Multi-core Clusters Research Articles

PARamrfinder: detecting allele-specific DNA methylation on multicore clusters

The discovery of Allele-Specific Methylation (ASM) is an important research field in biology as it regulates genomic imprinting, which has been identified as the cause of some genetic diseases. Nevertheless, the high computational cost of the bioinformatic tools developed for this purpose prevents their application to large-scale datasets. Hence, much faster tools are required to further progress in this research field. In this work we present PARamrfinder, a parallel tool that applies a statistical model to identify ASM in data from high-throughput short-read bisulfite sequencing. It is based on the state-of-the-art sequential tool amrfinder, which is able to detect ASM at regional level from Bisulfite Sequencing (BS-Seq) experiments in the absence of Single Nucleotide Polymorphism information. PARamrfinder provides the same Allelically Methylated Regions as amrfinder but at significantly reduced runtime thanks to exploiting the compute capabilities of common multicore CPU clusters and MPI RMA operations to attain an efficient dynamic workload balance. As an example, our tool is up to 567 times faster for real data experiments on a cluster with 8 nodes, each one containing two 16-core processors. The source code of PARamrfinder, as well as a reference manual, is available at https://github.com/UDC-GAC/PARamrfinder.

ControlPULP: A RISC-V On-Chip Parallel Power Controller for Many-Core HPC Processors with FPGA-Based Hardware-In-The-Loop Power and Thermal Emulation

High-performance computing (HPC) processors are nowadays integrated cyber-physical systems demanding complex and high-bandwidth closed-loop power and thermal control strategies. To efficiently satisfy real-time multi-input multi-output (MIMO) optimal power requirements, high-end processors integrate an on-die power controller system (PCS). While traditional PCSs are based on a simple microcontroller (MCU)-class core, more scalable and flexible PCS architectures are required to support advanced MIMO control algorithms for managing the ever-increasing number of cores, power states, and process, voltage, and temperature variability. This paper presents ControlPULP, an open-source, HW/SW RISC-V parallel PCS platform consisting of a single-core MCU with fast interrupt handling coupled with a scalable multi-core programmable cluster accelerator and a specialized DMA engine for the parallel acceleration of real-time power management policies. ControlPULP relies on FreeRTOS to schedule a reactive power control firmware (PCF) application layer. We demonstrate ControlPULP in a power management use-case targeting a next-generation 72-core HPC processor. We first show that the multi-core cluster accelerates the PCF, achieving 4.9x speedup compared to single-core execution, enabling more advanced power management algorithms within the control hyper-period at a shallow area overhead, about 0.1% the area of a modern HPC CPU die. We then assess the PCS and PCF by designing an FPGA-based, closed-loop emulation framework that leverages the heterogeneous SoCs paradigm, achieving DVFS tracking with a mean deviation within 3% the plant’s thermal design power (TDP) against a software-equivalent model-in-the-loop approach. Finally, we show that the proposed PCF compares favorably with an industry-grade control algorithm under computational-intensive workloads.

Real-time performance evaluation and optimization of electrical substation equipment inspection algorithm based on distributed computing

Abstract Substation equipment inspection faces problems such as large amounts of data, various information types, complex analysis and calculations, and low resource integration. Distributed computing system uses networks to realize computer connectivity and collaboration, achieving in-depth sharing of computing resources, software resources, information resources, and communication resources. Therefore, firstly, this article introduces segmentation method for load balancing and recommendation calculation based on path search; secondly, an algorithm model for substation equipment inspection based on distributed computing is constructed; then, the article analyzes and discusses multi-core cluster task allocation, heterogeneous task scheduling framework, fragmented transmission mechanism, and vertical expansion mechanism; finally, case analysis and performance evaluation are carried out. Distributed computing has significant advantages in the inspection algorithm of power substation equipment. It can efficiently process large-scale data, improve computing power, ensure data redundancy and fault tolerance, provide good scalability, optimize resource utilization, and support remote data processing. By integrating multi-source data, distributed computing improves the accuracy and comprehensiveness of the algorithm, enhances security, supports complex algorithms such as machine learning and deep learning, and realizes real-time monitoring and early warning. The results show that the proposed algorithm can improve the efficiency of distributed parallel computing and analysis of substation equipment inspections and can simulate, evaluate, and screen substation equipment failure scenarios that may cause serious consequences within an effective time.

Large-Scale Meta-Heuristic Feature Selection Based on BPSO Assisted Rough Hypercuboid Approach.

The selection of prominent features for building more compact and efficient models is an important data preprocessing task in the field of data mining. The rough hypercuboid approach is an emerging technique that can be applied to eliminate irrelevant and redundant features, especially for the inexactness problem in approximate numerical classification. By integrating the meta-heuristic-based evolutionary search technique, a novel global search method for numerical feature selection is proposed in this article based on the hybridization of the rough hypercuboid approach and binary particle swarm optimization (BPSO) algorithm, namely RH-BPSO. To further alleviate the issue of high computational cost when processing large-scale datasets, parallelization approaches for calculating the hybrid feature evaluation criteria are presented by decomposing and recombining hypercuboid equivalence partition matrix via horizontal data partitioning. A distributed meta-heuristic optimized rough hypercuboid feature selection (DiRH-BPSO) algorithm is thus developed and embedded in the Apache Spark cloud computing model. Extensive experimental results indicate that RH-BPSO is promising and can significantly outperform the other representative feature selection algorithms in terms of classification accuracy, the cardinality of the selected feature subset, and execution efficiency. Moreover, experiments on distributed-memory multicore clusters show that DiRH-BPSO is significantly faster than its sequential counterpart and is perfectly capable of completing large-scale feature selection tasks that fail on a single node due to memory constraints. Parallel scalability and extensibility analysis also demonstrate that DiRH-BPSO could scale out and extend well with the growth of computational nodes and the volume of data.

Methods, algorithms and programs of computer algebra in problems of registration and analysis of random point structures

An original approach to solving difficult time-consuming problems of registration and analysis of random point images is described. The approach is based on the development and application of high-performance specialized computer algebra systems. Three software packages have been created specifically for carrying out equivalent analytical transformations on a computer. The first software system is designed to calculate formulas describing the volumes of convex polyhedra with parametrically specified boundaries in n-dimensional space. The second system is based on the calculation of multidimensional integral expressions by the method of cyclic differentiation of the integral with respect to the parameter. The third system is based on the accelerated implementation of complex combinatorial-recursive transformations on a computer. Another distinctive feature of the work is the extension of the classical Catalan numbers to the multidimensional case (they were required to solve a number of intermediate probabilistic-combinatorial problems). The implementation of the above computer algebra software systems on a multi-core cluster of Novosibirsk State University, together with the direct use of the explicit form of generalized Catalan numbers, allowed the authors to obtain several new previously unknown probabilistic formulas and dependencies required for solving problems in the field of analysis of random point images.

Unsupervised Fuzzy-Multi-Core Aspect Sentiment Analysis for Big Data of Online News Users' Persian Opinions

An online news article can cover various topics or contain different aspects of a subject, encouraging readers to express their opinions on specific topics or aspects. Sentiment analysis evaluates the overall sentiment of the audience towards the entire news article, whether it is positive, negative, or neutral. However, in aspect-based sentiment analysis, the focus is on determining which aspect of the news article the opinion is referring to. Extracting the relevant aspect in sentiment analysis involves identifying the part of the article that the reader has expressed an opinion about. This task can lead to a more precise analysis of audience reactions to future news and events. To accomplish this, the news text is segmented into constituent sentences and transformed into a vector space. Then, an unsupervised clustering method is applied to extract various aspects of the news. Fuzzy multi-core clustering is employed as the clustering technique, which has lower computational overhead and can handle uncertain, noisy, and outlier data easily. The implemented approach is based on the concept of feasibility and utilizes multi-core learning to detect clusters in complex data structures. This method remains robust against issues such as ineffective cores or unrelated features by automatically adjusting the core weights within an optimized framework. Furthermore, support vector machines are employed to establish the relationship between opinions and relevant aspects. The transition to the vector space, the mapping process, clustering operations, and aspect extraction are performed in the reducer.

Making applications faster by asynchronous execution: Slowing down processes or relaxing MPI collectives

Comprehending the performance bottlenecks at the core of the intricate hardware–software interactions exhibited by highly parallel programs on HPC clusters is crucial. This paper sheds light on the issue of automatically asynchronous MPI communication in memory-bound parallel programs on multicore clusters and how it can be facilitated. For instance, slowing down MPI processes by deliberate injection of delays can improve performance if certain conditions are met. This leads to the counter-intuitive conclusion that noise, independent of its source, is not always detrimental but can be leveraged for performance improvements. We employ phase-space graphs as a new tool to visualize parallel program dynamics. They are useful in spotting certain patterns in parallel execution that will easily go unnoticed with traditional tracing tools. We investigate five different microbenchmarks and applications on different supercomputer platforms: an MPI-augmented STREAM Triad, two implementations of Lattice-Boltzmann fluid solvers (D3Q19 and SPEChpc D2Q37), the LULESH and HPCG proxy applications.

RHDOFS: A Distributed Online Algorithm Towards Scalable Streaming Feature Selection

Feature selection is an important topic in data mining and machine learning, which aims to select an optimal feature subset for building effective and explainable prediction models. This paper introduces Rough Hypercuboid based Distributed Online Feature Selection (RHDOFS) method to tackle two critical challenges of Volume and Velocity associated with Big Data. By exploring the class separability in the boundary region of rough hypercuboid approach, a novel integrated feature evaluation criterion is proposed by examining not only the explicit patterns contained in the positive region but also the useful implicit patterns derived from the boundary region. An efficient online feature selection method for streaming feature scenario is developed to identify relevant and nonredundant features in an incremental iterative fashion. Furthermore, a parallel optimization mechanism by combining both data and computational independence is further employed to accelerate the original sequential implementation. An efficient distributed online feature selection algorithm is presented and implemented on the Apache Spark platform to scale for massive amount of data by exploiting the computational capabilities of multicore clusters. Encouraging results of extensive experiments indicate the superiority and notable advantages of the proposed algorithm over the relevant and representative online feature selection algorithms. Empirical tests on scalability and extensibility also demonstrate our distributed implementation significantly reduces the computational times requirements while maintaining the prediction accuracy, and is capable of scaling well in volume of data and number of computing nodes.

ParRADMeth: Identification of Differentially Methylated Regions on Multicore Clusters.

The discovery of Differentially Methylated (DM) regions is an important research field in biology, as it can help to anticipate the risk of suffering from specific diseases. Nevertheless, the high computational cost of the bioinformatic tools developed for this purpose prevents their application to large-scale datasets. Hence, much faster tools are required to further progress in this research field. In this work we present ParRADMeth, a parallel tool that applies beta-binomial regression for the identification of these DM regions. It is based on the state-of-the-art sequential tool RADMeth, which proved superior biological accuracy compared to counterparts in previous experimental evaluations. ParRADMeth provides the same DM regions as RADMeth but at significantly reduced runtime thanks to exploiting the compute capabilities of common multicore CPU clusters. For example, our tool is up to 189 times faster for real data experiments on a cluster with 16 nodes, each one containing two eight-core processors. The source code of ParRADMeth, as well as a reference manual, are available at https://github.com/UDC-GAC/ParRADMeth.

A New Hybrid Hierarchical Parallel Algorithm to Enhance the Performance of Large-Scale Structural Analysis Based on Heterogeneous Multicore Clusters

Heterogeneous multicore clusters are becoming more popular for high-performance computing due to their great computing power and cost-to-performance effectiveness nowadays. Nevertheless, parallel efficiency degradation is still a problem in large-scale structural analysis based on heterogeneous multicore clusters. To solve it, a hybrid hierarchical parallel algorithm (HHPA) is proposed on the basis of the conventional domain decomposition algorithm (CDDA) and the parallel sparse solver. In this new algorithm, a three-layer parallelization of the computational procedure is introduced to enable the separation of the communication of inter-nodes, heterogeneous-core-groups (HCGs) and inside-heterogeneous-core-groups through mapping computing tasks to various hardware layers. This approach can not only achieve load balancing at different layers efficiently but can also improve the communication rate significantly through hierarchical communication. Additionally, the proposed hybrid parallel approach in this article can reduce the interface equation size and further reduce the solution time, which can make up for the shortcoming of growing communication overheads with the increase of interface equation size when employing CDDA. Moreover, the distributed sparse storage of a large amount of data is introduced to improve memory access. By solving benchmark instances on the Shenwei-Taihuzhiguang supercomputer, the results show that the proposed method can obtain higher speedup and parallel efficiency compared with CDDA and more superior extensibility of parallel partition compared with the two-level parallel computing algorithm (TPCA).

Detecting the city-scale spatial pattern of the urban informal sector by using the street view images: A street vendor massive investigation case

Automatically obtaining information on informal practitioners, especially their spatial distribution, has proven challenging when using traditional methods. This study addresses this issue by presenting a street view deep learning method, called the Street Informal Practitioners Spatial Investigation (SIPSI) methodology. This paper's application of this technology focuses on the study case of the street vendor, which is one of the most visible occupations in the informal economy. There were 3907 street vendors that were detected using this method; as well, the kernel density estimation indicated that they agglomerated in a multi-core cluster pattern in the city. Further analysis of the factors that influence agglomeration shows that the street vendors prefer premises that are near the lower level of the road and the higher density population sites, whereas the NIMBY (Not In My Back Yard) syndrome keeps these vendors away from the central City Business Districts and high-rent regions. The presented methodology and the study results contribute to high-efficiency investigations of informal economy employment, and it further assists in advising for the spatial governance policies improvement and implementation in any cities whose street view images are abundant and open-access.

Spatial Pattern and Influencing Factors of Rural Settlements in Qinba Mountains, Shaanxi Province, China

Spatial patterns and the influencing determinants of rural settlements are the most important indicators for understanding the constituent structure of rural regional systems. However, there is little knowledge addressing the characteristics from the settlement perspective by realizing the spatial reconstruction and sustainable development of rural settlements. Therefore, in this study, we analyzed the geographical, size, and morphological properties of rural settlement patterns in the Qinba Mountains in southern Shaanxi Province, China, using rural settlement and remote sensing data through spatial measurement index, gradient transects, demographic-economic index, and geodetector analysis. The results show the following: (1) Overall, rural settlements have spatial characteristics of “high-density multi-core clusters (0.8–1.6/km2) and low-density broadly scattered (<0.08/km2)”. There is a significant positive correlation between the scale of rural settlement density and the characteristics of high-value agglomeration. (2) The spatial disparities of morphological traits of settlement shapes are significant. Furthermore, 1840 NP/piece of plain basin landform types provide high-value areas for each settlement feature value, and locations with moderate slopes are best for settlement dispersal. Moreover, rivers, roads, and distance from township centers are all examples of beneficial directivity. There is consistency between the spatial differentiation of rural settlement areas per capita and the distribution of settlement scale. Conversely, the settlement density is inconsistent with the agricultural production value density’s spatial distribution features. (3) The impact of geographical factors on the diversification of settlement characteristics has significant spatial differences. Moreover, natural ecological characteristics such as elevation and landform and the distribution of cultivated land strongly influence the spatial pattern of the study region. Finally, the study findings can be beneficial for land and space planning and rural governments to develop sustainable rural settlements.

Parallel-FST: A feature selection library for multicore clusters

Feature selection is a subfield of machine learning focused on reducing the dimensionality of datasets by performing a computationally intensive process. This work presents Parallel-FST, a publicly available parallel library for feature selection that includes seven methods which follow a hybrid MPI/multithreaded approach to reduce their runtime when executed on high performance computing systems. Performance tests were carried out on a 256-core cluster, where Parallel-FST obtained speedups of up to 229x for representative datasets and it was able to analyze a 512 GB dataset, which was not previously possible with a sequential counterpart library due to memory constraints.

Optimization of Sparse Distributed Computations

We address the problem of the optimization of sparse matrix-vector product (SpMV) on homogeneous distributed systems. For this purpose, we propose three approaches based on partitioning the matrix into row blocks. These blocks are defined by a set of a fixed number of rows and a set of contiguous (resp. non-contiguous) rows containing a fixed number of non-zero elements. These approaches lead to solve some specific NP-hard scheduling problems. Thus, adequate heuristics are designed. We analyse the theoretical performance of the proposed approaches and validate them by a series of experiments. This work represents an important step in an overall objective which is to determine the best-balanced distribution for the SpMV computation on a distributed system. In order to validate our approaches for sparse matrix distribution, we compare them to hypergraph model as well as to PETSc library for SpMV distribution on a homogenous multicore cluster. Experimentations show that our approaches provide performances 2 times better than hypergraph and 49 times better than PETSc.

Batch-sequential design and heteroskedastic surrogate modeling for delta smelt conservation

Delta smelt is an endangered fish species in the San Francisco estuary that have shown an overall population decline over the past 30 years. Researchers have developed a stochastic, agent-based simulator to virtualize the system with the goal of understanding the relative contribution of natural and anthropogenic factors that might play a role in their decline. However, the input configuration space is high dimensional, running the simulator is time-consuming, and its noisy outputs change nonlinearly in both mean and variance. Getting enough runs to effectively learn input–output dynamics requires both a nimble modeling strategy and parallel evaluation. Recent advances in heteroskedastic Gaussian process (HetGP) surrogate modeling helps, but little is known about how to appropriately plan experiments for highly distributed simulation. We propose a batch sequential design scheme, generalizing one-at-a-time variance-based active learning for HetGP, as a means of keeping multicore cluster nodes fully engaged with runs. Our acquisition strategy is carefully engineered to favor selection of replicates which boost statistical and computational efficiency when training surrogates to isolate signal from noise. Design and modeling are illustrated on a range of toy examples before embarking on a large-scale smelt simulation campaign and downstream high-fidelity input sensitivity analysis.

Research on Library Book Information Resource Management Based on Artificial Intelligence and Sensors

In order to explore the research on library book information resource management, the author proposes a method based on artificial intelligence and sensors. Using an improved SVM algorithm, in order to realize the personalized data mining of the library, the support vector machine algorithm has supervised, scalable, and nonlinear high-efficiency characteristics in the use process, able to achieve nonlinear multicore data clustering effect, thereby improving the learning ability of data mining. The experimental results show the following: BP neural network was used to adaptively train the processed data samples, users give certain positive feedback during use, the sensor system is based on the result of feedback, continuous self-learning was carried out, sample data were updated and optimized, and a closed virtuous circle has been realized. In the classification experiment of Sogou Chinese text corpus data set, the classification effect of several classification models in the “sports” category is significantly higher than that of other categories; it shows that the text classification characteristics of the “sports” category are more significant. Among them, KNN ( K -Nearest Neighbor) has a classification accuracy of 99.7% in the “sports” category; this shows that some classification algorithms, in a specific category, can achieve its best classification performance. Prove the method based on artificial intelligence; it can better realize library book information resource management.

Model-based selection of optimal MPI broadcast algorithms for multi-core clusters

The performance of collective communication operations determines the overall performance of MPI applications. Different algorithms have been developed and implemented for each MPI collective operation, but none proved superior in all situations. Therefore, MPI implementations have to solve the problem of selecting the optimal algorithm for the collective operation depending on the platform, the number of processes involved, the message size(s), etc. The current solution method is purely empirical.Recently, an alternative solution method using analytical performance models of collective algorithms has been proposed and proved both accurate and efficient for one-process-per-CPU configurations. The method derives the analytical performance models of algorithms from their code implementation rather than from high-level mathematical definitions, and estimates the parameters of the models separately for each algorithm. The method is network and topology oblivious and uses the Hockney model for point-to-point communications. In this paper, we extend that selection method to the case of clusters of multi-core processors, where each core of the platform runs a process of the MPI application.We present the proposed approach using Open MPI broadcast algorithms, and experimentally validate it on three different clusters of multi-core processors, Grisou, Gros and MareNostrum4.

A parallel time series algorithm for searching similar sub-sequences

<p><span>Dynamic time warping (DTW) is an important metric for measuring similarity for most time series applications. The computations of DTW cost too much especially with the gigantic of sequence databases and lead to an urgent need for accelerating these computations. However, the multi-core cluster systems, which are available now, with their scalability and performance/cost ratio, meet the need for more powerful and efficient performance. This paper proposes a highly efficient parallel vectorized algorithm with high performance for computing DTW, addressed to multi-core clusters using the Intel quad-core Xeon co-processors. It deduces an efficient architecture. Implementations employ the potential of both message passing interface (MPI) and OpenMP libraries. The implementation is based on the OpenMP parallel programming technology and offloads execution mode, where part of the code sub-sequences on the processor side, which are uploaded to the co-processor for the DTW computations. The results of experiments confirm the effectiveness of the algorithm.</span></p>

A highly optimized skeleton for unbalanced and deep divide-and-conquer algorithms on multi-core clusters

AbstractEfficiently implementing the divide-and-conquer pattern of parallelism in distributed memory systems is very relevant, given its ubiquity, and difficult, given its recursive nature and the need to exchange tasks and data among the processors. This task is noticeably further complicated in the presence of multi-core systems, where hybrid parallelism must be exploited to attain the best performance, and when unbalanced and deep workloads are considered, as additional measures must be taken to load balance and avoid deep recursion problems. In this manuscript a parallel skeleton that fulfills all these requirements while providing high levels of usability is presented. In fact, the evaluation shows that our proposal is on average 415.32% faster than MPI codes and 229.18% faster than MPI + OpenMP benchmarks, while offering an average improvement in the programmability metrics of 131.04% over MPI alternatives and 155.18% over MPI + OpenMP solutions.

Prediction of multicore CPU performance through parallel data mining on public datasets

In the present scenario, high-performance computing needs more attention towards multicore computing. While designing the CPU, we need to consider hardware for processing speed, cache bandwidth, minimum memory requirements, etc. So for the selection of the best combination of CPU data mining tools may play an important role. In this era, data mining attracts more interest on parallel computing to enhance the performance of multicores. This paper demonstrates a parallel strategy similar to the traditional parallel programming paradigm to improve the performance of multicores by using a data mining approach. We have selected one approach EM with Gaussian and analyze the impact of its parallel execution on selected multicore clusters obtained through data mining. We have also evaluated our finding with a virtual environment of having 32 different families of CPUs, showing a speedup of up to ≈1.02x. This paper considers data clusters, cache mapping techniques and ranking of MPI programming techniques.