检索结果-内蒙古大学图书馆

35th ieee International parallel and Distributed Processing symposium (IPDPS)

作者： Artiles, Oswaldo Saeed, Fahad Florida Int Univ Sch Comp & Informat Sci Miami FL 33199 USA

ISBN: (纸本)9781665435772

Graphs that are used for modeling of human brain, omics data, or social networks are huge, and manual inspection of these graph is impossible. A popular, and fundamental, method used for making sense of these large graphs is the well-known Breadth-First Search (BFS) algorithm. However, BFS suffers from large computational cost especially for big graphs of interest. More recently, the use of graphics processing units (GPU) has been promising, but challenging because of limited global memory of GPU's, and irregular structures of real-world graphs. In this paper, we present a GPU based linear-algebraic formulation and implementation of BFS, called TurboBFS, that exhibits excellent scalability on unweighted, undirected or directed sparse graphs of arbitrary structure. We demonstrate that our algorithms obtain up to 40 GTEPs, and are on average 15.7x, 5.8x, and 1.8x faster than the other state-of-the-art algorithms implemented on the SuiteSparse:GraphBLAS, GraphBLAST, and gunrock libraries respectively. The codes to implement the algorithms proposed in this paper are available at https://***/pcdslab.

关键词： GPU CUDA graph parallel algorithms BFS linear algebra

来源：评论

学校读者我要写书评

暂无评论

Scaling Up Study Area Size in Flood Susceptibility Mapping

Scaling Up Study Area Size in Flood Susceptibility Mapping

引用

ieee International symposium on Geoscience and Remote Sensing (IGARSS)

作者： Aswathi Mundayatt Jaya Sreevalsan-Nair Graphics-Visualization-Computing Lab International Institute of Information Technology Bangalore Bangalore India

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Flood susceptibility mapping (FSM) is crucial for preparedness and risk mitigation of floods, and machine learning (ML)-based FSM methods have been well-studied. However, due to computational constraints, geographical variations, and differential data availability, FSM is often confined to smaller regions, much less than 1,000 km 2 . To address the computational constraints of FSM generation in data-rich regions, we propose a data-parallel approach using PySpark with two levels of spatial partitioning, where they address the computational load and geographical variations, respectively. In our case study of the state of Kerala, India, we propose grid lattice partitioning and the Ecologically Sensitive Zone (ESZ) map for the two levels of spatial partitioning, respectively. The latter is used to train random forest classifier models. We investigate the influence of contiguity in training grids on FSM outcomes within different ESZs. Our quantitative and qualitative comparative analysis of observations demonstrate the importance of contiguous training grids, especially in capturing finer details in FSM. Our implementation demonstrates the efficiency of our approach in the study area of Kerala spanning 38,863 km 2 .

关键词： Training Accuracy Computational modeling Biological system modeling Scalability Lattices Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

High Throughput Matrix Transposition on HBM-Enabled FPGAs

High Throughput Matrix Transposition on HBM-Enabled FPGAs

引用

Annual ieee symposium on Field-Programmable Custom Computing Machines (FCCM)

作者： Yang Yang Rajgopal Kannan Viktor K. Prasanna Department of Electrical and Computer Engineering University of Southern California DEVCOM ARL Army Research Office Los Angeles CA

ISBN: (数字)9798331502812

ISBN: (纸本)9798331502829

Matrix transposition is a classic operation in machine learning and scientific applications. HBM-enabled FPGAs, with their high-bandwidth capabilities, are increasingly deployed in the data centers. However, achieving high bandwidth utilization on HBM is challenging due to the large strided access patterns in matrix transposition, which significantly degrade bandwidth utilization. Additionally, saturating HBM bandwidth requires a large number of parallel accesses, further complicating the design. In this paper, we present a high throughput matrix transposition design for HBM-enabled FPGAs. Our design performs small strided accesses to HBM, ensuring optimized bandwidth utilization. We use on-chip SRAMs to reorganize data from HBM into the access pattern needed for matrix transposition. Inspired by Latin Squares, we propose a novel data layout for storing the matrix tiles in SRAM. This data layout is paired with a customized scheduling strategy to eliminate SRAM bank conflicts. We develop a fully pipelined architecture with multiple Processing Elements (PEs) to enable parallel HBM accesses. Our design is highly scalable, supporting various configurations of HBM channels and arbitrary matrix dimensions. We implement the proposed design on the AMD Alveo U280 FPGA. Experimental results show that our design achieves a matrix transposition throughput of up to 415 GB/s, more than 90% of the peak HBM bandwidth of the target FPGA platform. Our design outperforms state-of-the-art GPU implementations, delivering up to 1.44 × higher HBM memory bandwidth utilization.

关键词： Layout Memory management Random access memory graphics processing units Bandwidth Machine learning parallel processing Throughput System-on-chip Field programmable gate arrays

来源：评论

学校读者我要写书评

暂无评论

Interactive Selection on Calculated Attributes of large-Scale Particle data

Interactive Selection on Calculated Attributes of Large-Scal...

引用

21st Eurographics symposium on parallel graphics and visualization, EGPGV 2021

作者： Wollet, B. Reinhardt, S. Weiskopf, D. Eberhardt, B. University of Stuttgart Germany Hochschule der Medien Germany

ISBN: (纸本)9783038681380

We present a GPU-based technique for efficient selection in interactive visualizations of large particle datasets. In particular, we address multiple attributes attached to particles, such as pressure, density, or surface tension. Unfortunately, such intermediate attributes are often available only during the simulation run. They are either not accessible during visualization or have to be saved as additional information along with the usual simulation data. The latter increases the size of the dataset significantly, and the required variables may not be known in advance. Therefore, we choose to compute intermediate attributes on the fly. In this way, we are even able to obtain attributes that were not calculated by the simulation but may be relevant for data analysis or debugging. We present an interactive selection technique designed for such attributes. It leverages spatial regions of the selection to efficiently compute attributes only where needed. This lazy evaluation also works for intelligent and data-driven selection, extending the region to include neighboring particles. Our technique is evaluated by measurements of performance scalability and case studies for typical usage examples. © 2021 The Author(s).

关键词： visualization

来源：评论

学校读者我要写书评

暂无评论

A Novel Cloud-Native and Multi-Platform parallelized SBAS-INSAR Algorithm

A Novel Cloud-Native and Multi-Platform Parallelized SBAS-IN...

引用

ieee International symposium on Geoscience and Remote Sensing (IGARSS)

作者： Peichen Yu Chao Wang Yixian Tang Weikang Zhang Haihang You Shaoyang Guan Lichuan Zou Hong Zhang Key Laboratory of Digital Earth Science Aerospace Information Research Institute Chinese Academy of Sciences Beijing China International Research Center of Big Data for Sustainable Development Goals Beijing China University of Chinese Academy of Sciences Beijing China Institute of Computing Technology Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350360325

ISBN: (纸本)9798350360332

Facing massive Synthetic Aperture Radar (SAR) data, the challenge of achieving rapid and efficient data processing has garnered attention. Currently, most time-series InSAR processing solutions are designed to operate on a single computing platform, leading to drawbacks such as inflexible deployment and slow data transmission. Leveraging the open-source Kubernetes platform, we have employed cloud-native technology to deploy a cross-platform, multi-level parallelization algorithm across multiple nodes. The algorithm is designed based on modular concept, and its modules can successfully achieve cross-platform deployment by relying on both the Network File System (NFS) protocol and the Common Internet File System (CFIS) protocol. This overcomes the limitations of the previous data file storage system, which solely depended on the NFS protocol, leading to deployment on a single operating system. Deploying the algorithm on different operating systems, our results show that the speeds of Linux platform's algorithm parallel modules were improved 16% and 30%, respectively. The successful cross-platform operation of the algorithm enables the data processing workflow to assimilate the strengths of different operating platforms, enhancing data visualization capabilities and gaining support from diverse platform resources. This introduces a new approach for large-scale time-series InSAR processing.

关键词： Cloud computing Protocols File systems Operating systems Linux Geoscience and remote sensing data visualization

来源：评论

学校读者我要写书评

暂无评论

Efficient data-parallel Continual Learning with Asynchronous Distributed Rehearsal Buffers

Efficient Data-Parallel Continual Learning with Asynchronous...

引用

ieee/ACM International symposium on Cluster Computing and the Grid (CCGRID)

作者： Thomas Bouvier Bogdan Nicolae Hugo Chaugier Alexandru Costan Ian Foster Gabriel Antoniu Inria CNRS IRISA University of Rennes Argonne National Laboratory

ISBN: (数字)9798350395662

ISBN: (纸本)9798350395679

Deep learning has emerged as a powerful method for extracting valuable information from large volumes of data. However, when new training data arrives continuously (i.e., is not fully available from the beginning), incremental training suffers from catastrophic forgetting (i.e., new patterns are reinforced at the expense of previously acquired knowledge). Training from scratch each time new training data becomes available would result in extremely long training times and massive data accumulation. Rehearsal-based continual learning has shown promise for addressing the catastrophic forgetting challenge, but research to date has not addressed performance and scalability. To fill this gap, we propose an approach based on a distributed rehearsal buffer that efficiently complements data-parallel training on multiple GPUs, allowing us to achieve short runtime and scalability while retaining high accuracy. It leverages a set of buffers (local to each GPU) and uses several asynchronous techniques for updating these local buffers in an embarrassingly parallel fashion, all while handling the communication overheads necessary to augment input mini-batches (groups of training samples fed to the model) using unbiased, global sampling. In this paper we explore the benefits of this approach for classification models. We run extensive experiments on up to 128 GPUs of the ThetaGPU supercomputer to compare our approach with baselines representative of training-from-scratch (the upper bound in terms of accuracy) and incremental training (the lower bound). Results show that rehearsal-based continual learning achieves a top-5 classification accuracy close to the upper bound, while simultaneously exhibiting a runtime close to the lower bound.

关键词： Training Continuing education Deep learning Accuracy Runtime Upper bound Scalability Training data graphics processing units Supercomputers

来源：评论

学校读者我要写书评

暂无评论

PreSto: An In-Storage data Preprocessing System for Training Recommendation Models

PreSto: An In-Storage Data Preprocessing System for Training...

引用

Annual International symposium on Computer Architecture, ISCA

作者： Yunjae Lee Hyeseong Kim Minsoo Rhu School of Electrical Engineering KAIST

ISBN: (数字)9798350326581

ISBN: (纸本)9798350326598

Training recommendation systems (RecSys) faces several challenges as it requires the “data preprocessing” stage to preprocess an ample amount of raw data and feed them to the GPU for training in a seamless manner. To sustain high training throughput, state-of-the-art solutions reserve a large fleet of CPU servers for preprocessing which incurs substantial deployment cost and power consumption. Our characterization reveals that prior CPU-centric preprocessing is bottlenecked on feature generation and feature normalization operations as it fails to reap out the abundant inter-/intra-feature parallelism in RecSys preprocessing. PreSto is a storage-centric preprocessing system leveraging In-Storage Processing (ISP), which offloads the bottlenecked preprocessing operations to our ISP units. We show that PreSto outperforms the baseline CPU-centric system with a 9.6× speedup in end-to-end preprocessing time, 4.3× enhancement in cost-efficiency, and 11.3× improvement in energy-efficiency on average for production-scale RecSys preprocessing.

关键词： Training Power demand Costs data preprocessing graphics processing units parallel processing Throughput

来源：评论

学校读者我要写书评

暂无评论

AMST: Accelerating large-Scale Graph Minimum Spanning Tree Computation on FPGA

AMST: Accelerating Large-Scale Graph Minimum Spanning Tree C...

引用

International symposium on parallel and Distributed Processing (IPDPS)

作者： Haishuang Fan Rui Meng Qichu Sun Jingya Wu Wenyan Lu Xiaowei Li Guihai Yan State Key Laboratory of Processors Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences YUSUR Technology Co. Ltd

ISBN: (数字)9798350387117

ISBN: (纸本)9798350387124

The minimum spanning tree (MST) plays an important role in variant fields, such as chip design and network analysis. With the rapid expansion of vertices in real-life graphs, the bottleneck problem of MST algorithms in large-scale graphs grows more prominent. While there have been many FPGA-based accelerators for large-scale graph algorithms such as Graph Random Walk, and various algorithms to accelerate MST on CPUs and GPUs, effectively implementing MST algorithms for large-scale graphs on FPGAs remains quite challenging. This is due to several reasons: The neighbor vertices in the graph require extensive random memory access and the memory access characteristics vary across different stages and iterations. There are a large number of useless computations due to the existence of internal edges within a component (intra-edge). parallel MST algorithm suffers from significant communication overhead due to the minimum edge data update conflicts and memory read-write *** paper proposes AMST to accelerate large-scale graph MST computation on FPGA. First, AMST employs a customized hash-based high-degree vertex cache (HDC) to improve memory access efficiency. Second, AMST adopts a graph pruning strategy that skips intra-edge and sorts edges by weight to eliminate useless computation and memory access. Finally, AMST utilizes a sorting networking module and a multi-port HDC to improve parallel efficiency. The experimental results demonstrate that AMST achieves an average performance speedup of 17.52× over CPU and 1.89× over GPU, as well as 74.96× over CPU and 10.45× over GPU on energy efficiency.

关键词： Distributed processing Memory management Pipelines graphics processing units Network analyzers parallel processing Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Interactive visualization and On-Demand Processing of large Volume data: A Fully GPU-Based Out-of-Core Approach

引用

ieee TRANSACTIONS ON visualization AND COMPUTER graphics 2020年第10期26卷 3008-3021页

作者： Sarton, Jonathan Courilleau, Nicolas Remion, Yannick Lucas, Laurent Univ Reims F-51100 Reims France Neoxia F-75008 Paris France

In a wide range of scientific fields, 3D datasets production capabilities have widely evolved in recent years, especially with the rapid increase in their sizes. As a result, many large-scale applications, including visualization or processing, have become challenging to address. A solution to this issue lies in providing out-of-core algorithms specifically designed to handle datasets significantly larger than memory. In this article, we present a new approach that extends the broad interactive addressing principles already established in the field of out-of-core volume rendering on GPUs to allow on-demand processing during the visualization stage. We propose a pipeline designed to manage data as regular 3D grids regardless of the underlying application. It relies on a caching approach with a virtual memory addressing system coupled to an efficient parallel management on GPU to provide efficient access to data in interactive time. It allows any visualization or processing application to leverage the flexibility of its structure by managing multi-modality datasets. Furthermore, we show that our system delivers good performance on a single standard PC with low memory budget on the GPU.

关键词： GPU caching system out-of-core data management large data interactive visualization on-demand processing

来源：评论

学校读者我要写书评

暂无评论

Unveiling the Dynamics of Video Out-of-Focus Blur: A Paradigm of Realistic Simulation and Novel Evaluation

Unveiling the Dynamics of Video Out-of-Focus Blur: A Paradig...

引用

International symposium on parallel and Distributed Processing with Applications, ISPA

作者： Jing Chen Zhao Qiu Zhiwei Zheng School of Computer Science and Technology Hainan University Haikou China School of Hotel Management China University of Labor Relations Beijing China

ISBN: (数字)9798331509712

ISBN: (纸本)9798331509729

Video serves as the paramount medium through which humanity perceives the world via ocular faculties, spurring the development of myriad algorithms aimed at replicating the verisimilitude of the tangible realm. Among the numerous visual artifacts, out-of-focus blur remains a ubiquitous challenge, particularly prevalent in handheld camera cinematography. However, despite its common occurrence, the academic discourse on the underlying mechanisms of focal variance in video compositions is notably sparse, with a marked absence of publicly available datasets addressing real-world out-of-focus blur. In this study, we not only elucidate the phenomenon of video out-of-focus blur but also dissect the intrinsic dynamics governing focal fluctuations within authentic video sequences. We propose a novel framework for out-of-focus video simulation that faithfully replicates the nuanced characteristics of real-world scenarios. This framework involves segmenting a multitude of frames into discrete intervals through strategic keyframe selection, uniformly distributing focal planes across intervals, and meticulously rendering frames via a single-frame rendering methodology. Moreover, to evaluate the extent of out-of-focus blur in videos, we introduce an innovative metric that operates independently of ground truth data, thereby offering enhanced reliability compared to existing benchmarks.

关键词： Measurement visualization Computer vision Technological innovation Humanities Fluctuations Video sequences Cinematography Media Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：