Over the last years, innovative parallel and distributed SAT solving techniques were presented that could impressively exploit the power of modern hardware and cloud systems. Two approaches were particularly successfu...
详细信息
ISBN:
(纸本)9783031308222;9783031308239
Over the last years, innovative parallel and distributed SAT solving techniques were presented that could impressively exploit the power of modern hardware and cloud systems. Two approaches were particularly successful: (1) search-space splitting in a Divide-and-Conquer (D&C) manner and (2) portfolio-based solving. The latter executes different solvers or configurations of solvers in parallel. For quantified Boolean formulas (QBFs), the extension of propositional logic with quantifiers, there is surprisingly little recent work in this direction compared to SAT. In this paper, we present ParaQooba, a novel framework for parallel and distributed QBF solving which combines D&C parallelization and distribution with portfolio-based solving. Our framework is designed in such a way that it can be easily extended and arbitrary sequential QBF solvers can be integrated out of the box, without any programming effort. We show how ParaQooba orchestrates the collaboration of different solvers for joint problem solving by performing an extensive evaluation on benchmarks from QBFEval'22, the most recent QBF competition.
The proceedings contain 15 papers. The special focus in this conference is on parallel Computing Technologies. The topics include: parallel Generation and Analysis of Optimal Chordal Ring Networks Using Pyth...
ISBN:
(纸本)9783031416729
The proceedings contain 15 papers. The special focus in this conference is on parallel Computing Technologies. The topics include: parallel Generation and Analysis of Optimal Chordal Ring Networks Using Python Tools on Kunpeng Processors;Combinatorial Aspect of Code Restructuring for Virtual Memory Computer systems Under WS Swapping Strategy;probabilistic Resources Allocation with Group Dependencies in distributed Computing;multicriteria Task Distribution Problem for Resource-Saving Data Processing;scheduling of Workflows with Task Resource Requirements in Cluster Environments;Verifying the Correctness of HPC Performance Monitoring Data;automatic parallelization of Iterative Loops Nests on distributed Memory Computing systems;didal: distributed Data Library for Development of parallel Fragmented Programs;Trace Balancing Technique for Trace Playback in LuNA System;Case Study for Running Memory-Bound Kernels on RISC-V CPUs;pair of Genes: Technical Validation of distributed Causal Role Attribution to Gene Network Expansion;HiTViSc: High-Throughput Virtual Screening as a Service;expanding the Cellular Automata Topologies Library for parallel Implementation of Synchronous Cellular Automata.
The proceedings contain 17 papers. The special focus in this conference is on Asynchronous Many-Task systems and Applications. The topics include: Evaluating PaRSEC Through Matrix Computations in Scientific Appli...
ISBN:
(纸本)9783031617621
The proceedings contain 17 papers. The special focus in this conference is on Asynchronous Many-Task systems and Applications. The topics include: Evaluating PaRSEC Through Matrix Computations in Scientific Applications;distributed Asynchronous Contact Mechanics with DARMA/vt;IRIS Reimagined: Advancements in Intelligent Runtime System for Task-Based Programming;MatRIS: Addressing the Challenges for Portability and Heterogeneity Using Tasking for Matrix Decomposition (Cholesky);parSweet: A Suite of Codes for Benchmarking and Testing Mutex-Based parallelsystems;Rethinking Programming Paradigms in the QC-HPC Context;dynamic Tuning of Core Counts to Maximize Performance in Object-Based Runtime systems;enhancing Sparse Direct Solver Scalability Through Runtime System Automatic Data Partition;Experiences Porting Shared and distributed Applications to Asynchronous Tasks: A Multidimensional FFT Case-Study;an Abstraction for distributed Stencil Computations Using Charm++;DLA-Future: A Task-Based Linear Algebra Library Which Provides a GPU-Enabled distributed Eigensolver;ALPI: Enhancing Portability and Interoperability of Task-Aware Libraries;Evolving APGAS Programs: Automatic and Transparent Resource Adjustments at Runtime;optimizing parallel System Efficiency: Dynamic Task Graph Adaptation with Recursive Tasks;HPX with Spack and Singularity Containers: Evaluating Overheads for HPX/Kokkos Using an Astrophysics Application.
High-performance computing (HPC) has become an essential tool for improving the efficiency and scalability of transaction processing systems, especially as data volumes continue to grow in fields like finance, e-comme...
详细信息
In this work, we propose MDLoader, a hybrid in-memory data loader for distributed deep neural networks. MDLoader introduces a model-driven performance estimator to automatically switch between one-sided and collective...
详细信息
ISBN:
(纸本)9798350364613;9798350364606
In this work, we propose MDLoader, a hybrid in-memory data loader for distributed deep neural networks. MDLoader introduces a model-driven performance estimator to automatically switch between one-sided and collective communication at runtime.
Remote Memory Access (RMA) enables direct access to remote memory to achieve high performance for HPC applications. However, most modern parallel programming models lack schemes for the remote process to detect the co...
详细信息
ISBN:
(数字)9798350352917
ISBN:
(纸本)9798350352924;9798350352917
Remote Memory Access (RMA) enables direct access to remote memory to achieve high performance for HPC applications. However, most modern parallel programming models lack schemes for the remote process to detect the completion of RMA operations. Many previous works have proposed programming models and extensions to notify the communication peer, but they did not solve the multi-NIC aggregation, portability, hardware-software co-design, and usability problems. In this work, we proposed a Unified Notifiable RMA (UNR) library for HPC to address these challenges. In addition, we demonstrate the best practice of utilizing UNR within a real-world scientific application, PowerLLEL. We deployed UNR across four HPC systems, each with a different interconnect. The results show that PowerLLEL powered by UNR achieves up to a 36% acceleration on 1728 nodes of the Tianhe-Xingyi supercomputing system.
The evolution of the distributed computing paradigm had as a result new computing models such as grid and cloud computing. Furthermore, in these environments it is common to run complex parallel applications thus maki...
详细信息
The Open structure for allotted and Cooperative Media Algorithms (OADCMA) is an open-deliver framework imparting a plug-in platform that lets customers, without problem, develop distributed and cooperative media algor...
详细信息
Log-based anomaly detection has been extensively studied to help detect complex runtime anomalies in production systems. However, existing techniques exhibit several common issues. First, they rely heavily on expert-l...
详细信息
ISBN:
(纸本)9798400701559
Log-based anomaly detection has been extensively studied to help detect complex runtime anomalies in production systems. However, existing techniques exhibit several common issues. First, they rely heavily on expert-labeled logs to discern anomalous behavior patterns. But labelling enough log data manually to effectively train deep neural networks may take too long. Second, they rely on numeric model prediction based on numeric vector input which causes model decisions to be largely non-interpretable by humans which further rules out targeted error correction. In recent years, we have witnessed groundbreaking advancements in large language models (LLMs) such as ChatGPT. These models have proven their ability to retain context and formulate insightful responses over entire conversations. They also present the ability to conduct few-shot and in-context learning with reasoning ability. In light of these abilities, it is only natural to explore their applicability in understanding log content and conducting anomaly classification among parallel file system logs.
The rapid evolution of IIoT (Industrial Internet of Things) in computing has brought about numerous security concerns, among which is the looming threat of False Data Injection (FDI) attacks. To address these attacks,...
详细信息
ISBN:
(纸本)9798350391558;9798350379990
The rapid evolution of IIoT (Industrial Internet of Things) in computing has brought about numerous security concerns, among which is the looming threat of False Data Injection (FDI) attacks. To address these attacks, a study introduces a novel approach called MLBT-FDIA-IIoT (Fault Data Injection Attack Detection in IIoT using parallel Physics-Informed Neural Networks with Giza Pyramid Construction Optimization algorithm). This method makes use of real-time sensor data for attack detection. The data is preprocessed using distributed Set-Membership Fusion Filtering (DSMFF) to remove noise. Then, it is fed into a neural network for classification. Specifically, parallel Physics-Informed Neural Networks (PPINN) are used to distinguish between normal operations and False Data Injection Attacks (FDIAs). However, PPINN lacks optimization methods for accurate detection. To address this, the study proposes the Giza Pyramid Construction Optimization algorithm (GPCOA). This algorithm optimizes the PPINN classifier to detect attacks with more precision. The proposed MLBT-FDIA-IIoT method is implemented using MATLAB and evaluates various metrics such as accuracy, recall, and precision. The results demonstrate significant improvements compared to existing techniques such as MLT-FDI-IIoT, FDIA-FDAS-IIoT, and DCDD-IIoT-FDIA.
暂无评论