2021 29th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)最新文献

筛选
英文 中文
Message from the Program Committee Chairs 来自计划委员会主席的信息
{"title":"Message from the Program Committee Chairs","authors":"","doi":"10.1109/pdp52278.2021.00006","DOIUrl":"https://doi.org/10.1109/pdp52278.2021.00006","url":null,"abstract":"On behalf of the SCAM 2002 Conference and Program Committees, we would like to welcome you to this year's workshop. This is the second Source Code Analysis and Manipulation Workshop. While it required a great deal of effort by a large number of people to put together this year's workshop, this work only serves to underscore the greater effort put forth by Mark Harman in making the first SCAM workshop a reality. Thank you, Mark.","PeriodicalId":356657,"journal":{"name":"2021 29th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128737606","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
Analyzing the distributed training of deep-learning models via data locality 基于数据局部性的深度学习模型分布式训练分析
Saúl Alonso-Monsalve, A. Calderón, Félix García Carballeira, José Rivadeneira
{"title":"Analyzing the distributed training of deep-learning models via data locality","authors":"Saúl Alonso-Monsalve, A. Calderón, Félix García Carballeira, José Rivadeneira","doi":"10.1109/PDP52278.2021.00026","DOIUrl":"https://doi.org/10.1109/PDP52278.2021.00026","url":null,"abstract":"In the last few years, deep-learning models are becoming crucial for numerous scientific and industrial applications. Due to the growth and complexity of deep neural networks, researchers have been investigating techniques to train those networks more efficiently. Many efforts have been made to optimize deep-learning models by parallelizing or distributing their training computation across multiple devices. Current state-of-the-art techniques, such as Horovod, have shown to maximize the performance of both the training computation and the inter-node communication of models for different deep-learning frameworks. However, some applications cannot take advantage of the above techniques due to an I/O bottleneck caused by the input data, thus limiting the scalability of the trainings. In this paper, we study an approach based on data locality - that has not been fully studied yet - for those neural networks that cannot benefit from scaling their computation due to a significant bottleneck in the data I/O.","PeriodicalId":356657,"journal":{"name":"2021 29th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125906095","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
A Cross-Platform OpenVX Library for FPGA Accelerators FPGA加速器的跨平台OpenVX库
Maria Angélica Dávila-Guzmán, Rubén Gran Tejero, M. Villarroya-Gaudó, D. S. Gracia, Lester Kalms, D. Göhringer
{"title":"A Cross-Platform OpenVX Library for FPGA Accelerators","authors":"Maria Angélica Dávila-Guzmán, Rubén Gran Tejero, M. Villarroya-Gaudó, D. S. Gracia, Lester Kalms, D. Göhringer","doi":"10.1109/PDP52278.2021.00020","DOIUrl":"https://doi.org/10.1109/PDP52278.2021.00020","url":null,"abstract":"In Computer Vision, open programming standards such as OpenVX have emerged to bring together portability and acceleration across devices. Unfortunately, achieving both goals on FPGAs remains a challenge because FPGAs still require to adapt the code with proprietary extensions. Exclusively for Xilinx devices, the HiFlipVX open source library partially solves this problem by offering a clean C++ OpenVX API that offers the performance of proprietary extensions without exposing its complexity to programmer. While HiFlipVX enables portability within Xilinx devices, portability between FPGA manufacturers remains an open challenge. This work extends the HiFlipVX’s capabilities with a twofold goal: i) to support Intel FPGA devices with different memory configurations, and ii) to enable execution on FPGAs as discrete accelerators. To accomplish these goals, the proposed implementation combines two HLS programming models: C++, using Intel’s system of tasks that enables to coalesce nodes and reduce control overhead, and OpenCL, which provides efficient compute kernel nodes. On Intel FPGAs, compared with pure OpenCL implementations, the proposed implementation reduces kernel dispatch resources, saving up to 24% of ALUT resources for each kernel in a graph, and improves performance. Gains are $2.6times$ on average for representative applications, such as Canny edge detector, or Census transform, compared with state-of-the-art frameworks.","PeriodicalId":356657,"journal":{"name":"2021 29th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116607529","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
Bucket MapReduce: Relieving the Disk I/O Intensity of Data-Intensive Applications in MapReduce Frameworks 桶式MapReduce:减轻MapReduce框架中数据密集型应用的磁盘I/O强度
Kairui Chen, Hsin-Yuan Chen, Chien-Min Wang
{"title":"Bucket MapReduce: Relieving the Disk I/O Intensity of Data-Intensive Applications in MapReduce Frameworks","authors":"Kairui Chen, Hsin-Yuan Chen, Chien-Min Wang","doi":"10.1109/PDP52278.2021.00013","DOIUrl":"https://doi.org/10.1109/PDP52278.2021.00013","url":null,"abstract":"Hadoop MapReduce is a software framework for processing vast amounts of data in parallel on large clusters. As data size increases, a need arises to resolve the significant increase in the disk $I/O$ of reducer nodes, which may cause runtime bottlenecks. In response, we propose Bucket MapReduce, a system that utilizes bucket sort and pipeline parallelism to improve the performance of Hadoop MapReduce. Several parameters may influence the performance in Bucket MapReduce, and thus we will further discuss parameter tuning. In this paper, we perform experiments on TeraSort benchmark. Bucket MapReduce successfully reduces local disk $I/O$ by 61% and improves the runtime by 1. 39x in 800GB TeraSort benchmark.","PeriodicalId":356657,"journal":{"name":"2021 29th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128681075","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
On GPU optimizations of stencil codes for highly parallel simulations 高并行仿真中模板代码的GPU优化
Nikolai Pfisterer, M. Berghoff, A. Streit
{"title":"On GPU optimizations of stencil codes for highly parallel simulations","authors":"Nikolai Pfisterer, M. Berghoff, A. Streit","doi":"10.1109/PDP52278.2021.00043","DOIUrl":"https://doi.org/10.1109/PDP52278.2021.00043","url":null,"abstract":"Stencil codes are valuable methods to solve partial differential equations of models in a wide range of applications in science and engineering. Graphics processing units (GPUs) provide a highly parallel architecture with fast directly accessible memory that is desirable to run stencil codes. They enable larger and more complex simulations that are solved faster compared to simulating on CPUs. We provide a solution for users to run highly parallel stencil codes on GPUs, that can also be efficiently used on a distributed GPU cluster.In this work, we present an extension to the multi-disciplinary framework NAStJA originally designed to efficiently run stencil codes on the CPUs in current high-performance computing (HPC) systems, to also be able to run on GPUs. We describe different methods to increase the performance of stencil codes on GPUs like a border exchange method which is transparent to the user, as well as a buffer for gradient values that are needed multiple times. We show their performance using the phase-field method as a stencil code example.With this GPU extension and optimizations implemented into the NAStJA framework, we can show highly improved performance compared to the CPU implementation, and an efficiency of 92% (weak scaling) for a large-scale example simulation on 64 GPUs on the ForHLR II HPC system.","PeriodicalId":356657,"journal":{"name":"2021 29th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129292974","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
An Efficient Practical Non-Blocking PageRank Algorithm for Large Scale Graphs 一种高效实用的大规模图无阻塞PageRank算法
Hemalatha Eedi, Sathya Peri, Neha Ranabothu, Rahul Utkoor
{"title":"An Efficient Practical Non-Blocking PageRank Algorithm for Large Scale Graphs","authors":"Hemalatha Eedi, Sathya Peri, Neha Ranabothu, Rahul Utkoor","doi":"10.1109/PDP52278.2021.00015","DOIUrl":"https://doi.org/10.1109/PDP52278.2021.00015","url":null,"abstract":"PageRank algorithm is a benchmark for many graph analytics and is the underlying kernel for link predictions, recommendation systems. It is an iterative algorithm that updates ranks of pages until the value converges. Implementation of PageRank algorithm on a shared memory architecture while taking advantage of fine-grained parallelism using large-scale graphs is a challenging task. In this paper, We present parallel algorithms for computing the PageRank suitable to the shared memory systems. Initially, we present parallel implementations of page-rank algorithms using barrier and lock variants. Later, we propose new approaches which are lock-free and are barrier-less synchronization to overcome the issues of lock based methods.A detailed experimental analysis of our approach is carried out using real-world web graphs from SNAP and Synthetic Graphs from RMAT on an Intel(R) Xeon E5-2660 v4 processor architecture with 56 threads using the POSIX thread library.","PeriodicalId":356657,"journal":{"name":"2021 29th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123317263","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: 5
Combining Thread Throttling and Mapping to Optimize the EDP of Parallel Applications 结合线程节流和映射优化并行应用程序的EDP
Gustavo Berned, Thiarles S. Medeiros, M. Serpa, F. Rossi, M. C. Luizelli, P. Navaux, A. C. S. Beck, A. Lorenzon
{"title":"Combining Thread Throttling and Mapping to Optimize the EDP of Parallel Applications","authors":"Gustavo Berned, Thiarles S. Medeiros, M. Serpa, F. Rossi, M. C. Luizelli, P. Navaux, A. C. S. Beck, A. Lorenzon","doi":"10.1109/PDP52278.2021.00035","DOIUrl":"https://doi.org/10.1109/PDP52278.2021.00035","url":null,"abstract":"Thread-throttling and mapping strategies have been used together to make better use of hardware resources and improve the energy-delay product (EDP) of high-performance computing (HPC) systems. However, the design space exploration significantly grows with the increasing number of cores in those systems, making the task of finding the ideal number of active threads and allocating strategy a challenging task. On top of that, parallel applications present various patterns, such as irregularity, unbalanced computations, or high rates of communications. Given these considerations, we propose ETTM, an EDPaware thread-throttling and mapping optimization strategy that automatically finds an ideal combination of number of threads and thread mapping strategy. With the execution of eighteen well-known benchmarks on three multicore architectures, we show that EDP can be significantly improved when running applications with the solution found by EETM1.","PeriodicalId":356657,"journal":{"name":"2021 29th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130670472","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: 2
A Case Study of Run-Time Testing of Self Organizations in Multi-Embedded-Agent Systems 多嵌入式智能体系统中自组织运行时测试案例研究
Arthur Baudet, O. Aktouf, Annabelle Mercier, Jean-Paul Jamont
{"title":"A Case Study of Run-Time Testing of Self Organizations in Multi-Embedded-Agent Systems","authors":"Arthur Baudet, O. Aktouf, Annabelle Mercier, Jean-Paul Jamont","doi":"10.1109/PDP52278.2021.00018","DOIUrl":"https://doi.org/10.1109/PDP52278.2021.00018","url":null,"abstract":"We develop a testing approach for validating global adaptation in self-organizing multi-embedded-agent systems. These systems are complex and ever adapting, thus challenging to test. We propose an approach aiming at validating at run-time the adaptation of these systems when the entities composing them, the agents, use self-organization processes. These processes allow agents to change their organization, i.e., their way of interacting, at run-time. Thus, run-time testing is needed to validate self-organization. We propose a decentralized self-organization runtime testing algorithm and we apply it, through simulation, to the Multi-Wireless-Agent Communication model.","PeriodicalId":356657,"journal":{"name":"2021 29th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)","volume":"88 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130490357","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
High Performance and Energy Efficient Integer Matrix Multiplication for Deep Learning 用于深度学习的高性能节能整数矩阵乘法
Pau San Juan, P. Alonso-Jordá, E. S. Quintana‐Ortí
{"title":"High Performance and Energy Efficient Integer Matrix Multiplication for Deep Learning","authors":"Pau San Juan, P. Alonso-Jordá, E. S. Quintana‐Ortí","doi":"10.1109/PDP52278.2021.00027","DOIUrl":"https://doi.org/10.1109/PDP52278.2021.00027","url":null,"abstract":"We present a multi-threaded implementation of the matrix multiplication for deep learning on ARM multicore processors. Following standard practice for inference with convolutional neural networks, our GEMM kernel operates with 16-bit integer arithmetic, yielding significant performance acceleration and cutting the memory requirements with respect to IEEE (floating point) single precision by half, allowing the deployment of larger neural network models on low power devices with limited storage capacity.","PeriodicalId":356657,"journal":{"name":"2021 29th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)","volume":"112 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126396662","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: 2
Local Traffic-Based Energy-Efficient Hybrid Switching for On-Chip Networks 基于本地流量的片上网络节能混合交换
Yuan He, Jinyu Jiao, Masaaki Kondo
{"title":"Local Traffic-Based Energy-Efficient Hybrid Switching for On-Chip Networks","authors":"Yuan He, Jinyu Jiao, Masaaki Kondo","doi":"10.1109/PDP52278.2021.00039","DOIUrl":"https://doi.org/10.1109/PDP52278.2021.00039","url":null,"abstract":"Advanced flow control mechanisms employed by modern on-chip networks are the reasons of large energy footprint and long per-hop latency. On the other hand, dated and simpler flow controls such as circuit switching can draw far less power and offer an end-to-end latency analogous to wire delay. In this paper, we present a hybrid flow control mechanism, which mixes both virtual channels and circuit-switching, to provide a latency-competitive and energy-efficient on-chip network design. Contrary to existing hybrid switching designs, our proposal is based on local traffic so that circuits are formed without the knowledge of end-to-end traffic. When compared to on-chip networks with virtual channels, our proposal achieves a very competitive latency per flit, for up to 4% lower, while also dramatically suppressing the energy per flit by up to 18%.","PeriodicalId":356657,"journal":{"name":"2021 29th Euromicro International Conference on Parallel, Distributed and Network-Based Processing (PDP)","volume":"317 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121114273","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
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信
小红书