检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Czappa, Fabian Geiß, Alexander Wolf, Felix Laboratory for Parallel Programming Department of Computer Science Technical University of Darmstadt Germany

Structural plasticity of the brain describes the creation of new and the deletion of old synapses over time. Rinke et al. (JPDC 2018) introduced a scalable algorithm that simulates structural plasticity for up to one billion neurons on current hardware using a variant of the Barnes–Hut algorithm. They demonstrate good scalability and prove a runtime complexity of O(n log2 n). In this comment paper, we show that with careful consideration of the algorithm and a rigorous proof, the theoretical runtime can even be classified as O(n log n). © 2022, CC BY-NC-ND.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Using Shared Arrays in Message-Driven parallel Programs

Using Shared Arrays in Message-Driven Parallel Programs

引用

IEEE International Symposium on parallel and Distributed Processing Workshops and Phd Forum (IPDPSW)

作者： Phil Miller Aaron Becker Laxmikant Kale Parallel Programming Laboratory Department of Computer Science University of Illinois Urbana-Champaign USA

This paper describes a safe and efficient combination of the object-based message-driven execution and shared array parallel programming models. In particular, we demonstrate how this combination engenders the composition of loosely coupled parallel modules safely accessing a common shared array. That loose coupling enables both better flexibility in parallel execution and greater ease of implementing multi-physics simulations. As a case study, we describe how the parallelization of a new method for molecular dynamics simulation benefits from both of these advantages. We also describe a system of typed handle objects that embed some of the determinacy constraints of the Multiphase Shared Array programming model in the C++ type system, to catch some violations at compile time. The combined programming model communicates in terms of these handles as a natural means of detecting and preventing errors.

关键词： Arrays Message systems Synchronization Instruction sets Runtime Phased arrays programming

来源：评论

学校读者我要写书评

暂无评论

Scalable detection of MPI-2 remote memory access inefficiency patterns

Scalable detection of MPI-2 remote memory access inefficienc...

引用

作者： Hermanns, Marc-André Geimer, Markus Mohr, Bernd Wolf, Felix Laboratory for Parallel Programming German Research School for Simulation Sciences GmbH 52425 Jülich Germany Forschungszentrum Jülich Jülich Supercomputing Centre Germany Department of Computer Science RWTH Aachen University Germany

Wait states in parallel applications can be identified by scanning event traces for characteristic patterns. In our earlier work we defined such inefficiency patterns for MPI-2 one-sided communication, although still based on a serial trace-analysis scheme with limited scalability. In this article we show how wait states in one-sided communications can be detected in a more scalable fashion by taking advantage of a new scalable trace-analysis approach based on a parallel replay, which was originally developed for MPI-1 point-to-point and collective communication. Moreover, we demonstrate the scalability of our method and its usefulness for the optimization cycle with applications running on up to 32,768 cores. © The Author(s) 2012.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

MICE: a prototype MPI implementation in Converse environment

MICE: a prototype MPI implementation in Converse environment

引用

Proceedings of the MPI Developer's Conference

作者： M.A. Bhandarkar L.V. Kale Parallel Programming Laboratory Department of Computer Science University of Illinois Urbana-Champaign Urbana IL USA

The paper describes MICE, a prototype implementation of MPI on the Converse interoperable parallel programming environment. It is based on MPICH, a public-domain implementation of MPI and uses the Abstract Device Interface (ADI) which has been retargeted on top of Converse. MICE makes use of message-managers and allows use of thread-objects to let MPI modules co-exist with other types of computations and communication (such as a library computation in Charm++ or asynchronous computations in multipol) within a single application. It also makes it possible to interoperate PVM (in a restricted form) and MPI modules. Thread-objects make it possible to build multi-threaded MPI programs. This MPI implementation demonstrates that it is possible to provide interoperability without any significant performance degradation.

关键词： Mice Prototypes parallel programming Libraries parallel languages Computer science Degradation programming profession programming environments Computer languages

来源：评论

学校读者我要写书评

暂无评论

Capturing inter-application interference on clusters

Capturing inter-application interference on clusters

引用

IEEE International Conference on Cluster Computing

作者： Aamer Shah Felix Wolf Sergey Zhumatiy Vladimir Voevodin German Research School for Simulation Sciences Laboratory for Parallel Programming Moscow State University Research Computing Center

Cluster systems usually run several applications-often from different users-concurrently, with individual applications competing for access to shared resources such as the file system or the network. Low application performance is therefore not always the result of inefficient program design, but may instead be caused by interference from outside. However, knowing the difference is essential for an appropriate response. Unfortunately, traditional performance-analysis techniques consider an application always in isolation, without the ability to compare its performance to the overall performance conditions on the system when it was executed. In this paper, we present a novel approach of how to correlate the performance behavior of applications running side by side. To accomplish this, we divide the application runtime into fine-grained time slices whose boundaries are synchronized across the entire system. Mapping performance data related to shared resources onto these time slices, we are able to establish the simultaneity of their usage across jobs, which can be indicative of inter-application interference. Our experiments show that such interference effects, for which the developer is usually not to blame, can degrade application performance significantly.

关键词： Interference Noise Benchmark testing Measurement Graphics processing units Runtime Hardware

来源：评论

学校读者我要写书评

暂无评论

Optimizing an MPI weather forecasting model via processor virtualization

Optimizing an MPI weather forecasting model via processor vi...

引用

17th International Conference on High Performance Computing, HiPC 2010

作者： Rodrigues, Eduardo R. Navaux, Philippe O. A. Panetta, Jairo Mendes, Celso L. Kalé, Laxmikant V. Institute of Informatics Federal University of Rio Grande do Sul Porto Alegre Brazil Center for Weather Forecasts and Climate Studies INPE Cachoeira Paulista Brazil Parallel Programming Laboratory University of Illinois at Urbana-Champaign Urbana IL United States

ISBN: (纸本)9781424485185

Weather forecasting models are computationally intensive applications. These models are typically executed in parallel machines and a major obstacle for their scalability is load imbalance. The causes of such imbalance are either static (e.g. topography) or dynamic (e.g. shortwave radiation, moving thunderstorms). Various techniques, often embedded in the application's source code, have been used to address both sources. However, these techniques are inflexible and hard to use in legacy codes. In this paper, we demonstrate the effectiveness of processor virtualization for dynamically balancing the load in BRAMS, a mesoscale weather forecasting model based on MPI parallelization. We use the Charm++ infrastructure, with its overdecomposition and object-migration capabilities, to move subdomains across processors during execution of the model. Processor virtualization enables better overlap between computation and communication and improved cache efficiency. Furthermore, by employing an appropriate load balancer, we achieve better processor utilization while requiring minimal changes to the model's code. ©2010 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Automatic parallel Pattern Detection in the Algorithm Structure Design Space

Automatic Parallel Pattern Detection in the Algorithm Struct...

引用

International Symposium on parallel and Distributed Processing (IPDPS)

作者： Zia Ul Huda Rohit Atre Ali Jannesari Felix Wolf Laboratory for Parallel Programming Technische Universität Darmstadt Darmstadt Germany RWTH Aachen University Aachen Germany

ISBN: (纸本)9781509021413

parallel design patterns have been developed to help programmers efficiently design and implement parallel applications. However, identifying a suitable parallel pattern for a specific code region in a sequential application is a difficult task. Transforming an application according to support structures applicable to these parallel patterns is also very challenging. In this paper, we present a novel approach to automatically find parallel patterns in the algorithm structure design space of sequential applications. In our approach, we classify code blocks in a region according to the appropriate supportstructure of the detected pattern. This classification eases the transformation of a sequential application into its parallel version. Weevaluated our approach on 17 applications from four different benchmark suites. Our method identified suitable algorithm structure patterns in the sequential applications. We confirmed our results by comparing them with the existing parallel versions of these applications. We also implemented the patterns we detected in cases in which parallel implementations were not available and achieved speedups of up to 14x.

关键词： Pipelines parallel processing Positron emission tomography Linear regression Algorithm design and analysis Benchmark testing Software

来源：评论

学校读者我要写书评

暂无评论

Scaling Score-P to the next level *

引用

Procedia Computer Science 2017年 108卷 2180-2189页

作者： Daniel Lorenz Christian Feld Laboratory for Parallel Programming Technische Universität Darmstadt Darmstadt Germany Jülich Supercomputing Centre Forschungszentrum Jülich GmbH Jülich Germany

As part of performance measurements with Score-P, a description of the system and the execution locations is recorded into the performance measurement reports. For large-scale measurements using a million or more processes, the global system description can consume all the available memory. While the information stored process-locally during measurement is small, the memory requirement becomes a bottleneck in the process of constructing a global representation of the whole system. To address this problem we implemented a new system description in Score-P that exploits regular structures of the system, and results, on homogeneous systems, in a system description of constant size. Furthermore, we present a parallel algorithm to create a global view from the process-local information. The scalable system description comes at the price that it is no longer possible to assign individual names to each system element, but only enumerate elements of the same type. We have successfully tested the new approach on the full JUQUEEN system with up to nearly two million processes.

关键词： Performance analysis data compression exascale computing

来源：评论

学校读者我要写书评

暂无评论

Automatic Instrumentation Refinement for Empirical Performance Modeling

Automatic Instrumentation Refinement for Empirical Performan...

引用

IEEE/ACM International Workshop on programming and Performance Visualization Tools (ProTools)

作者： Jan-Patrick Lehr Alexandru Calotoiu Christian Bischof Felix Wolf Institute for Scientific Computing Technische Universität Darmstadt Darmstadt Germany Laboratory for Parallel Programming Technische Universität Darmstadt Darmstadt Germany

ISBN: (纸本)9781728160276

The analysis of runtime performance is important during the development and throughout the life cycle of HPC applications. One important objective in performance analysis is to identify regions in the code that show significant runtime increase with larger problem sizes or more processes. One approach to identify such regions is to use empirical performance modeling, i.e., building performance models based on measurements. While the modeling itself has already been streamlined and automated, the generation of the required measurements is time consuming and tedious. In this paper, we propose an approach to automatically adjust the instrumentation to reduce overhead and focus the measurements to relevant regions, i.e.,such that show increasing runtime with larger input parameters or increasing number of MPI ranks. Our approach employs Extra-P to generate performance models, which it then uses to extrapolate runtime and, finally, decide which functions should be kept for measurement. Also, the analysis expands the instrumentation, by heuristically adding functions based on static source-code features. We evaluate our approach using benchmarks from SPEC CPU 2006, SU2, and parallel MILC. The evaluation shows that our approach can filter functions of little interest and generate profiles that contain mostly relevant regions. For example, the overhead for SU2 can be improved automatically from 200% to 11% compared to filtered Score-P measurements.

关键词： Instruments Runtime Mathematical model Analytical models Atmospheric measurements Particle measurements parallel processing

来源：评论

学校读者我要写书评

暂无评论

A new technique for data privatization in user-level threads and its use in parallel applications 10

A new technique for data privatization in user-level threads...

引用

25th Annual ACM Symposium on Applied Computing, SAC 2010

作者： Rodrigues, Eduardo R. Navaux, Philippe O. A. Panetta, Jairo Mendes, Celso L. Institute of Informatics Federal University of Rio Grande Do Sul - UFRGS Porto Alegre Brazil Center for Weather Forecasts and Climate Studies National Institute for Space Research - INPE Cachoeira Paulista Brazil Parallel Programming Laboratory University of Illinois at Urbana-Champaign - UIUC Urbana IL United States

ISBN: (纸本)9781605586380

User-level threads have been used to implement migratable MPI processes. This is a better strategy to implement load balancing mechanisms. That is because, in general, these threads are faster to create, manage and migrate than heavy processes and kernel threads. However, they present some issues concerning private data because they break the private address space that MPI programs typically assume. In this paper, we propose a new approach to privatize data in user-level threads. This approach is based on Thread Local Storage, which is used by kernel threads. We apply this technique to enable MPI processes based on user thread to execute a wider range of parallel programs. We show that this alternative has a more efficient context switch and lower migration cost than other approaches. © 2010 ACM.

关键词： Privatization

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：