we developed a graphical user interface that gracefully presents our analysis results using a multiplicity of views, which helps users identify problematic accesses and data structures. We demonstrate the utility of our approach by showing how our tool identifies problematic data access patterns in several HPC applications and a pair of the SPEC CPU2006 benchmarks.

Software transactional memory (STM) has been proposed as a promising programming paradigm for shared memory multi-threaded programs as an alternative to conventional lock based synchronization primitives. Typical STM implementations employ a conflict detection scheme, which works with uniform access granularity, tracking shared data accesses either at word/cache line or at object level. It is well known that a single fixed access tracking granularity cannot meet the conflicting goals of reducing false conflicts without impacting concurrency adversely. A fine grained granularity while improving concurrency can have an adverse impact on performance due to lock aliasing, lock validation overheads, and additional cache pressure. On the other hand, a coarse grained granularity can impact performance due to reduced concurrency. Thus, in general, a fixed or uniform granularity access tracking (UGAT) scheme is application-unaware and rarely matches the access patterns of individual application or parts of an application, leading to sub-optimal performance for different parts of the application(s). In order to mitigate the disadvantages associated with UGAT scheme, we propose a Variable Granularity Access Tracking (VGAT) scheme in this paper. We propose a compiler based approach wherein the compiler uses inter-procedural whole program static analysis to select the access tracking granularity for different shared data structures of the application based on the application's data access pattern. We describe our prototype VGAT scheme, using TL2 as our STM implementation. Our experimental results reveal that VGAT-STM scheme can improve the application performance of STAMP benchmarks from 1.87% to up to 21.2%.

During concurrent I/O workloads, sequential access to one I/O stream can be interrupted by accesses to other streams in the system. Frequent switching between multiple sequential I/O streams may severely affect I/O efficiency due to long disk seek and rotational delays of disk-based storage devices. Aggressive prefetching can improve the granularity of sequential data access in such cases, but it comes with a higher risk of retrieving unneeded data. This paper proposes a competitive prefetching strategy that controls the prefetching depth so that the overhead of disk I/O switch and unnecessary prefetching are balanced. The proposed strategy does not require a-priori information on the data access pattern, and achieves at least half the performance (in terms of I/O throughput) of the optimal offline policy. We also provide analysis on the optimality of our competitiveness result and extend the competitiveness result to capture prefetching in the case of random-access workloads.We have implemented the proposed competitive prefetching policy in Linux 2.6.10 and evaluated its performance on both standalone disks and a disk array using a variety of workloads (including two common file utilities, Linux kernel compilation, the TPC-H benchmark, the Apache web server, and index searching). Compared to the original Linux kernel, our competitive prefetching system improves performance by up to 53%. At the same time, it trails the performance of an oracle prefetching strategy by no more than 42%.

SIMD (single-instruction multiple-data) instruction set extensions are quite common today in both high performance and embedded microprocessors, and enable the exploitation of a specific type of data parallelism called SLP (Superword Level Parallelism). While prior research shows that significant performance savings are possible when SLP is exploited, placing SIMD instructions in an application code manually can be very difficult and error prone. In this paper, we propose a novel automated compiler framework for improving superword level parallelism exploitation. The key part of our framework consists of two stages: superword statement generation and data layout optimization. The first stage is our main contribution and has two phases, statement grouping and statement scheduling, of which the primary goals are to increase SIMD parallelism and, more importantly, capture more superword reuses among the superword statements through global data access and reuse pattern analysis. Further, as a complementary optimization, our data layout optimization organizes data in memory space such that the price of memory operations for SLP is minimized. The results from our compiler implementation and tests on two systems indicate performance improvements as high as 15.2% over a state-of-the-art SLP optimization algorithm.

Many cloud applications are data intensive requiring the processing of large data sets and the MapReduce/Hadoop architecture has become the de facto processing framework for these applications. Large data sets are stored in data nodes in the cloud which are typically SAN or NAS devices. Cloud applications process these data sets using a large number of application virtual machines (VMs), with the total completion time being an important performance metric. There are many factors that affect the total completion time of the processing task such as the load on the individual servers, the task scheduling mechanism, communication and data access bottlenecks, etc. One dominating factor that affects completion times for data intensive applications is the access latencies from processing nodes to data nodes. Ideally, one would like to keep all data access local to minimize access latency but this is often not possible due to the size of the data sets, capacity constraints in processing nodes which constrain VMs from being placed in their ideal location and so on. When it is not possible to keep all data access local, one would like to optimize the placement of VMs so that the impact of data access latencies on completion times is minimized. We address this problem of optimized VM placement - given the location of the data sets, we need to determine the locations for placing the VMs so as to minimize data access latencies while satisfying system constraints. We present optimal algorithms for determining the VM locations satisfying various constraints and with objectives that capture natural tradeoffs between minimizing latencies and incurring bandwidth costs. We also consider the problem of incorporating inter-VM latency constraints. In this case, the associated location problem is NP-hard with no effective approximation within a factor of 2 - ϵ for any ϵ > 0. We discuss an effective heuristic for this case and evaluate by simulation the impact of the various tradeoffs in the optimization objectives.

BackgroundThe exponential growth in patient data collection by healthcare providers, governments, and private industries is yielding large and diverse datasets that offer new insights into critical medical questions. Leveraging extensive computational resources, Machine Learning and Artificial Intelligence are increasingly utilized to address health-related issues, such as predicting outcomes from Electronic Health Records and detecting patterns in multi-omics data. Despite the proliferation of medical devices based on Artificial Intelligence, data accessibility for research is limited due to privacy concerns. Efforts to de-identify data have met challenges in maintaining effectiveness, particularly with large datasets. As an alternative, synthetic data, that replicate main statistical properties of real patient data, are proposed. However, the lack of standardized evaluation metrics complicates the selection of appropriate synthetic data generation methods. Effective evaluation of synthetic data must consider resemblance, utility and privacy, tailored to specific applications. Despite available metrics, benchmarking efforts remain limited, necessitating further research in this area.ResultsWe present SynthRO (Synthetic data Rank and Order), a user-friendly tool for benchmarking health synthetic tabular data across various contexts. SynthRO offers accessible quality evaluation metrics and automated benchmarking, helping users determine the most suitable synthetic data models for specific use cases by prioritizing metrics and providing consistent quantitative scores. Our dashboard is divided into three main sections: (1) Loading Data section, where users can locally upload real and synthetic datasets; (2) Evaluation section, in which several quality assessments are performed by computing different metrics and measures; (3) Benchmarking section, where users can globally compare synthetic datasets based on quality evaluation.ConclusionsSynthetic data mitigate concerns about privacy and data accessibility, yet lacks standardized evaluation metrics. SynthRO provides an accessible dashboard helping users select suitable synthetic data models, and it also supports various use cases in healthcare, enhancing prognostic scores and enabling federated learning. SynthRO’s accessible GUI and modular structure facilitate effective data evaluation, promoting reliability and fairness. Future developments will include temporal data evaluation, further broadening its applicability.