Parallel Processing Research Articles

A hardware-implemented neural network for the analysis of handwritten numerals

This study presents a specialized hardware-accelerated neural network tailored for the recognition of handwritten digits in 28x28 pixel grayscale images. Employing the perceptron model, our single-layer neural network is composed of 10 neurons, each handling inputs from all pixels to generate an output. The digit recognition is determined by the neuron with the highest output value. Implemented in synthesizable Verilog, the design complies with a constraint of 350 multipliers. To achieve this, this paper employs a combination of parallel processing and pipelining, breaking down the 785 multiplications needed for each digit into 8 stages, simultaneously processing 98 data points per clock cycle. In testbench evaluations, the final design exhibits impressive performance, successfully recognizing the majority of the provided images, and attaining a remarkable 99% accuracy rate, all with a minimal delay of just 115 clocks. This accomplishment is achieved using only 99 multipliers and 107 adders, showcasing the efficiency and effectiveness of our hardware-accelerated neural network for handwritten digit recognition.

Krisp: A Python package to aid in the design of CRISPR and amplification-based diagnostic assays from whole genome sequencing data.

Recent pandemics like COVID-19 highlighted the importance of rapidly developing diagnostics to detect evolving pathogens. CRISPR-Cas technology has recently been used to develop diagnostic assays for sequence-specific recognition of DNA or RNA. These assays have similar sensitivity to the gold standard qPCR but can be deployed as easy to use and inexpensive test strips. However, the discovery of diagnostic regions of a genome flanked by conserved regions where primers can be designed requires extensive bioinformatic analyses of genome sequences. We developed the Python package krisp to aid in the discovery of primers and diagnostic sequences that differentiate groups of samples from each other, using either unaligned genome sequences or a variant call format (VCF) file as input. Krisp has been optimized to handle large datasets by using efficient algorithms that run in near linear time, use minimal RAM, and leverage parallel processing when available. The validity of krisp results has been demonstrated in the laboratory with the successful design of a CRISPR diagnostic assay to distinguish the sudden oak death pathogen Phytophthora ramorum from closely related Phytophthora species. Krisp is released open source under a permissive license with all the documentation needed to quickly design CRISPR-Cas diagnostic assays.

Parallel Spatio-Temporal Attention Transformer for Video Frame Interpolation

Traditional video frame interpolation methods based on deep convolutional neural networks face challenges in handling large motions. Their performance is limited by the fact that convolutional operations cannot directly integrate the rich temporal and spatial information of inter-frame pixels, and these methods rely heavily on additional inputs such as optical flow to model motion. To address this issue, we develop a novel framework for video frame interpolation that uses Transformer to efficiently model the long-range similarity of inter-frame pixels. Furthermore, to effectively aggregate spatio-temporal features, we design a novel attention mechanism divided into temporal attention and spatial attention. Specifically, spatial attention is used to aggregate intra-frame information, integrating both attention and convolution paradigms through the simple mapping approach. Temporal attention is used to model the similarity of pixels on the timeline. This design achieves parallel processing of these two types of information without extra computational cost, aggregating information in the space–time dimension. In addition, we introduce a context extraction network and multi-scale prediction frame synthesis network to further optimize the performance of the Transformer. Our method and state-of-the-art methods are extensively quantitatively and qualitatively experimented on various benchmark datasets. On the Vimeo90K and UCF101 datasets, our model achieves improvements of 0.09 dB and 0.01 dB in the PSNR metrics over UPR-Net-large, respectively. On the Vimeo90K dataset, our model outperforms FLAVR by 0.07 dB, with only 40.56% of its parameters. The qualitative results show that for complex and large-motion scenes, our method generates sharper and more realistic edges and details.

MetaSSI: A Framework for Personal Data Protection, Enhanced Cybersecurity and Privacy in Metaverse Virtual Reality Platforms

The Metaverse brings together components of parallel processing computing platforms, the digital development of physical systems, cutting-edge machine learning, and virtual identity to uncover a fully digitalized environment with equal properties to the real world. It possesses more rigorous requirements for connection, including safe access and data privacy, which are necessary with the advent of Metaverse technology. Traditional, centralized, and network-centered solutions fail to provide a resilient identity management solution. There are multifaceted security and privacy issues that hinder the secure adoption of this game-changing technology in contemporary cyberspace. Moreover, there is a need to dedicate efforts towards a secure-by-design Metaverse that protects the confidentiality, integrity, and privacy of the personally identifiable information (PII) of users. In this research paper, we propose a logical substitute for established centralized identity management systems in compliance with the complexity of the Metaverse. This research proposes a sustainable Self-Sovereign Identity (SSI), a fully decentralized identity management system to mitigate PII leaks and corresponding cyber threats on all multiverse platforms. The principle of the proposed framework ensures that the users are the only custodians and proprietors of their own identities. In addition, this article provides a comprehensive approach to the implementation of the SSI principles to increase interoperability and trustworthiness in the Metaverse. Finally, the proposed framework is validated using mathematical modeling and proved to be stringent and resilient against modern-day cyber attacks targeting Metaverse platforms.

Engineered 3D Vortex Array with Customized Energy and Topological Charges for Multi‐View Display

AbstractArrays of multiple vortex beams enhance parallel processing capabilities from particle manipulation to information communication. However, the spatial position, topological charge, and energy parameters of the vortex beams within the array have yet to be precisely controlled, posing significant challenges to the realization of multi‐view 3D Orbital Angular Momentum (OAM) display using vortex arrays as information carriers. To address this issue, a method for generating vortex arrays based on a phase‐only hologram, customizing the array by using the energy and OAM spectrum of each vortex beam as the loss function is developed. Experimental results indicate that a 2D array generates 100 vortex beams in the spatial frequency domain, while a 3D array in the Fresnel zone produces 252 vortex beams across 7 planes, each with 36 unprecedentedly controllable energy and topological charge vortex beams. Subsequently, images of 4 views using the 3D vortex arrays and decoded through coordinate transformation to achieve a multi‐view 3D OAM display are encoded. The results demonstrate imaging quality with Mean Peak Signal‐to‐Noise Ratio (MPSNR) of 12.7, 13.0, 13.4, and 12.2 dB in 4 views, respectively, offering promising opportunities for applications in 3D optical manipulation, high‐capacity communication, and 3D OAM holography.

A content analysis of EPPM’s threat and efficacy information in environmental news: The impact of a community of practice and topic

The extended parallel process model summarizes the positive impact of threat and efficacy messages on behavioral intentions. In news contexts, research to date shows national journalists emphasize threat information and neglect efficacious information. Findings show U.S. university student journalists emphasized efficacy rather than threats countering past content analysis research. We also found environmental and sustainability communities of practice did not predict threat and efficacy information, but topics did.

Attack on optical cryptosystems by skip connection networks

Optical encryption methods, due to their efficient operation speed and parallel processing capabilities, hold significant importance in securing multidimensional and large-volume data. Enhancing the security of optical cryptosystems from the perspective of cryptanalysis holds significant importance currently. Presently, attack methods against optical encryption are complex, and the effectiveness of these attacks is insufficient. Security analysis solutions face limitations in both breadth and depth. Therefore, this paper proposes an attack on optical cryptosystems based on a skip connection network, demonstrating the susceptibility of optical cryptosystems to attacks based on neural network algorithms. The network model is trained on plaintext-ciphertext pairs, fitting equivalent keys without various additional conditions. It approximates plaintext information in high-dimensional space, directly obtaining corresponding plaintext through ciphertext information, expanding the applicability and enhancing the effectiveness of the attack scheme. Finally, the feasibility and effectiveness of the attack scheme were verified through computer simulations. The experiments indicate that the method proposed in this paper has low computational complexity, wide applicability, produces high-quality decrypted images, and high decipherment accuracy. This provides a universal approach for analyzing the security of various optical cryptosystems from the perspective of chosen plaintext attacks.

The temporal dynamics of task processing and choice in a novel multitasking paradigm.

This study investigated the temporal dynamics of task performance and voluntary task choice within a multitasking paradigm in which the task-related processing outcomes themselves determined the to-be-performed task. In the novel forced-no-go trials, the stimulus for one task required an overt response, but the stimulus for the other task was associated with a no-go response. Task performance results showed that participants often processed the no-go task's stimulus before switching to the go-task. Dual-task interference effects and switch costs indicated various forms of multitasking interference, with their underlying causes appearing to overlap, as engagement in parallel processing seemed to be limited by switch-related reconfiguration processes. Intermixing free-choice trials, where both stimuli were associated with overt responses, revealed costs associated with switching between processing modes, providing new evidence that the distinctions between free and forced task goals stem from differences in their internal representations rather than alterations in processing due to different presentations in the environment. Task choice results align with this perspective, demonstrating a preference for repeating a free- over a forced-choice task. Furthermore, these free-choice results illuminate the interplay of cognitive (task-repetition bias) and environmental constraints (first-task bias) in shaping task choices: It appears that task-specific information increases goal activations for both task goals concurrently, with participants favoring central processing of the second- over the first-presented task to optimize their behavior when shorter central processing is required (task repetition). Overall, this study offers new insights into the dynamics of task processing and choice in environments requiring the balance of multiple tasks.

Minimum Congestion and Wirelength of Embedding the nth Cartesian Product of K4 into Various Kinds of Grid Networks

Embedding an interconnection network into another network is one of the main problems in parallel processing and computing systems. Interconnection networks in multiprocessing systems facilitate effective communication among various system components. Obtaining the minimum cutwidth, congestion, and wirelength in graph embedding problems is of great significance for network design and architecture, where the minimum is taken over all embedding of guest graphs into host graphs, and addressing these issues can reduce time and cost in embedded design. This work aims to accurately calculate the minimum congestion and wirelength for the [Formula: see text] (the [Formula: see text]th Cartesian product of [Formula: see text]) layout into [Formula: see text]-dimensional, [Formula: see text]-dimensional, and [Formula: see text]-dimensional grids by the optimal solution of edge isoperimetric problem on [Formula: see text].

Short-term power load forecasting for integrated energy system based on a residual and attentive LSTM-TCN hybrid network

In the context of Integrated Energy System (IES), accurate short-term power demand forecasting is crucial for ensuring system reliability, optimizing operational efficiency through resource allocation, and supporting effective real-time decision-making in energy management. However, achieving high forecasting accuracy faces significant challenges due to the inherent complexity and stochastic nature of IES’s short-term load profiles, resulting from diverse consumption patterns among end-users and the intricate coupling within the network of interconnected energy sources. To address this issue, a dedicated Short-Term Power Load Forecasting (STPLF) framework for IES is proposed, which relies on a newly developed hybrid deep learning architecture. The framework seamlessly combines Long Short-Term Memory (LSTM) with Temporal Convolutional Network (TCN), enhanced by an attention mechanism module. By merging these methodologies, the network leverages the parallel processing prowess of TCN alongside LSTM’s ability to retain long-range temporal information, thus enabling it to dynamically concentrate on relevant sections of time series data. This synergy leads to improved prediction accuracy and broader applicability. Furthermore, the integration of residual connections within the network structure serves to deepen its learning capabilities and enhance overall performance. Ultimately, results from a real case study of a user-level IES demonstrate that the Mean Absolute Percentage Error (MAPE) of the proposed framework on the test set is 2.35%. This error rate is lower than the averages of traditional methods (3.43%) and uncombined single submodules (2.80%).

Parallel processing of quickly and slowly mobilized reserve vesicles in hippocampal synapses.

Vesicles within presynaptic terminals are thought to be segregated into a variety of readily releasable and reserve pools. The nature of the pools and trafficking between them is not well understood, but pools that are slow to mobilize when synapses are active are often assumed to feed pools that are mobilized more quickly, in a series. However, electrophysiological studies of synaptic transmission have suggested instead a parallel organization where vesicles within slowly and quickly mobilized reserve pools would separately feed independent reluctant- and fast-releasing subdivisions of the readily releasable pool. Here, we use FM-dyes to confirm the existence of multiple reserve pools at hippocampal synapses and a parallel organization that prevents intermixing between the pools, even when stimulation is intense enough to drive exocytosis at the maximum rate. The experiments additionally demonstrate extensive heterogeneity among synapses in the relative sizes of the slowly and quickly mobilized reserve pools, which suggests equivalent heterogeneity in the numbers of reluctant and fast-releasing readily releasable vesicles that may be relevant for understanding information processing and storage.

Parallel processing of quickly and slowly mobilized reserve vesicles in hippocampal synapses

Vesicles within presynaptic terminals are thought to be segregated into a variety of readily releasable and reserve pools. The nature of the pools and trafficking between them is not well understood, but pools that are slow to mobilize when synapses are active are often assumed to feed pools that are mobilized more quickly, in a series. However, electrophysiological studies of synaptic transmission have suggested instead a parallel organization where vesicles within slowly and quickly mobilized reserve pools would separately feed independent reluctant- and fast-releasing subdivisions of the readily releasable pool. Here, we use FM-dyes to confirm the existence of multiple reserve pools at hippocampal synapses and a parallel organization that prevents intermixing between the pools, even when stimulation is intense enough to drive exocytosis at the maximum rate. The experiments additionally demonstrate extensive heterogeneity among synapses in the relative sizes of the slowly and quickly mobilized reserve pools, which suggests equivalent heterogeneity in the numbers of reluctant and fast-releasing readily releasable vesicles that may be relevant for understanding information processing and storage.

Network-based visualisation of frequent sequences.

Frequent sequence pattern mining is an excellent tool to discover patterns in event chains. In complex systems, events from parallel processes are present, often without proper labelling. To identify the groups of events related to the subprocess, frequent sequential pattern mining can be applied. Since most algorithms provide too many frequent sequences that make it difficult to interpret the results, it is necessary to post-process the resulting frequent patterns. The available visualisation techniques do not allow easy access to multiple properties that support a faster and better understanding of the event scenarios. To answer this issue, our work proposes an intuitive and interactive solution to support this task, introducing three novel network-based sequence visualisation methods that can reduce the time of information processing from a cognitive perspective. The proposed visualisation methods offer a more information rich and easily understandable interpretation of sequential pattern mining results compared to the usual text-like outcome of pattern mining algorithms. The first uses the confidence values of the transitions to create a weighted network, while the second enriches the adjacency matrix based on the confidence values with similarities of the transitive nodes. The enriched matrix enables a similarity-based Multidimensional Scaling (MDS) projection of the sequences. The third method uses similarity measurement based on the overlap of the occurrences of the supporting events of the sequences. The applicability of the method is presented in an industrial alarm management problem and in the analysis of clickstreams of a website. The method was fully implemented in Python environment. The results show that the proposed methods are highly applicable for the interactive processing of frequent sequences, supporting the exploration of the inner mechanisms of complex systems.

The developmental trajectories of teacher autonomy support and adolescent mental well-being and academic stress

AbstractThis study investigated the developmental impact of teacher autonomy support on changes in students’ mental well-being and academic stress throughout upper secondary school. The sample consisted of 1453 Norwegian students (baseline Mage = 17.00; 60.6% girls; 80.9% Norwegian-born). The unconditional latent growth curve model results showed that perceived teacher autonomy support and mental well-being decreased during the three-year-long education. Academic stress, on the other hand, increased during this period. Findings from the parallel process latent growth curve model indicated that the initial status and change in teacher autonomy support were positively and negatively related to the initial levels and trajectories of mental well-being and academic stress, respectively. Girls experienced a higher level of academic stress and lower mental well-being and teacher autonomy support at the beginning of upper secondary school. Students with a higher socioeconomic status reported higher initial mental well-being and teacher autonomy support than others but also a more rapid decline in teacher autonomy support throughout upper secondary school. This study provides new insights into academic, psychological, and affective processes and their interrelationships during upper secondary school.

MtDNA-Server 2: advancing mitochondrial DNA analysis through highly parallelized data processing and interactive analytics.

Over the past decade, mtDNA-Server established itself as one of the most widely used variant calling web-services for human mitochondrial genomes. The service accepts sequencing data in BAM format and returns an annotated variant analysis report for both homoplasmic and heteroplasmic variants. In this work we present mtDNA-Server 2, which includes several new features highly requested by the community. Most importantly, it includes (a) the integration of a novel variant calling mode that accurately call insertions, deletions and single nucleotide variants at once, (b) the integration of additional quality control and input validation modules, (c) a method to estimate the required coverage to minimize false positives and (d) an interactive analytics dashboard. Furthermore, we migrated the complete analysis workflow to the Nextflow workflow manager for improved parallelization, reproducibility and local execution. Recognizing the importance of insertions and deletions as well as offering novel quality control, validation and reporting features, mtDNA-Server 2 provides researchers and clinicians a new state-of-the-art analysis platform for interpreting mitochondrial genomes. mtDNA-Server 2 is available via mitoverse, our analysis platform that offers a centralized place for mtDNA analysis in the cloud. The web-service, source code and its documentation are freely accessible at https://mitoverse.i-med.ac.at.

In-line imaging and recognition of flip chip fabrication defects by real-time photoacoustic remote sensing system

Microscopic defects in flip chips, originating from manufacturing, significantly affect performance and longevity. Post-fabrication sampling methods ensure product functionality but lack in-line defect monitoring to enhance chip yield and lifespan in real-time. This study introduces a photoacoustic remote sensing (PARS) system for in-line imaging and defect recognition during flip-chip fabrication. We first propose a real-time PARS imaging method based on continuous acquisition combined with parallel processing image reconstruction to achieve real-time imaging during the scanning of flip-chip samples, reducing reconstruction time from an average of approximately 1134 ms to 38 ms. Subsequently, we propose improved YOLOv7 with space-to-depth block (IYOLOv7-SPD), an enhanced deep learning defect recognition method, for accurate in-line recognition and localization of microscopic defects during the PARS real-time imaging process. The experimental results validate the viability of the proposed system for enhancing the lifespan and yield of flip-chip products in chip manufacturing facilities.

Highly Fault-Tolerant Systolic-Array-Based Matrix Multiplication

Matrix multiplication plays a crucial role in various engineering and scientific applications. Cannon’s algorithm, executed within two-dimensional systolic arrays, significantly enhances computational efficiency through parallel processing. However, as the matrix size increases, reliability issues become more prominent. Although the previous work has proposed a fault-tolerant mechanism, it is only suitable for scenarios with a limited number of faulty processing elements (PEs). This paper introduces a pair-matching mechanism, assigning a fault-free PE as a proxy for each faulty PE to execute its tasks. Our fault-tolerant mechanism comprises two stages: in the first stage, each fault-free PE completes its designated computations; in the second stage, computations intended for each faulty PE are executed by its assigned fault-free PE proxy. The experimental results demonstrate that compared to the previous work, our approach not only significantly improves the fault tolerance of systolic arrays (applicable to scenarios with a higher number of faulty PEs) but also reduces circuit areas. Therefore, the proposed approach proves effective in practical applications.

Accelerating spliced alignment of long RNA sequencing reads using parallel maximal exact match retrieval

The genomics landscape has undergone a revolutionary transformation with the emergence of third-generation sequencing technologies. Fueled by the exponential surge in sequencing data, there is an urgent demand for accurate and rapid algorithms to effectively handle this burgeoning influx. Under such circumstances, we developed a parallelized, yet accuracy-lossless algorithm for maximal exact match (MEM) retrieval to strategically address the computational bottleneck of uLTRA, a leading spliced alignment algorithm known for its precision in handling long RNA sequencing (RNA-seq) reads. The design of the algorithm incorporates a multi-threaded strategy, enabling the concurrent processing of multiple reads simultaneously. Additionally, we implemented the serialization of index required for MEM retrieval to facilitate its reuse, resulting in accelerated startup for practical tasks. Extensive experiments demonstrate that our parallel algorithm achieves significant improvements in runtime, speedup, throughput, and memory usage. When applied to the largest human dataset, the algorithm achieves an impressive speedup of 10.78 × , significantly improving throughput on a large scale. Moreover, the integration of the parallel MEM retrieval algorithm into the uLTRA pipeline introduces a dual-layered parallel capability, consistently yielding a speedup of 4.99 × compared to the multi-process and single-threaded execution of uLTRA. The thorough analysis of experimental results underscores the adept utilization of parallel processing capabilities and its advantageous performance in handling large datasets. This study provides a showcase of parallelized strategies for MEM retrieval within the context of spliced alignment algorithm, effectively facilitating the process of RNA-seq data analysis. The code is available at https://github.com/RongxingWong/AcceleratingSplicedAlignment.

Cross-connection of multiplexed cylindrical vector beams using off-axis spin-decoupled metasurfaces.

Cylindrical vector beam (CVB) multiplexing communication demands effective mode cross-connection techniques to establish communication networks. While methods like polarized grating and coordinate transformation have been developed for (de)multiplexing CVB modes, challenges persist in the cross-connection of these multiplexed mode channels, including multi-mode conversion and inhomogeneous polarization control. Herein, we present an independent off-axis spin-orbit interaction strategy utilizing spin-decoupled metasurfaces. Cross-connection is achieved by encoding conjugated Dammann optical vortex grating phases onto the two orthogonal circularly polarized components of CVBs. Experimental results demonstrate the successful interconversion of four CVB modes (CVB+1 and CVB-2, CVB+2 and CVB-4) using a Si-based metasurface with a polarization conversion efficiency exceeding 85%. This facilitates the cross-connection of 200 Gbit/s quadrature phase-shift keying signals with bit-error-rates below 10-6. Offering advantages such as ultra-compact device size, flexible control of CVB modes, and multi-mode parallel processing, this approach shows promise in advancing the networking capabilities of CVB mode multiplexing communication networks.

Study on Influencing Factors of Two-Body Parallel Separation

In the parallel separation process of two bodies, the initial velocity state and the surrounding flow field environment jointly determine the motion state of the two bodies, which is a direct determinant of the separation process safety. To study the two-body parallel separation process and the influencing factors, this paper adopts the dynamic mesh technique and finite volume method to solve the Navier-Stokes equations and study the influence of the initial separation clearance and velocity state on the separation process. The results show that: with the increase of the initial separation clearance, the separation process safety of two bodies under the action of complex flow field may decrease; the effect is poor when the two bodies are separated at rest, and a suitable initial velocity state is beneficial to improve the separation safety to achieve the purpose of safe separation, and the two bodies show different separation processes under different initial velocity states.