We develop a distributed-memory parallel algorithm for performing batch updates on streaming graphs, where vertices and edges are continuously added or removed. Our algorithm leverages distributed sparse matrices as t...
详细信息
As the parallelcomputing education movement attempts to increase the coverage of parallel and distributedcomputing (PDC) material in worldwide CS curricula, a major challenge is propagation: getting others to adopt ...
详细信息
ISBN:
(纸本)9798350383782;9798350383799
As the parallelcomputing education movement attempts to increase the coverage of parallel and distributedcomputing (PDC) material in worldwide CS curricula, a major challenge is propagation: getting others to adopt PDC-related curricular materials. This paper reports on a series of faculty development workshops for the ToUCH project, held with the goal of propagating modules on heterogeneous parallelcomputing. Due to the COVID-19 pandemic, these workshops were held in a new virtual format that split the meeting over multiple days and included explicit expectations for followup work to increase adoption. Subsequent evaluation show that the participants appreciated the format and that many of them adopted one or more of the modules.
With the continuous advancement of large-scale models and expanding volumes of data, a single acceleration hardware is no longer sufficient to meet the training demands. Simply stacking multiple acceleration hardware ...
详细信息
The application of GPU to accelerate large-scale smoke simulation is a hot research topic in computational fluid dynamics. However, the current smoke parallelcomputing methods for different scale smoke flow field, th...
详细信息
The proceedings contain 68 papers. The topics discussed include: study on the relation between image recognition and art counsel using deep learning;changes in marketing brought by AI;the impact of capital structure o...
ISBN:
(纸本)9780738125510
The proceedings contain 68 papers. The topics discussed include: study on the relation between image recognition and art counsel using deep learning;changes in marketing brought by AI;the impact of capital structure on the profitability efficiency of ICT firms;a study on the change in service quality in the era of the 4th industrial revolution compared to the existing service quality evaluation;a deep learning approach for human face sentiment classification;development of craft copyright industry using blockchain technology;the design of industrial security tasks and capabilities required in industrial site;research and implementation of image recognition of tea based on deep learning;and the effects of local culture experience on revisit intention.
Containers are widely deployed in clouds. There are two common container architectures: operating system-level (OS-level) container and virtual machine-level (VM-level) container. Typical examples are runc and Kata. I...
详细信息
ISBN:
(纸本)9798350386066;9798350386059
Containers are widely deployed in clouds. There are two common container architectures: operating system-level (OS-level) container and virtual machine-level (VM-level) container. Typical examples are runc and Kata. It is well known that VM-level containers provide better isolation than OS-level containers, but at a higher overhead. Although there are quantitative analyses of the performance gap between these two container architectures, they rarely discuss the performance gap under the constrained resources provisioned to containers. Since the high-density deployment of containers is demanding in the cloud, each container is provisioned with limited resources specified by the cgroup mechanism. In this paper, we provide an in-depth analysis of the storage and network (two key aspects) performance differences between runc and Kata under varying resource constraints. We identify configuration implications that are crucial to performance and find that some of them are not exposed by the Kata interfaces. Based on that, we propose a profiling tool to automatically offer configuration suggestions for optimizing container performance. Our evaluation shows that the auto-generated configuration can improve the performance of MySQL by up to 107% in the TPCC benchmark compared with the default Kata setup.
An innovative architecture called execute-order-validate (EOV) has been proposed by Hyperledger Fabric that enables concurrent processing of transactions. However, the architecture suffers from issues such as excessiv...
详细信息
ISBN:
(纸本)9798350386066;9798350386059
An innovative architecture called execute-order-validate (EOV) has been proposed by Hyperledger Fabric that enables concurrent processing of transactions. However, the architecture suffers from issues such as excessive invalid transactions and serialization limitations in scenarios with high transaction conflicts, which restrict its applicability in real-time and high-performance settings. To address the aforementioned limitations, we propose ParFabric to enhance the EOV architecture. Firstly, we analyze four essential characteristics required for the transaction reordering algorithm within this architecture. We propose a heuristic dynamic reordering algorithm to reduce the number of invalid transactions. This is achieved through real-time identification and early abortion of transactions based on weighted pre-ordering and the construction of a transaction conflict graph. Secondly, leveraging the transaction conflict graph, we introduce a novel optimal block packing strategy based on transaction dependencies. This strategy replaces the total transaction order with partial order, enabling parallel validation and commit at the block level, thereby leading to increased system throughput while reducing transaction latency. Experimental results indicate that, ParFabric demonstrates excellent performance in terms of vertical scaling of peers. Additionally, at the same infrastructure cost, ParFabric provides 2.2x and 1.6x higher throughput than FabricPlusPlus and FabricSharp in high-conflict scenarios.
We introduce a distributed memory parallel algorithm for force-directed node embedding that places vertices of a graph into a low-dimensional vector space based on the interplay of attraction among neighboring vertice...
详细信息
ISBN:
(纸本)9798350364613;9798350364606
We introduce a distributed memory parallel algorithm for force-directed node embedding that places vertices of a graph into a low-dimensional vector space based on the interplay of attraction among neighboring vertices and repulsion among distant vertices. We develop our algorithms using two sparse matrix operations, SDDMM and SpMM. We propose a configurable pull -push -based communication strategy that optimizes memory usage and data transfers based on computing resources and asynchronous MPI communication to overlap communication and computation. Our algorithm scales up to 256 nodes on distributed supercomputers by surpassing the performance of state-of-the-art algorithms
Subgraph isomorphism enumerates all embeddings in a data graph that are identical to a query graph. It is a well-known NP-hard problem widely used in various domains, such as bioinformatics, chem-informatics, and soci...
详细信息
ISBN:
(纸本)9798400717932
Subgraph isomorphism enumerates all embeddings in a data graph that are identical to a query graph. It is a well-known NP-hard problem widely used in various domains, such as bioinformatics, chem-informatics, and social network analysis. Recent works are focused on using GPUs for subgraph isomorphism. Due to the massive scale of intermediate results, current GPU implementations face challenges in scaling across multiple nodes due to high communication costs. The computational power of CPUs is not fully utilized in this process. We present a distributed framework for subgraph isomorphism that leverages CPU and GPU heterogeneous computing. It eliminates the intermediate results on GPU and significantly reduces communication overhead during the load-balancing process. The experiments indicate that our algorithm can be extended to multiple nodes with an almost linear efficiency improvement. Furthermore, our method also significantly outperforms other existing works on GPUs. It can reach an improvement of up to 21x compared to the state-of-the-art implementation CuTS in the distributed environment.
作者：
Chen, JunchaoThou, Jian-taoHao, XinyuInner Mongolia Univ
Natl & Local Joint Engn Res Ctr Intelligent Infor Inner Mongolia Engn Lab Cloud Comp & Serv Softwar Inner Mongolia Key Lab Social Comp & Data ProcCo Hohhot Peoples R China
The accuracy of data analysis depends on data quality, and addressing data consistency issues is a key challenge to improve it. Constant Conditional Functional Dependency (CCFD) is an effective approach that ensures d...
详细信息
ISBN:
(纸本)9798350376975;9798350376968
The accuracy of data analysis depends on data quality, and addressing data consistency issues is a key challenge to improve it. Constant Conditional Functional Dependency (CCFD) is an effective approach that ensures data consistency by enforcing bindings of semantically related values, thus providing quality assurance for data analysis and decision-making processes. However, with the growth of data scale, especially the increasing number of data tuples and attributes, existing single-machine CCFD discovery algorithms face issues of low computational efficiency and lengthy computation time. This paper proposes a time-efficient distributed CCFD discovery algorithm (DCCFD). Through the optimization of data preprocessing and index mapping, the data organization structure is enhanced, laying the foundation for the discovery of CCFDs under distributed conditions. The Spark parallelcomputing framework is used to partition the dataset, which accelerates the parallel loading and processing of data. Additionally, this algorithm ensures accuracy and processing speed when discovering dependencies by efficiently generating frequent itemsets and verifying CCFDs in parallel. Experiments on multiple real datasets show that, especially with the complex Airline dataset, the DCCFD algorithm not only accurately discovers CCFDs, but also reduces the average running time by 75.64% compared with the preCFDMiner algorithm.
暂无评论