15,048 Hits in 3.7 sec

Experiences of Converging Big Data Analytics Frameworks with High Performance Computing Systems [chapter]

Peng Cheng, Yutong Lu, Yunfei Du, Zhiguang Chen
2018 Lecture Notes in Computer Science  
However, due to the different workload characteristics and optimization objectives of system architectures, migrating data-intensive applications to HPC systems that are geared for traditional compute-intensive  ...  Based on our characterization and findings of the performance behaviors, we propose shared map output shuffle strategy and file metadata cache layer to alleviate the impact of metadata bottleneck.  ...  Experiment and Analysis To explore an efficient way of accelerating complex applications on HPC systems and analyze the performance impact of different architecture between big data analytics and HPC,  ... 
doi:10.1007/978-3-319-69953-0_6 fatcat:t33sqtffwnbzjbutvjll5hnspe

A Compiler-in-the-Loop framework to explore Horizontally Partitioned Cache architectures

Aviral Shrivastavat, Ilya Issenin, Nikil Dutt
2008 2008 Asia and South Pacific Design Automation Conference  
However, the energy reduction obtained using HPC architectures is very sensitive to the HPC parameters.  ...  Therefore it is very important to explore the HPC design space and carefully choose the HPC parameters that result in minimum energy consumption for the application.  ...  However other than achieving energy reduction just due to performance improvements, HPC architectures reduce energy due to the lower energy per access to the smaller cache.  ... 
doi:10.1109/aspdac.2008.4483968 dblp:conf/aspdac/ShrivastavaID08 fatcat:2ridn5vg6jgxbbyo6hr2st5rcy

FOSquare: A Novel Optical HPC Interconnect Network Architecture Based on Fast Optical Switches with Distributed Optical Flow Control

Fulong Yan, Changshun Yuan, Chao Li, Xiong Deng
2021 Photonics  
We numerically investigate and compare the network performance of FOSquare with Leaf-Spine under real traffic traces collected by running multiple applications (CG, MG, MILC, and MINI_MD) in an HPC infrastructure  ...  We also present an Optimized Mapping (OPM) algorithm that maps the most communication-related processes inside a rack.  ...  The latency performance of the FOSquare is numerically investigated by analyzing real HPC application traces under the specific mapping mechanism.  ... 
doi:10.3390/photonics8010011 fatcat:qsnmqzucuvca5kjwkupij2mpdq

Big Data at HPC Wales [article]

Sidharth N. Kashyap, Ade J. Fewings, Jay Davies, Ian Morris, Andrew Thomas Thomas Green, Martyn F. Guest
2015 arXiv   pre-print
This coupling of environments creates a platform for applications to utilize the native HPC solutions along with the Big Data Frameworks.  ...  This paper describes an automated approach to handling Big Data workloads on HPC systems.  ...  The container-based architecture provides the opportunity to execute generic commands and not constrain us to Map Reduce.  Lustre File System [20]: We chose to use the Lustre Parallel file systems as  ... 
arXiv:1506.08907v1 fatcat:d3sna2txtbcnlnyktedkknpyxe

HPMMAP: Lightweight Memory Management for Commodity Operating Systems

Brian Kocoloski, John Lange
2014 2014 IEEE 28th International Parallel and Distributed Processing Symposium  
In contrast to Linux, there is a substantial history of work in the HPC community focused on lightweight OS/R architectures that provide scalable and consistent performance for tightly coupled HPC applications  ...  Our system HPMMAP provides isolated and low overhead memory performance transparently to HPC applications by bypassing Linux's memory management layer.  ...  HPMMAP is optimized to support HPC application performance.  ... 
doi:10.1109/ipdps.2014.73 dblp:conf/ipps/KocoloskiL14 fatcat:ajau6scuxrgjpiux7ng2vh524y

A Study of Software Development for High Performance Computing [chapter]

Manish Parashar, Salim Hariri, Tomasz Haupt, Geoffrey Fox
1994 Programming Environments for Massively Parallel Distributed Systems  
Software development in a High Performance Computing (HPC) environment is non-trivial and requires a thorough understanding of the application and the architecture.  ...  The objective of this paper is to study the software development process in a high performance computing environment and to outline the stages typically encountered in this process.  ...  Introduction Software development in any High Performance (Parallel/Distributed) Computing (HPC) environment is a non-trivial process and requires a thorough understanding of the application and the architecture  ... 
doi:10.1007/978-3-0348-8534-8_11 fatcat:cbor542bojhnpkkfoblc5qvf4i

Mitigating soft error failures for multimedia applications by selective data protection

Kyoungwoo Lee, Aviral Shrivastava, Ilya Issenin, Nikil Dutt, Nalini Venkatasubramanian
2006 Proceedings of the 2006 international conference on Compilers, architecture and synthesis for embedded systems - CASES '06  
Since multimedia applications are increasingly being used in mission-critical embedded systems where both reliability and energy are a major concern, there is a definite need to improve reliability in  ...  Experimental results demonstrate that our selective data protection can achieve the failure rate close to that of a soft error protected cache system, while retaining the performance and energy consumption  ...  Similar to existing HPC architectures, the memory is divided into pages, and each page has a Cache Mapping Attribute or CMA. The CMA defines which cache the page is mapped to.  ... 
doi:10.1145/1176760.1176810 dblp:conf/cases/LeeSIDV06 fatcat:ji7r6isurbeozamagg3lqcj3ee

Compiler-in-the-Loop Design Space Exploration Framework for Energy Reduction in Horizontally Partitioned Cache Architectures

A. Shrivastava, I. Issenin, N. Dutt, Sanghyun Park, Yunheung Paek
2009 IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems  
Consequently, most previous research has focused on exploiting HPCs to improve performance and achieve energy reduction only as a byproduct of performance improvement.  ...  HPCs help reduce cache pollution and thereby improve performance.  ...  Thus, an HPC is a simple, yet powerful architectural feature to improve performance. Consequently, most existing approaches for partitioning data between the HPCs aim at improving performance.  ... 
doi:10.1109/tcad.2009.2013275 fatcat:447v2tzwxncefiuzikxukeunfu

Ecoscale: Reconfigurable Computing And Runtime System For Future Exascale Systems

Iakovos Mavroidis, Ioannis Papaefstathiou, Luciano Lavagno, Dimitrios Nikolopoulos, Dirk Koch, John Goodacre, Ioannis Sourdis, Vassilis Papaefstathiou, Marcello Coppola, Manuel Palomino
2016 Zenodo  
In order to reach exascale performance, current HPC systems need to be improved.  ...  Apart from improvements in implementation technology, what is needed is to refine the HPC application development flow as well as the system architecture of future HPC systems.  ...  HPC Application Characteristics The ECOSCALE architecture is tailored to the characteristics and trends of future HPC applications to efficiently scale to exaflop performance.  ... 
doi:10.5281/zenodo.34893 fatcat:ocwfndo4vjei3hqucmndj22xu4

Rethinking High Performance Computing System Architecture for Scientific Big Data Applications

Yong Chen, Chao Chen, Yanlong Yin, Xian-He Sun, Rajeev Thakur, William Gropp
2016 2016 IEEE Trustcom/BigDataSE/ISPA  
big data applications can be mapped to such a decoupled For example, the Global Cloud Resolving Model (GCRM) HPC system architecture and are executed in a decoupled project, part of Department  ...  Performance tools can system architecture is to change the conventional architecture provide information and guidance to understand application to handle these two phases differently on different nodes  ... 
doi:10.1109/trustcom.2016.0248 dblp:conf/trustcom/ChenCYSTG16 fatcat:ci6xudtd4jaerm6zum2ezvrh5a

Preparing for the Future – Rethinking Proxy Apps [article]

Satoshi Matsuoka, Jens Domke, Mohamed Wahib, Aleksandr Drozd, Ray Bair, Andrew A. Chien, Jeffrey S. Vetter, John Shalf
2022 arXiv   pre-print
A considerable amount of research and engineering went into designing proxy applications, which represent common high-performance computing workloads, to co-design and evaluate the current generation of  ...  Unfortunately, proxy applications force HPC centers and providers (vendors) into a an undesirable state of rigidity, in contrast to the fast-moving trends of current technology and future heterogeneity  ...  The main point for the HPCS program was to provide benchmarks that bound the performance of many real applications as a function of memory access characteristics and then use a correlation matrix to map  ... 
arXiv:2204.07336v1 fatcat:r7pmvluvtngfnkii7fq56o6n5y

Exploring the Design Space of Combining Linux with Lightweight Kernels for Extreme Scale Computing

Balazs Gerofi, Masamichi Takagi, Yutaka Ishikawa, Rolf Riesen, Evan Powers, Robert W. Wisniewski
2015 Proceedings of the 5th International Workshop on Runtime and Operating Systems for Supercomputers - ROSS '15  
HPC Node OS Architecture • Traditionally: driven by the need for scalable, consistent performance for bulk-synchronous HPC Linux FileSys Drivers Dev.  ...  ) • User-space virtual to physical mappings are set up to be the same in Linux so that the proxy process can access syscall arguments • A pseudo file mapping in mcexec (proxy process) covers the entire  ...  Conclusion • Need for enhanced system software to meet HW and SW requirements of exascale and beyond • Hybrid Linux+LWK approach proposed to provide LWK performance but to retain Linux APIs at the same  ... 
doi:10.1145/2768405.2768410 dblp:conf/hpdc/GerofiTIRPW15 fatcat:hfnq6tembzfqfo3asyjjgqhc7e

Workflow optimization of performance and quality of service for bioinformatics application in high performance computing

Rashid Al-Ali, Nagarajan Kathiresan, Mohammed El Anbari, Eric R. Schendel, Tariq Abu Zaid
2016 Journal of Computational Science  
Accordingly, our proposed optimization workflow will advise the end user of a selection criteria to apply toward resources and options for a given application and HPC system architecture.  ...  Nowadays, High Performance Computing (HPC) systems commonly used in bioinformatics, such as genome sequencing, incorporate multi-processor architectures.  ...  application.  ... 
doi:10.1016/j.jocs.2016.03.005 fatcat:5ujoe3km3fenplo3gzqirqyggu

D7.2: Report on systems compliant with user requirements

G. Erbacci, C. Cavazzoni
2008 Zenodo  
Finally, an initial match of the main applications analysed to the HPC architectural classes is attempted and some considerations and remarks are presented.  ...  Deliverable D7.2 is organised into three main sections: first, the user requirements, coming from the applications, are analysed in terms of architecture specifications, trying to identify the ideal architectural  ...  Finally, in Section 4, a mapping of the key applications analysed in Section 2 to HPC architectural classes is attempted.  ... 
doi:10.5281/zenodo.6546118 fatcat:hmgi2fvjrfdm7okspmuhjf5i24

Unique Sense: Smart Computing Prototype

S. Vijaykumar, S.G. Saravanakumar, M. Balamurugan
2015 Procedia Computer Science  
In addition it achieves low cost architecture and eco-friendly to meet all the levels of peoples needs.  ...  This smart computing prototype is the light weight compact architecture which is designed to satisfy all the needs of this society.  ...  G. are Grateful to Research, Technical and Advisor members of 6 th SENSE Research Foundation, Tamilnadu, South India. Url :  ... 
doi:10.1016/j.procs.2015.04.056 fatcat:fb6po5vws5hb7fd3rfbnmwnp54
« Previous Showing results 1 — 15 out of 15,048 results