2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)最新文献_第9页

Performance Analysis of Parallel FFT on Large Multi-GPU Systems 大型多gpu系统上并行FFT的性能分析

2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW) Pub Date : 2022-05-01 DOI: 10.1109/IPDPSW55747.2022.00072

Alan Ayala, S. Tomov, M. Stoyanov, A. Haidar, J. Dongarra

{"title":"Performance Analysis of Parallel FFT on Large Multi-GPU Systems","authors":"Alan Ayala, S. Tomov, M. Stoyanov, A. Haidar, J. Dongarra","doi":"10.1109/IPDPSW55747.2022.00072","DOIUrl":"https://doi.org/10.1109/IPDPSW55747.2022.00072","url":null,"abstract":"In this paper we present a performance study of multidimensional Fast Fourier Transforms (FFT) with GPU accelerators on modern hybrid architectures, as those expected for upcoming exascale systems. We assess and leverage features from traditional implementations of parallel FFTs and provide an algorithm that encompasses a wide range of their parameters, and adds novel developments such as FFT grid shrinking and batched transforms. Next, we create a bandwidth model to quantify the computational costs and analyze the well-known communication bottleneck for All-to-All and Point-to-Point MPI exchanges. Then, using a tuning methodology, we are able to accelerate the FFT computation and reduce the communication cost, achieving linear scalability on a large-scale system with GPU accelerators. Finally, our performance analysis is extended to show that carefully tuning the algorithm can further accelerate applications heavily relying on FFTs, such is the case of molecular dynamics software. Our experiments were performed on Summit and Spock supercomputers with IBM Power9 cores, over 3000 NVIDIA V-100 GPUs, and AMD MI-100 GPUs.","PeriodicalId":286968,"journal":{"name":"2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125408772","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

27th International Workshop on High-Level Parallel Programming Models and Supportive Environments (HIPS 2022) 第27届高级并行编程模型和支持环境国际研讨会(HIPS 2022)

2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW) Pub Date : 2022-05-01 DOI: 10.1109/IPDPSW55747.2022.00090

引用次数: 0

Message from the EduPar-22 Workshop Chairs 来自EduPar-22工作坊主席的信息

2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW) Pub Date : 2022-05-01 DOI: 10.1109/IPDPSW55747.2022.00062

引用次数: 0

DECISION: Distributing OpenVX Applications on CPUs, GPUs and FPGAs using OpenCL 决定:使用OpenCL在cpu、gpu和fpga上分发OpenVX应用程序

2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW) Pub Date : 2022-05-01 DOI: 10.1109/IPDPSW55747.2022.00023

Lester Kalms, Tim Haering, Diana Göhringer

{"title":"DECISION: Distributing OpenVX Applications on CPUs, GPUs and FPGAs using OpenCL","authors":"Lester Kalms, Tim Haering, Diana Göhringer","doi":"10.1109/IPDPSW55747.2022.00023","DOIUrl":"https://doi.org/10.1109/IPDPSW55747.2022.00023","url":null,"abstract":"The demand for computer vision systems and algorithms is steadily increasing. However, users often have to deal with different or new languages, architectures and tools. Furthermore, there is often no linkage between vendors, defined standards, or model-based modularization to connect everything. We propose a modularized framework for distributing applications on heterogeneous systems consisting of CPUs, GPUs, and FPGAs. The user builds an OpenVX-compliant application without knowledge of the underlying hardware. The middleend automatically schedules and maps the nodes to the available OpenCL devices. Benefits of FPGA acceleration, such as pipelining and running multiple nodes in parallel, are taken into account. The backend generates a program including memory management, synchronization mechanisms and data transfers, even between vendors. This is executed in our parallelized OpenCL based runtime system with minimal overhead. We achieved speedups of 1.63 for a heterogeneous schedule in comparison to a single GPU design when limiting the FPGA resources. Without this limitation a speedup of 13.39 is achieved for the same application.","PeriodicalId":286968,"journal":{"name":"2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","volume":"104 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122554789","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

JSSPP 2022 - 25th Workshop on Job Scheduling Strategies for Parallel Processing 并行处理作业调度策略研究[j]

2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW) Pub Date : 2022-05-01 DOI: 10.1109/IPDPSW55747.2022.00136

引用次数: 0

EDAML 2022 Invited Speaker 3: Scalable ML Architectures for Real-time Energy-efficient Computing EDAML 2022特邀演讲3:面向实时节能计算的可扩展机器学习架构

2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW) Pub Date : 2022-05-01 DOI: 10.1109/IPDPSW55747.2022.00196

R. I. Bahar

{"title":"EDAML 2022 Invited Speaker 3: Scalable ML Architectures for Real-time Energy-efficient Computing","authors":"R. I. Bahar","doi":"10.1109/IPDPSW55747.2022.00196","DOIUrl":"https://doi.org/10.1109/IPDPSW55747.2022.00196","url":null,"abstract":"Technological advancements have led to a proliferation machine learning systems to assist humans in a wide range of tasks. However, we are still far from accurate, reliable, and resource-efficient operations for many of these systems. Despite the strengths of convolutional neural networks (CNNs) for object recognition, these discriminative techniques have several shortcomings that leave them vulnerable to exploitation from adversaries. In addition, the computational cost incurred to train these discriminative models can be quite significant. Discriminative-generative approaches offers a promising avenue for robust perception and action. Such methods combine inference by deep learning with sampling and probabilistic inference models to achieve robust and adaptive understanding. In this talk, I will present our work on implementing a scalable, computationally efficient generative inference algorithm in hardware that can achieve real-time results in an energy efficient manner. I will also discuss future directions in designing scalable and efficient ML algorithms in hardware more broadly.","PeriodicalId":286968,"journal":{"name":"2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127633098","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Effect of Community-based Opinion Leaders on Guideline Dissemination in Large-Scale Physician Networks 基于社区意见领袖对大型医师网络指南传播的影响

2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW) Pub Date : 2022-05-01 DOI: 10.1109/IPDPSW55747.2022.00191

Vairavan Murugappan, Suresh Subramanian, John Korah, Pranav Pamidighantam, Eunice E. Santos

{"title":"Effect of Community-based Opinion Leaders on Guideline Dissemination in Large-Scale Physician Networks","authors":"Vairavan Murugappan, Suresh Subramanian, John Korah, Pranav Pamidighantam, Eunice E. Santos","doi":"10.1109/IPDPSW55747.2022.00191","DOIUrl":"https://doi.org/10.1109/IPDPSW55747.2022.00191","url":null,"abstract":"Despite continuous innovation and progress in the medical field, many treatments and interventions fail to translate to practice. Studies have shown that healthcare providers are slow to adopt new medical guidelines due to various reasons (slower knowledge dissemination, implementation challenges, etc.). Furthermore, there is a lack of computational modeling approaches to analyze and understand physician guideline adoption behaviors in real-world scenarios. Professional network characteristics and local opinion leaders play a vital role in dissemination and adoption of medical guidelines in physician communities. In this work, we provide a systematic approach to identify opinion leaders (OLs) based on physician community characteristics. The proposed approach will leverage our previous work in Culturally Infused Agent Based Modeling Framework that can capture physician decision-making and guideline adoption behavior in real-world settings. Using large physician datasets such as the Physician Compare and physician share datasets, we demonstrate the utility and scalability of our approach. By comparing with various strategies to select OLs, we show that our community-based OL detection method can capture the trade-off between increasing reach and rate of spread.","PeriodicalId":286968,"journal":{"name":"2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124712278","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

ScaDL 2022: Fourth IPDPS Workshop on Scalable Deep Learning over Parallel and Distributed Infrastructure ScaDL 2022:第四届基于并行和分布式基础设施的可扩展深度学习IPDPS研讨会

2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW) Pub Date : 2022-05-01 DOI: 10.1109/IPDPSW55747.2022.00165

引用次数: 0

ScaDL 2022 Invited Talk 4: Sustainable AI @ Scale: Accelerating AI models for billions of users ScaDL 2022特邀演讲4:可持续人工智能@规模:加速数十亿用户的人工智能模型

2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW) Pub Date : 2022-05-01 DOI: 10.1109/IPDPSW55747.2022.00169

M. Gschwind

引用次数: 0

Sequre: a high-performance framework for rapid development of secure bioinformatics pipelines secure:用于快速开发安全生物信息学管道的高性能框架

2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW) Pub Date : 2022-05-01 DOI: 10.1109/IPDPSW55747.2022.00040

Haris Smajlovic, Ariya Shajii, Bonnie Berger, Hyunghoon Cho, Ibrahim Numanagić

{"title":"Sequre: a high-performance framework for rapid development of secure bioinformatics pipelines","authors":"Haris Smajlovic, Ariya Shajii, Bonnie Berger, Hyunghoon Cho, Ibrahim Numanagić","doi":"10.1109/IPDPSW55747.2022.00040","DOIUrl":"https://doi.org/10.1109/IPDPSW55747.2022.00040","url":null,"abstract":"Genomic data leaks are irreversible. Leaked DNA cannot be changed, stays disclosed indefinitely, and affects the owner's family members as well. The recent large-scale genomic data collections [1], [2] render the traditional privacy protection mechanisms, like the Health Insurance Portability and Accountability Act (HIPAA), inadequate for protection against the novel security attacks [3]. On the other hand, data access restrictions hinder important clinical research that requires large datasets to operate [4]. These concerns can be naturally addressed by the employment of privacy-enhancing technologies, such as a secure multiparty computation (MPC) [5]–[10]. Secure MPC enables computation on data without disclosing the data itself by dividing the data and computation between multiple computing parties in a distributed manner to prevent individual computing parties from accessing raw data. MPC systems are being increasingly adopted in fields that operate on sensitive datasets [11]–[13], such as computational genomics and biomedical research [14]–[22].","PeriodicalId":286968,"journal":{"name":"2022 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)","volume":"176 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116472880","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1