Multi-threaded Environment Research Articles

Caveats of three direct linear solvers for finite element analyses

AbstractThe solution of large linear systems of equations with sparse matrices is a critical component of finite element analyses. Three linear solvers are investigated here: MUMPS, UMFPACK, and Intel DSS (PARDISO). Often, these solvers are employed as “black boxes.” However, some caveats in their implementation must be observed. For instance, the solvers may yield incorrect results or perform extremely poorly in a multithread environment. These issues are demonstrated, and suggestions to fix them are provided. Some performance benchmarks are also presented with a focus on the multithreaded behavior.

GraphTango: A Hybrid Representation Format for Efficient Streaming Graph Updates and Analysis

Streaming graph processing performs batched updates and analytics on a time-evolving graph. The underlying representation format of the graph largely determines the throughputs of these updates and analytics phases. Existing representation formats usually employ variations of hash tables or adjacency lists. However, a recent study showed that the adjacency-list-based approaches perform poorly on heavy-tailed graphs, and the hash table-based approaches suffer on short-tailed graphs. We propose GraphTango, a hybrid representation format that provides excellent update and analytics throughput regardless of the graph’s degree distribution. GraphTango dynamically switches among three different formats based on a vertex’s degree: (i) Low-degree vertices store the edges directly with the neighborhood metadata, confining accesses to a single cache line, (2) Medium-degree vertices use adjacency lists, and (3) High-degree vertices use hash tables as well as adjacency lists. In this case, the adjacency list provides fast traversal during the analytics phase, while the hash table provides constant-time lookups during the update phase. We further optimized the performance by designing an open-addressing-based hash table that fully utilizes every fetched cache line. In addition, we developed a thread-local lock-free memory pool that allows fast growing/shrinking of the adjacency lists and hash tables in a multi-threaded environment. We evaluated GraphTango with the help of the SAGA-Bench framework and compared it with four other representation formats: Stinger, Degree-aware Robin Hood Hashing, and two adjacency list-based formats with different workload balancing scheme. On average, GraphTango provides 4.5x higher insertion throughput, 3.2x higher deletion throughput, and 1.1x higher analytics throughput over the next best format. Furthermore, we integrated GraphTango with the state-of-the-art graph processing frameworks DZiG and RisGraph. Compared to the vanilla DZiG and vanilla RisGraph, [GraphTango + DZiG] and [GraphTango + RisGraph] reduces the average batch processing time by 2.3x and 1.5x, respectively.

Efficient end-to-end long-read sequence mapping using minimap2-fpga integrated with hardware accelerated chaining

minimap2 is the gold-standard software for reference-based sequence mapping in third-generation long-read sequencing. While minimap2 is relatively fast, further speedup is desirable, especially when processing a multitude of large datasets. In this work, we present minimap2-fpga, a hardware-accelerated version of minimap2 that speeds up the mapping process by integrating an FPGA kernel optimised for chaining. Integrating the FPGA kernel into minimap2 posed significant challenges that we solved by accurately predicting the processing time on hardware while considering data transfer overheads, mitigating hardware scheduling overheads in a multi-threaded environment, and optimizing memory management for processing large realistic datasets. We demonstrate speed-ups in end-to-end run-time for data from both Oxford Nanopore Technologies (ONT) and Pacific Biosciences (PacBio). minimap2-fpga is up to 79% and 53% faster than minimap2 for sim 30times ONT and sim 50times PacBio datasets respectively, when mapping without base-level alignment. When mapping with base-level alignment, minimap2-fpga is up to 62% and 10% faster than minimap2 for sim 30times ONT and sim 50times PacBio datasets respectively. The accuracy is near-identical to that of original minimap2 for both ONT and PacBio data, when mapping both with and without base-level alignment. minimap2-fpga is supported on Intel FPGA-based systems (evaluations performed on an on-premise system) and Xilinx FPGA-based systems (evaluations performed on a cloud system). We also provide a well-documented library for the FPGA-accelerated chaining kernel to be used by future researchers developing sequence alignment software with limited hardware background.

Cloud Key-Value Storage

The paper represents all the stages of designing, architecting, and developing cloud-based key-value storage. This work aims to bring new approaches to distributed data systems. The authors focus on the security and productivity of the project as well as security and maintainability. The authors have studied the use of hash tables in a multi-threaded environment. Architectural approaches and tools have been described. The general structure of the key-value storage server has been presented. The server algorithm has been presented. Our research delves into the intricate nuances of utilizing hash tables in a multi-threaded environment, shedding light on the intricacies and challenges of managing concurrent access to key-value data structures. The authors have explored the trade-offs between lock-free designs and traditional locking approaches.

Application of multi agent systems for advanced energy management in cyber physical hybrid microgrid systems

This paper develops a multi agent system in real time for hybrid microgrids as advanced energy management (ADEM) protocol using a Java agent development environment (JADE) frame work. The proposed system is configured with two micro-grids, each having 1kw solar photo voltaic power, 1.5Kw wind power, 24 V, 150AH battery along with a local load, thus making it a hybrid Microgrid, modelled in MATLAB/Simulink. Due stability constraints while using MATLAB/Simulink, in a multi-threading environment, a middle ware called Multi agent Control Using Simulink with Jade Extension (MACSimJX) is adopted. The microgrid environment variables are captured through sensors, delivered to the agents operations in JADE, for the implementation of dynamic operation in hybrid microgrids. This results in maximizing operational efficiency of hybrid microgrids system. The simulation suggests that MAS can successfully manage dynamic loads, generated power in real time microgrids.

Classification of Large-Scale Datasets of Landsat-8 Satellite Image Based on LIBLINEAR Library

One of the most common machine learning approaches is linear classification. Multithreading used in LIBLINEAR Library has become an important research topic for processing large datasets. Working in a multithreaded environment accelerates the training of large datasets and increases classification accuracy. This study examines multiple linear support vector machine implementations for binary classification of Landsat-8 satellite image datasets to determine the optimal model. Four datasets have been created for different scenes in Iraq. Each dataset contains millions of pixels to be classified optimally. This article selects an appropriate algorithm for such a large dataset of current types in the LIBLINEAR library optimal for organizing large datasets using the linear SVM algorithm. Each dataset containing about 4.5 million samples was used to test the performance. The seven linear SVM techniques have statically examined the most effective SVM implementation method. Accuracy, F-Score, and Kappa are used as model assessment measures to evaluate and rank the models' performances. Based on the results, the LibLINEAR library with type 4 (LINLINEAR4) classifier was the best classifier for satellite image classification in remote sensing when applied to large datasets. The accuracy, Kappa, and f-score of the LIBLINEAR 4 classifier are as follows: (92.89 %), (73.53 %), and (77.77%) with dataset1, (96.25 %), (59.97 %), and (61.88%) with dataset2, (96.65%), (68.33%), and (70.03%), and (94.72%), (53.67%), and (56.25%), respectively, with dataset4.

Classification of Large-Scale Datasets of Landsat-8 Satellite Image Based on LIBLINEAR Library

One of the most common machine learning approaches is linear classification. Multithreading used in LIBLINEAR Library has become an important research topic for processing large datasets. Working in a multithreaded environment accelerates the training of large datasets and increases classification accuracy. This study examines multiple linear support vector machine implementations for binary classification of Landsat-8 satellite image datasets to determine the optimal model. Four datasets have been created for different scenes in Iraq. Each dataset contains millions of pixels to be classified optimally. This article selects an appropriate algorithm for such a large dataset of current types in the LIBLINEAR library optimal for organizing large datasets using the linear SVM algorithm. Each dataset containing about 4.5 million samples was used to test the performance. The seven linear SVM techniques have statically examined the most effective SVM implementation method. Accuracy, F-Score, and Kappa are used as model assessment measures to evaluate and rank the models' performances. Based on the results, the LibLINEAR library with type 4 (LINLINEAR4) classifier was the best classifier for satellite image classification in remote sensing when applied to large datasets. The accuracy, Kappa, and f-score of the LIBLINEAR 4 classifier are as follows: (92.89 %), (73.53 %), and (77.77%) with dataset1, (96.25 %), (59.97 %), and (61.88%) with dataset2, (96.65%), (68.33%), and (70.03%), and (94.72%), (53.67%), and (56.25%), respectively, with dataset4.

Swarm of Honey Bees for Association Rule Mining Using CUDA

Association Rule mining (ARM) is well studied and famous optimization problem which finds useful rules from given transactional databases. Many algorithms already proposed in literature which shows their efficiency when dealing with different sizes of datasets. Unfortunately, their efficiency is not enough for handling large scale datasets. In this case, Bees swarm optimization algorithm for association rule mining is more efficient. These kinds of problems need more powerful processors and are time expensive. For such issues solution can be provided by graphics processing units (GPUs) and are massively multithreaded processors. In this case GPUs can be used to increase speed of the computation. Bees swarm optimization algorithm for association rule mining can be designed using GPUs in multithreaded environment which will efficient for given datasets.

A Multi-hashing Index for hybrid DRAM-NVM memory systems

Hybrid memory systems composed of DRAM and Non-Volatile Memory (NVM) promise the capacity benefits of NVM and the low-latency benefits of DRAM. Most existing hash-based indexes are designed for NVM only and do not exploit the benefits of DRAM. In this paper, we proposed a novel hybrid DRAM-NVM persistent and concurrent hashing index, named Multi-Hashing Index (MuHash). MuHash uses a multi-hash function scheme to solve the cascading write problem of open-addressed hash-based indexes in NVM. It employs a Cuckoo Filter, an approximate membership query data structure, to prune unnecessary NVM accesses for improving read performance. To maximize throughput in multi-thread environments, MuHash also includes a fine-grained concurrency control mechanism. We implemented MuHash for Intel Optane DC Persist Memory, and single-core experiments shows that MuHash achieves up to 90% higher read throughput compared to state-of-the-art hash-based indexes. On multicore experiments, MuHash achieves near-linear scalability for all operations.

To share or not to share vector registers?

Query execution techniques in database systems constantly adapt to novel hardware features to achieve high query performance, in particular for analytical queries. In recent years, vectorization based on the Single Instruction Multiple Data parallel paradigm has been established as a state-of-the-art approach to increase single-query performance. However, since concurrent analytical queries running in parallel often access the same columns and perform a same set of vectorized operations, data accesses and computations among different queries may be executed redundantly. Various techniques have already been proposed to avoid such redundancy, ranging from concurrent scans via the construction of materialized views to applying multiple query optimization techniques. Continuing this line of research, we investigate the opportunity of sharing vector registers for concurrently running queries in analytical scenarios in this paper. In particular, our novel sharing approach relies on processing data elements of different queries together within a single vector register. As we are going to show, sharing vector registers to optimize the execution of concurrent analytical queries can be very beneficial in single-threaded as well as multi-thread environments. Therefore, we demonstrate the feasibility and applicability of such a novel work sharing strategy and thus open up a wide spectrum of future research opportunities.

Improving the Efficiency of Calculating B-splines in parallel Programming Tasks

The use of parallel computing tools can significantly reduce the execution time of calculations in many engineer­ing tasks. One of the main difficulties in the development of multithreaded programs remains the organization of simultaneous access from different threads to shared data. The most common solution to this problem is to use locking facilities when accessing shared data. There are a number of tasks where data sharing is not needed, but you need to synchronize access to a limited resource, such as a temporary buffer. In such tasks, there is no data exchange between different threads, but there is an object that at a given time can be used by the code of only one thread. One such task is calculating the value of a B-spline. The software implementation of the functions for calculating B-splines, performed according to classical algorithms, requires the use of blocking objects when accessing the common array of intermediate data from different threads. This reduces the degree of parallelism and reduces the efficiency of computational programs using B-splines running on multiprocessor computing systems. The article discusses a way to improve the efficiency of calculating B-splines in parallel programming tasks by eliminating locks when accessing general modified data. A soft­ware implementation is presented in the form of a C++ class template, which provides placement of a temporary array used for calculating a B-spline into a local buffer of a given size with the possibility of increasing it if necessary. Using the developed template in conjunction with the threadlocal qualifier reduces the number of requests for increasing the buffer for high degree B-splines (larger than the initially specified buffer size). It is also possible to implement this scheme using the std::vector template of the C++ STL Standard Library. The results of the application of the developed class when calculating the values of B-splines in a multithreaded environment, showing a reduction in the calculation time in proportion to an increase in the number of computational processors, are presented. The methods of specifying arrays for storing intermediate calculation results considered in this article can be used in other parallel programming tasks.

Pipelined XPath Query Based on Cost Optimization

XPath query is the key part of XML data processing, and its performance is usually critical for XML applications. In the process of XPath query, there is inherent seriality between query steps, which makes it difficult to parallelize the query effectively as a whole. On the other hand, although XPath query has the characteristics of data stream processing and is suitable for pipeline processing, the data flow of each query step usually varies a lot, which results in limited performance under multithreading conditions. In this paper, we propose a pipelined XPath query method (PXQ) based on cost optimization. This method uses pipelined query primitives to process query steps based on relation index. During pipeline construction, a cost estimation model based on XML statistics is proposed to estimate the cost of the query primitive and provide guidance for the creation of a pipeline phase through the partition of query primitive sequence. The pipeline construction technique makes full use of available worker threads and optimizes the load balance between pipeline stages. The experimental results show that our method can adapt to the multithreaded environment and stream processing scenarios of XPath query, and its performance is better than the existing typical query methods based on data parallelism.

Big Data Analytics for Energy Consumption Prediction in Smart Grid Using Genetic Algorithm and Long Short Term Memory

Smart Grids (SG) have smart meters and advance metering infrasturutre (AMI) which generates huge data. This data can be used for predicting energy consumption using big data analytics. A very limited work has been carried out in the literature which shows the utilization of big data in energy consumption prediction. In this paper, the proposed method is based on Genetic Algorithm - Long Short Term Memory (GA-LSTM). LSTM memorises values over an arbitrary interval that manages time series data very effictively while GA is an evolutionary process that is used for optimization. GA combines with LSTM to process hyperparameters such as hidden layers, epochs, data intervals, batchsize and activation functions. Hence, GA creates a new vector for optimum solution that provides minimum error. These methods provide the best performance when compared with existing benchmarks. Moreover, GA-LSTM is used in a multi-threaded environment which increases the speed of convergence. Here, the multi-core platform is operated for solving one-dimensional GA-based inverse scattering problems. The result shows that GA-LSTM provides better convergence as compared to random approach techniques. For validating the results, Pennsylvania-New Jersey-Maryland Interconnection (PJM) energy consumption data has been used while adopting different performance evaluation metrics.

A Fast Progressive TIN Densification Filtering Algorithm for Airborne LiDAR Data Using Adjacent Surface Information

Point cloud filtering is a preliminary and essential step in various applications of airborne LiDAR (light detection and ranging) data, with progressive triangulated irregular network (TIN) densification (PTD) being one of the classic methods for filtering LiDAR point clouds. The PTD algorithm densifies ground points through iteration operation based on initial ground seed points. However, the poor performance in steeply sloped areas and time-consuming processing are serious drawbacks for PTD algorithms. In this paper, we propose a fast progressive TIN densification (FPTD) filtering algorithm for airborne LiDAR data using adjacent surface information. After carefully establishing parameters and removing outliers, our improved FPTD uses a sliding window to obtain significantly more initial ground seed points. And we modified some iterative determination criterion, including the definition of maximum relative elevation threshold and the introduction of signed computation, to eliminate avoidable non-ground points. Then adjacent surface information was utilized to iterate each point cloud block, which is the smallest unit that point cloud can be segmented. Additionally, the algorithm is easily run in a multi-threaded environment, further accelerating the filtering process to some extent. Experiments show that our proposed FPTD filtering algorithm is fast and robust. Compared to the PTD, the FPTD algorithm yields better error rates and kappa coefficients in 1/12 of the time required by the PTD.

ATLAS in-file metadata and multi-threaded processing

Processing and scientific analysis of the data taken by the ATLAS experiment requires reliable information describing the event data recorded by the detector or generated in software. ATLAS event processing applications store such descriptive metadata information in the output data files along with the event information. To better leverage the available computing resources during LHC Run3 the ATLAS experiment has migrated its data processing and analysis software to a multi-threaded framework: AthenaMT. Therefore in-file metadata must support concurrent event processing, especially around input file boundaries. The in-file metadata handling software was originally designed for serial event processing. It grew into a rather complex system over the many years of ATLAS operation. To migrate this system to the multi-threaded environment it was necessary to adopt several pragmatic solutions, mainly because of the shortage of available person-power to work on this project in early phases of the AthenaMT development. In order to simplify the migration, first the redundant parts of the code were cleaned up wherever possible. Next the infrastructure was improved by removing reliance on constructs that are problematic during multi-threaded processing. Finally, the remaining software infrastructure was redesigned for thread safety.

Development platform for artificial pancreas algorithms

Assessing algorithms of artificial pancreas systems is critical in developing automated and fault-tolerant solutions that work outside clinical settings. The development and evaluation of algorithms can be facilitated with a platform that conducts virtual clinical trials. We present in this paper a clinically validated cloud-based distributed platform that supports the development and comprehensive testing of single and dual-hormone algorithms for type 1 diabetes mellitus (T1DM). The platform is built on principles of object-oriented design and runs user algorithms in real-time virtual clinical trials utilizing a multi-threaded environment enabled by concurrent execution over a cloud infrastructure. The platform architecture isolates user algorithms located on personal machines from proprietary patient data running on the cloud. Users import a plugin into their algorithms (Matlab, Python, or Java) to connect to the platform. Once connected, users interact with a graphical interface to design experimental protocols for their trials. Protocols include trial duration in days, mealtimes and amounts, variability in mealtimes and amounts, carbohydrate counting errors, snacks, and onboard insulin levels. The platform facilitates development by solving the ODE model in the cloud on large CPU-optimized machines, providing a 62% improvement in memory, speed and CPU utilization. Users can easily debug & modify code, test multiple strategies, and generate detailed clinical performance reports. We validated and integrated into the platform a glucoregulatory system of ordinary differential equations (ODEs) parameterized with clinical data to mimic the inter and intra-day variability of glucose responses of 15 T1DM patients. The platform utilizes the validated patient model to conduct virtual clinical trials for the rapid development and testing of closed-loop algorithms for T1DM.

Resettable Encoded Vector Clock for Causality Analysis With an Application to Dynamic Race Detection

Causality tracking among events is a fundamental challenge in distributed environments. Much previous work on this subject has focused on designing an efficient and scalable protocol to represent logical time. Several implementations of logical clocks have been proposed, most recently the Encoded Vector Clock (EVC), a protocol to encode Vector Clocks (VC) in scalar numbers through the use of prime numbers, to improve performance and scalability. We propose and formalize the concept of Resettable Encoded Vector Clock (REVC), a new logical clock implementation, which builds on the EVC to tackle its very high growth rate issue. We show how our REVC can be applied in both shared memory systems and message passing systems to achieve a consistent logical clock. We show, through practical examples, the advantage of REVC's growth rate with respect to EVC's growth rate. Finally, we show a practical application of the REVC to the dynamic race detection problem in multi-threaded environments. We compare our tool to the currently existing VC-based tool DJIT <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">+</sup> to show how the REVC can help in achieving higher performance with respect to the Vector Clock.

Parallel-Based Techniques for Managing and Analyzing the Performance on Semantic Graph

In recent years, data are generated rapidly that advanced the evolving of the linked data. Modern data are globally distributed over the semantically linked graphs. The nature of the distributed data over the semantic graph raised new demands on further investigation on improving performance on the semantic graphs. In this work, we analyzed the time latency as an important factor to be further investigated and improved. We evaluated the parallel computing on these distributed data in order to better utilize the parallelism approaches. A federation framework based on a multi-threaded environment supporting federated SPARQL query was introduced. In our experiments, we show the achievability and effectiveness of our model on a set of real-world quires through real-world Linked Open Data cloud. Significant performance improvement has noticed. Further, we highlight short-comings that could open an avenue in the research of federated queries. Keywords: Semantic web; distributed query processing; query federation; linked data; join methods.

An intelligent memory caching architecture for data-intensive multimedia applications

With the rapid developments in cloud computing and mobile networks, multimedia content can be accessed conveniently. Recently, some novel intelligent caching-based approaches have been proposed to improve the memory architectures for multimedia applications. These applications often face bottleneck related challenges which result in performance degradation and service delay issues. Intelligent multimedia network applications access the shared data by using a specific network file system. This results in answering the processing related constraints on hard-drive storage and might result in bringing bottleneck issues. Therefore, to improve the performance of these multimedia network applications, we present an intelligent distributed memory caching system. We integrate the multimedia application message passing interface in a multi-threaded environment and propose an algorithm which can handle concurrent response behavior for different multimedia applications. Results demonstrate that our proposed scheme outperforms traditional approaches in terms of throughput and file read access features.

Prime clock: Encoded vector clock to characterize causality in distributed systems

The vector clock is a fundamental tool for tracking causality in distributed applications. Unfortunately, it does not scale well to large systems because each process needs to maintain a vector of size n, where n is the total number of processes in the system. To address this problem, we propose the prime clock, which is based on the encoding of the vector clock using prime numbers and uses a single number to represent vector time. We propose the operations on the encoded vector clock (EVC). We then show how to timestamp global states and how to perform operations on the global states using the EVC. Using a theoretical analysis and a simulation model, we evaluate the growth rate of the size of the EVC. The EVC is seen to grow very fast and hence it does not appear to offer a general purpose practical replacement of vector clocks. To address this drawback, we propose several scalability techniques for the EVC that can allow the use of the EVC in practical applications. We then present two case studies of detecting memory consistency errors in MPI one-sided applications and of dynamic race detection in multi-threaded environments, that use a combination of two of these scalability techniques. The results show that the EVC is not just a theoretical concept, but it is applicable to practical problems and can compete in terms of both space and time requirements with other known protocols.