检索结果-内蒙古大学图书馆

Performance evaluation of GAIA supercomputer using NPB multi-zone benchmarks

COMPUTER PHYSICS COMMUNICATIONS 2011年第1期182卷 263-265页

作者： Yi, Hongsuk Korea Inst Sci & Technol Informat Supercomp Ctr Taejon 305806 South Korea

GAIA is a recently developed IBM POWER6 supercomputer consisting of 24 SMP compute nodes with 64-way processors each and it is currently ranked 393 on the Top500 supercomputer list published in November 2009 In this paper we present the performance characteristics of GAIA evaluated by interconnecting the 24 computing nodes with low-latency InfiniBand network We evaluate the performance of the new dual-core Power 595 system in terms of increased problem size using the multi-zone versions of the NAS parallel Benchmarks (C) 2010 Elsevier B V All rights reserved

关键词： Multi-level parallelism NAS parallel benchmarks hybrid parallel programming

来源：评论

学校读者我要写书评

暂无评论

The Energy Consumption Analysis for the Multispectral Infrared Satellite Images Processing Algorithm 3rd

The Energy Consumption Analysis for the Multispectral Infrar...

引用

3rd Russian Supercomputing Days (RuSCDays)

作者： Tyutlyaeva, Ekaterina Konyukhov, Sergey Odintsov, Igor Moskovsky, Alexander ZAO RSC Technol Kutuzovskiy Ave 36Bldg 23 Moscow 121170 Russia

ISBN: (纸本)9783319712543;9783319712550

This paper includes the energy consumption analysis of the testing mini-application that implements night time infrared remote sensing algorithm Nightfire. On this stage of our project computational nodes with Intel Xeon E5 and Intel Xeon Phi processors were tested. The correlation analysis between the number of used MPI ranks - OMP threads and total energy consumptions was performed for each of tested computational nodes. The optimized benchmarking parameters were used to compare energy efficiency of tested nodes. Moreover, the analysis of mini-application statements blocks was carried out for the following computation phases: I/O with HDF5 and ENVI data;the data processing using Nelder-Mead method. The impact of each computation phase to the total energy consumptions was determined so it gives new insights to possible ways of further optimization. Based on obtained results, the effectiveness of tested computational architectures for multispectral satellite images processing was evaluated.

关键词： Energy consumption Energy efficiency Satellite image processing Power-aware execution hybrid parallel programming

来源：评论

学校读者我要写书评

暂无评论

Enabling Efficient Multithreaded MPI Communication Through a Library-Based Implementation of MPI Endpoints 14

Enabling Efficient Multithreaded MPI Communication Through a...

引用

International Conference on High Performance Computing, Networking, Storage and Analysis

作者： Sridharan, Srinivas Dinan, James Kalamkar, Dhiraj D. Intel Corp Santa Clara CA 95054 USA

ISBN: (纸本)9781479955008

Modern high-speed interconnection networks are designed with capabilities to support communication from multiple processor cores. The MPI endpoints extension has been proposed to ease process and thread count tradeoffs by enabling multithreaded MPI applications to efficiently drive independent network communication. In this work, we present the first implementation of the MPI endpoints interface and demonstrate the first applications running on this new interface. We use a novel library-based design that can be layered on top of any existing, production MPI implementation. Our approach uses proxy processes to isolate threads in an MPI job, eliminating threading overheads within the MPI library and allowing threads to achieve process-like communication performance. We evaluate the performance advantages of our implementation through several benchmarks and kernels. Performance results for the Lattice QCD Dslash kernel indicate that endpoints provides up to 2.9x improvement in communication performance and 1.87x overall performance improvement over a highly optimized hybrid MPI+ OpenMP baseline on 128 processors.

关键词： MPI hybrid parallel programming Endpoints

来源：评论

学校读者我要写书评

暂无评论

A hybrid parallel Implementation for the Maximum Flow Problem 26

A Hybrid Parallel Implementation for the Maximum Flow Proble...

引用

26th Euromicro International Conference on parallel, Distributed, and Network-Based Processing (PDP)

作者： Stefanes, Marco A. Alvino, Luiz F. Univ Fed Mato Grosso do Sul Comp Coll Campo Grande Brazil Univ Fed Mato Grosso do Sul Campo Grande Brazil

ISBN: (纸本)9781538649756

The maximum flow problem is a classical combinatorial problem with many applications. In this work a hybrid parallel algorithm using both multi-core and many-core technologies for computing the maximum flow in a network is presented. The proposed implementation is applicable in OpenMP/CUDA-enabled computing environment. To improve the performance two strategies were implemented: an adaptive approach where the algorithm alternate GPU/CPU processing according to the number of active nodes and implementations of the global relabeling and gap relabeling heuristics on multi-core approach. When compared against the best sequential implementation, the speedups range from 2.36 to 5.38 in several kinds of graph. Results show that the proposed algorithm is faster than previous parallel implementations on CPU/GPUs for all kinds of tested graphs.

关键词： Maximum flow Push-relabel method hybrid parallel programming Multi/many-core architectures

来源：评论

学校读者我要写书评

暂无评论

Scaling Scientific Applications on Clusters of hybrid Multicore/GPU Nodes 11

Scaling Scientific Applications on Clusters of Hybrid Multic...

引用

8th ACM International Conference on Computing Frontiers (CF)

作者： Wang, Lingyuan Huang, Miaoqing Narayana, Vikram K. El-Ghazawi, Tarek George Washington Univ ECE Dept Washington DC 20052 USA Univ Arkansas CSCE Dept Fayetteville AR 72701 USA

ISBN: (纸本)9781450306980

Rapid advances in the performance and programmability of graphics accelerators have made GPU computing a compelling solution for a wide variety of application domains. However, the increased complexity as a result of architectural heterogeneity and imbalances in hardware resources poses significant programming challenges in harnessing the performance advantages of GPU accelerated parallel systems. Moreover, the speedup derived from GPU often gets offset by longer communication latencies and inefficient task scheduling. To achieve the best possible performance, a suitable parallel programming model is therefore essential. In this paper, we explore a new hybrid parallel programming model that incorporates GPU acceleration with the Partitioned Global Address Space (PGAS) programming paradigm. As we demonstrate, by combining Unified parallel C (UPC) and CUDA as a case study, this hybrid model offers programmers with both enhanced programmability and powerful heterogeneous execution. Two application benchmarks, namely NAS parallel Benchmark (NPB) FT and MG, are used to show the effectiveness of our proposed hybrid approach. Experimental results indicate that both implementations achieve significantly better performance due to optimization opportunities offered by the hybrid model, such as the funneled execution mode and fine-grained overlapping of communication and computation.

关键词： GPU Multicore UPC hybrid parallel programming

来源：评论

学校读者我要写书评

暂无评论

Optimizing Sparse Matrix Assembly in Finite Element Solvers with One-Sided Communication 1

引用

10th International Conference on High Performance Computing for Computational Science (VECPAR)

作者： Jansson, Niclas KTH Royal Inst Technol Sch Comp Sci & Commun SE-10044 Stockholm Sweden

ISBN: (数字)9783642387180

ISBN: (纸本)9783642387180;9783642387173

In parallel finite element solvers, sparse matrix assembly is often a bottleneck. Implemented using message passing, latency from message matching starts to limit performance as the number of cores increases. We here address this issue by using our own stack based representation of the sparse matrix, and a hybrid parallel programming model combining traditional message passing with one-sided communication. This gives an significantly faster insertion rate compared to state of the art implementations on a Cray XE6.

关键词： UPC PGAS hybrid parallel programming

来源：评论

学校读者我要写书评

暂无评论

Load balancing multi-zone applications on a heterogeneous cluster with multi-level parallelism

Load balancing multi-zone applications on a heterogeneous cl...

引用

3rd International Symposium on parallel and Distributed Computing (ISPDC 2004)/3rd International Workshop on Algorithms, Models and Tools for parallel Computing on Heterogeneous Networks (HeteroPar 04)

作者： Wong, P Jin, HQ Becker, J NASA Ames Res Ctr Adv Supercomp Div Moffett Field CA 94035 USA

ISBN: (纸本)0769522106

We investigate the feasibility of running parallel applications on heterogeneous clusters. The motivation for doing so is twofold. First, it is practical to be able to pull together existing machines to run a job that is too big for any one of them, especially if such jobs are run rarely. Second, in the event of an emergency, where a very large problem must be solved in a few days, it may not be feasible to purchase and install a new machine in time, and any existing machines will have to be brought to bear on the problem. We ran the Multi-zone versions of the NAS parallel Benchmarks (NPB) on a cluster composed of two SGI Origin 2000 servers, and an Intel SMP Xeon server connected by Gigabit Ethernet. We report on the results and their implications for running parallel applications on heterogeneous clusters.

关键词： NAS parallel Benchmarks heterogeneous cluster load balancing hybrid parallel programming

来源：评论

学校读者我要写书评

暂无评论

Communication and optimization aspects on hybrid architectures

引用

9th European parallel Virtual Machine and Message Passing Interface Group Meeting (PVM/MPI)

作者： Rabenseifner, R Univ Stuttgart Ctr High Performance Comp HLRS D-70550 Stuttgart Germany

ISBN: (纸本)3540442960

Most HPC systems are clusters of shared memory nodes. parallel programming must combine the distributed memory parallelization on the node inter-connect with the shared memory parallelization inside of each node. The hybrid MPI+OpenMP programming model is compared with pure MPI and compiler based parallelization. The paper focuses on bandwidth and latency aspects, but also whether programming paradigms can separate the optimization of communication. and computation. Benchmark results are presented for hybrid and pure MPI communication.

关键词： OpenMP MPI hybrid parallel programming threads and MPI HPC

来源：评论

学校读者我要写书评

暂无评论

Development Environment for hybrid Applications on Heterogeneous Clusters 9

Development Environment for Hybrid Applications on Heterogen...

引用

IEEE 9th International Conference on Advanced Computing (IACC)

作者： Deepika, H., V Mangala, N. C DAC Syst Software HPC Bangalore Karnataka India

ISBN: (纸本)9781728143927

The evolution of cluster computers based on multicores, many cores and GPGPU accelerators is encouraging application developers to write hybrid parallel programs. hybrid parallel programming is quite complex as it requires use of multiple programming paradigms such as MPI, OperiMP, CTIDA/OpenCL to exploit the varied computational power available in a system. The paper brings out the challenges faced by application developers desiring to use heterogeneous HPC clusters. It describes a unified development environment which eases the complete development lifecycle of hybrid parallel programs on a HPC cluster. The software is capable of providing access to multiple clusters of different architectures, owing to the modularity of design and web based approach. The paper also serves as a good resource for researchers interested to gain an insight into hybrid parallel programming.

关键词： hybrid parallel programming Heterogeneous CPU-GPU architecture Integrated Development Environment petascale prograntnting programmer productivity

来源：评论

学校读者我要写书评

暂无评论

A Distributed-memory parallelization of a Shared-memory parallel Ensemble Kalman Filter 16

A Distributed-memory Parallelization of a Shared-memory Para...

引用

16th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing (SYNASC)

作者： Rostami, M. Ali Buecker, H. Martin Vogt, Christian Seidler, Ralf Neuhaeuser, David Rath, Volker Univ Jena Inst Comp Sci D-07743 Jena Germany Rhein Westfal TH Aachen Inst Appl Geophys & Geothermal Energy EON Energy Res Ctr D-52056 Aachen Germany Dublin Inst Adv Studies Sch Cosm Phys Dublin 4 Ireland Univ Complutense Madrid Dept Fis Tierra Astron & Astrofis 2 Madrid Spain

ISBN: (纸本)9781479984480

Inverse problems arise in various areas of science and engineering. These problems are not only difficult to solve numerically, but they also require a large amount of computer resources both in time and memory. It is therefore not surprising that inverse problems are often solved using techniques from high-performance computing. We consider the parallelization of an inverse problem in the field of geothermal reservoir engineering. In this particular scientific application, the underlying software package is already parallelized using the shared-memory programming paradigm OpenMP. Here, we present an extension of this parallelization to distributed memory enabling a hybrid OpenMP/MPI parallelization. The situation is different from the standard way of hybrid parallel programming because the data structures of the OpenMP-parallelized code differ from those in the serial implementation. We exploit this transformation of the data structures in our distributed-memory strategy for parallelizing an ensemble Kalman filter, a particular method for the solution of inverse problems. We describe this novel parallelization strategy, introduce a performance model, and present timing results on a compute cluster using nodes with 2 sockets, each equipped with Intel Xeon X5675 Westmere EP processors with 6 cores. All timing results are obtained with a pure MPI parallelization without using any OpenMP threads.

关键词： Kalman filters message passing parallel programming shared memory systems Intel Xeon X5675 Westmere EP processors computer resource data structures distributed-memory parallelization geothermal reservoir engineering hybrid Open MP-MPI parallelization hybrid parallel programming message passing interface parallelization strategy shared-memory parallel ensemble Kalman filter shared-memory programming paradigm Algorithm design and analysis Arrays Computational modeling Inverse problems Mathematical model Standards Inverse method message passing Kalman filters parallelization Algorithm design and analysis shared memory systems parallel programming Data structures Reservoir engineering distributed memory Computational modeling Mathematical Model

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：