Pub Date : 2012-11-10DOI: 10.1109/SC.Companion.2012.294
Mehmet Balman
High-bandwidth networks are poised to provide new opportunities in tackling large data challenges in today's scientific applications. However, increasing the bandwidth is not sufficient by itself; we need careful evaluation of future high-bandwidth networks from the applications' perspective. We have experimented with current state-of-the-art data movement tools, and realized that file-centric data transfer protocols do not perform well with managing the transfer of many small files in high-bandwidth networks, even when using parallel streams or concurrent transfers. We require enhancements in current middleware tools to take advantage of future networking frameworks. To improve performance and efficiency, we develop an experimental prototype, called MemzNet: Memory-mapped Zero-copy Network Channel, which uses a block-based data movement method in moving large scientific datasets. We have implemented MemzNet that takes the approach of aggregating files into blocks and providing dynamic data channel management. In this work, we present our initial results in 100Gbps network.
{"title":"Abstract: MemzNet: Memory-Mapped Zero-Copy Network Channel for Moving Large Datasets over 100Gbps Network","authors":"Mehmet Balman","doi":"10.1109/SC.Companion.2012.294","DOIUrl":"https://doi.org/10.1109/SC.Companion.2012.294","url":null,"abstract":"High-bandwidth networks are poised to provide new opportunities in tackling large data challenges in today's scientific applications. However, increasing the bandwidth is not sufficient by itself; we need careful evaluation of future high-bandwidth networks from the applications' perspective. We have experimented with current state-of-the-art data movement tools, and realized that file-centric data transfer protocols do not perform well with managing the transfer of many small files in high-bandwidth networks, even when using parallel streams or concurrent transfers. We require enhancements in current middleware tools to take advantage of future networking frameworks. To improve performance and efficiency, we develop an experimental prototype, called MemzNet: Memory-mapped Zero-copy Network Channel, which uses a block-based data movement method in moving large scientific datasets. We have implemented MemzNet that takes the approach of aggregating files into blocks and providing dynamic data channel management. In this work, we present our initial results in 100Gbps network.","PeriodicalId":6346,"journal":{"name":"2012 SC Companion: High Performance Computing, Networking Storage and Analysis","volume":"78 1","pages":"1511-1512"},"PeriodicalIF":0.0,"publicationDate":"2012-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78478286","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}
Pub Date : 2012-11-10DOI: 10.1109/SC.Companion.2012.132
D. Ghoshal, L. Ramakrishnan
Scientific applications are increasingly using cloud resources for their data analysis workflows. However, managing data effectively and efficiently over these cloud resources is challenging due to the myriad storage choices with different performance-cost trade-offs, complex application choices, complexity associated with elasticity and, failure rates. The explosion in scientific data coupled with unique characteristics of cloud environments require a more flexible and robust distributed data management solution than the ones currently in existence. This paper describes the design and implementation of FRIEDA - a Flexible Robust Intelligent Elastic Data Management framework. FRIEDA coordinates data in a transient cloud environment taking into account specific application characteristics. Additionally, we describe a range of data management strategies and show the benefit of flexible data management schemes in cloud environments. We study two distinct scientific applications from bioinformatics and image analysis to understand the effectiveness of such a framework.
{"title":"FRIEDA: Flexible Robust Intelligent Elastic Data Management in Cloud Environments","authors":"D. Ghoshal, L. Ramakrishnan","doi":"10.1109/SC.Companion.2012.132","DOIUrl":"https://doi.org/10.1109/SC.Companion.2012.132","url":null,"abstract":"Scientific applications are increasingly using cloud resources for their data analysis workflows. However, managing data effectively and efficiently over these cloud resources is challenging due to the myriad storage choices with different performance-cost trade-offs, complex application choices, complexity associated with elasticity and, failure rates. The explosion in scientific data coupled with unique characteristics of cloud environments require a more flexible and robust distributed data management solution than the ones currently in existence. This paper describes the design and implementation of FRIEDA - a Flexible Robust Intelligent Elastic Data Management framework. FRIEDA coordinates data in a transient cloud environment taking into account specific application characteristics. Additionally, we describe a range of data management strategies and show the benefit of flexible data management schemes in cloud environments. We study two distinct scientific applications from bioinformatics and image analysis to understand the effectiveness of such a framework.","PeriodicalId":6346,"journal":{"name":"2012 SC Companion: High Performance Computing, Networking Storage and Analysis","volume":"116 1","pages":"1096-1105"},"PeriodicalIF":0.0,"publicationDate":"2012-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79367490","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}
Pub Date : 2012-11-10DOI: 10.1109/SC.Companion.2012.283
R. Jacob, Jayesh Krishna, Xiabing Xu, S. Mickelson, T. Tautges, M. Wilde, R. Latham, Ian T Foster, R. Ross, M. Hereld, J. Larson, P. Bochev, K. Peterson, M. Taylor, K. Schuchardt, Jain Yin, D. Middleton, Mary Haley, David Brown, Wei Huang, D. Shea, R. Brownrigg, M. Vertenstein, K. Ma, Jingrong Xie
Climate models are both outputting larger and larger amounts of data and are doing it on more sophisticated numerical grids. The tools climate scientists have used to analyze climate output, an essential component of climate modeling, are single threaded and assume rectangular structured grids in their analysis algorithms. We are bringing both task- and data-parallelism to the analysis of climate model output. We have created a new data-parallel library, the Parallel Gridded Analysis Library (ParGAL) which can read in data using parallel I/O, store the data on a compete representation of the structured or unstructured mesh and perform sophisticated analysis on the data in parallel. ParGAL has been used to create a parallel version of a script-based analysis and visualization package. Finally, we have also taken current workflows and employed task-based parallelism to decrease the total execution time.
{"title":"Poster: Bringing Task and Data Parallelism to Analysis of Climate Model Output","authors":"R. Jacob, Jayesh Krishna, Xiabing Xu, S. Mickelson, T. Tautges, M. Wilde, R. Latham, Ian T Foster, R. Ross, M. Hereld, J. Larson, P. Bochev, K. Peterson, M. Taylor, K. Schuchardt, Jain Yin, D. Middleton, Mary Haley, David Brown, Wei Huang, D. Shea, R. Brownrigg, M. Vertenstein, K. Ma, Jingrong Xie","doi":"10.1109/SC.Companion.2012.283","DOIUrl":"https://doi.org/10.1109/SC.Companion.2012.283","url":null,"abstract":"Climate models are both outputting larger and larger amounts of data and are doing it on more sophisticated numerical grids. The tools climate scientists have used to analyze climate output, an essential component of climate modeling, are single threaded and assume rectangular structured grids in their analysis algorithms. We are bringing both task- and data-parallelism to the analysis of climate model output. We have created a new data-parallel library, the Parallel Gridded Analysis Library (ParGAL) which can read in data using parallel I/O, store the data on a compete representation of the structured or unstructured mesh and perform sophisticated analysis on the data in parallel. ParGAL has been used to create a parallel version of a script-based analysis and visualization package. Finally, we have also taken current workflows and employed task-based parallelism to decrease the total execution time.","PeriodicalId":6346,"journal":{"name":"2012 SC Companion: High Performance Computing, Networking Storage and Analysis","volume":"12 1","pages":"1495"},"PeriodicalIF":0.0,"publicationDate":"2012-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76674227","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}
Pub Date : 2012-11-10DOI: 10.1109/SC.Companion.2012.122
M. Ellsworth
This presentation provides a tutorial on ASHRAE thermal guidelines for both air and liquid cooling.
本报告提供了ASHRAE空气和液体冷却热指南的教程。
{"title":"New ASHRAE Thermal Guidelines for Air and Liquid Cooling","authors":"M. Ellsworth","doi":"10.1109/SC.Companion.2012.122","DOIUrl":"https://doi.org/10.1109/SC.Companion.2012.122","url":null,"abstract":"This presentation provides a tutorial on ASHRAE thermal guidelines for both air and liquid cooling.","PeriodicalId":6346,"journal":{"name":"2012 SC Companion: High Performance Computing, Networking Storage and Analysis","volume":"39 1","pages":"942-961"},"PeriodicalIF":0.0,"publicationDate":"2012-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73600053","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}
Pub Date : 2012-11-10DOI: 10.1109/SC.Companion.2012.17
David Goodell, S. Kim, R. Latham, M. Kandemir, R. Ross
High-performance computing (HPC) storage systems typically consist of an object storage system that is accessed via the POSIX file interface. However, rapid increases in system scales and storage system complexity have uncovered a number of limitations in this model. In particular, applications and libraries are limited in their ability to partition data into units with independent concurrency control, and mapping complex science data models into the POSIX file model is inconvenient at best. In this paper we propose an alternative interface for use by applications and libraries that provides direct access to underlying storage objects. This model allows applications and libraries to organize storage access around these objects in order to avoid lock contention without needing to create many separate files. Additionally, complex data models are more readily organized into multiple object data streams, simplifying the storage of variable-length data and allowing a choice of degree of parallelism related to access needs. Our approach provides for datasets stored in this new model to coexist with POSIX files, allowing evolution to the new model over time. We apply these concepts in the PVFS, PLFS, and Parallel netCDF packages to prototype the model and describe our experiences.
{"title":"An Evolutionary Path to Object Storage Access","authors":"David Goodell, S. Kim, R. Latham, M. Kandemir, R. Ross","doi":"10.1109/SC.Companion.2012.17","DOIUrl":"https://doi.org/10.1109/SC.Companion.2012.17","url":null,"abstract":"High-performance computing (HPC) storage systems typically consist of an object storage system that is accessed via the POSIX file interface. However, rapid increases in system scales and storage system complexity have uncovered a number of limitations in this model. In particular, applications and libraries are limited in their ability to partition data into units with independent concurrency control, and mapping complex science data models into the POSIX file model is inconvenient at best. In this paper we propose an alternative interface for use by applications and libraries that provides direct access to underlying storage objects. This model allows applications and libraries to organize storage access around these objects in order to avoid lock contention without needing to create many separate files. Additionally, complex data models are more readily organized into multiple object data streams, simplifying the storage of variable-length data and allowing a choice of degree of parallelism related to access needs. Our approach provides for datasets stored in this new model to coexist with POSIX files, allowing evolution to the new model over time. We apply these concepts in the PVFS, PLFS, and Parallel netCDF packages to prototype the model and describe our experiences.","PeriodicalId":6346,"journal":{"name":"2012 SC Companion: High Performance Computing, Networking Storage and Analysis","volume":"108 1","pages":"36-41"},"PeriodicalIF":0.0,"publicationDate":"2012-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74661813","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}
Pub Date : 2012-11-10DOI: 10.1109/SC.Companion.2012.365
P. Baumann
Summary form only given. The paper presents the Array Databases using the example of rasdaman, a fully implemented system in operational service since years. We introduce an array query language which embeds seamlessly into standard SQL and show how this language can be supported by a streamlined architecture which allows for effective storage and query optimization and parallelization. In this context we emphasize that Array Database research can gain a lot from combining the knowledge of database, supercomputing, and programming language domains.
{"title":"Array Databases","authors":"P. Baumann","doi":"10.1109/SC.Companion.2012.365","DOIUrl":"https://doi.org/10.1109/SC.Companion.2012.365","url":null,"abstract":"Summary form only given. The paper presents the Array Databases using the example of rasdaman, a fully implemented system in operational service since years. We introduce an array query language which embeds seamlessly into standard SQL and show how this language can be supported by a streamlined architecture which allows for effective storage and query optimization and parallelization. In this context we emphasize that Array Database research can gain a lot from combining the knowledge of database, supercomputing, and programming language domains.","PeriodicalId":6346,"journal":{"name":"2012 SC Companion: High Performance Computing, Networking Storage and Analysis","volume":"28 1","pages":"1329-1329"},"PeriodicalIF":0.0,"publicationDate":"2012-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74073467","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}
Pub Date : 2012-11-10DOI: 10.1109/SC.Companion.2012.149
Joseph Jupin, Justin Y. Shi, Z. Obradovic
For health and human services, fraud detection and other security services, identity resolution is a core requirement for understanding big data in the cloud. Due to the lack of a globally unique identifier and captured typographic differences for the same identity, identity resolution has high spatial and temporal complexities. We propose a filter and verify method to substantially increase the speed of approximate string matching using edit distance. This method has been found to be almost 80 times faster (130 times when combined with other optimizations) than Damerau-Levenshtein edit distance and preserves all approximate matches. Our method creates compressed signatures for data fields and uses Boolean operations and an enhanced bit counter to quickly compare the distance between the fields. This method is intended to be applied to data records whose fields contain relatively short-length strings, such as those found in most demographic data. Without loss of accuracy, the proposed Fast Bitwise Filter will provide substantial performance gain to approximate string comparison in database, record linkage and deduplication data processing systems.
{"title":"Understanding Cloud Data Using Approximate String Matching and Edit Distance","authors":"Joseph Jupin, Justin Y. Shi, Z. Obradovic","doi":"10.1109/SC.Companion.2012.149","DOIUrl":"https://doi.org/10.1109/SC.Companion.2012.149","url":null,"abstract":"For health and human services, fraud detection and other security services, identity resolution is a core requirement for understanding big data in the cloud. Due to the lack of a globally unique identifier and captured typographic differences for the same identity, identity resolution has high spatial and temporal complexities. We propose a filter and verify method to substantially increase the speed of approximate string matching using edit distance. This method has been found to be almost 80 times faster (130 times when combined with other optimizations) than Damerau-Levenshtein edit distance and preserves all approximate matches. Our method creates compressed signatures for data fields and uses Boolean operations and an enhanced bit counter to quickly compare the distance between the fields. This method is intended to be applied to data records whose fields contain relatively short-length strings, such as those found in most demographic data. Without loss of accuracy, the proposed Fast Bitwise Filter will provide substantial performance gain to approximate string comparison in database, record linkage and deduplication data processing systems.","PeriodicalId":6346,"journal":{"name":"2012 SC Companion: High Performance Computing, Networking Storage and Analysis","volume":"59 1","pages":"1234-1243"},"PeriodicalIF":0.0,"publicationDate":"2012-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73140971","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}
Pub Date : 2012-11-10DOI: 10.1109/SC.Companion.2012.338
Jordi Ros-Giralt, Péter Szilágyi, R. Lethin
This paper addresses the problem of scalable cyber-security using a cloud computing architecture. Scalability is treated in two contexts: (1) performance and power efficiency and (2) degree of cyber security-relevant information detected by the cyber-security cloud (CSC). We provide a framework to construct CSCs, which derives from a set of fundamental building blocks (forwarders, analyzers and grounds) and the identification of the smallest functional units (atomic CSC cells or simply aCS C cells) capable of embedding the full functionality of the cyber-security cloud. aCSC cells are then studied and several high-performance algorithms are presented to optimize the system's performance and power efficiency. Among these, a new queuing policy - called tail early detection (TED) - is introduced to proactively drop packets in a way that the degree of detected information is maximized while saving power by avoiding spending cycles on less relevant traffic components. We also show that it is possible to use aCSC cells as core building blocks to construct arbitrarily large cyber-security clouds by structuring the cells using a hierarchical architecture. To demonstrate the utility of our framework, we implement one cyber-security "mini-cloud" on a single chip prototype based on the Tilera's TILEPro64 processor demonstrating performance of up to 10Gbps.
{"title":"Scalable Cyber-Security for Terabit Cloud Computing","authors":"Jordi Ros-Giralt, Péter Szilágyi, R. Lethin","doi":"10.1109/SC.Companion.2012.338","DOIUrl":"https://doi.org/10.1109/SC.Companion.2012.338","url":null,"abstract":"This paper addresses the problem of scalable cyber-security using a cloud computing architecture. Scalability is treated in two contexts: (1) performance and power efficiency and (2) degree of cyber security-relevant information detected by the cyber-security cloud (CSC). We provide a framework to construct CSCs, which derives from a set of fundamental building blocks (forwarders, analyzers and grounds) and the identification of the smallest functional units (atomic CSC cells or simply aCS C cells) capable of embedding the full functionality of the cyber-security cloud. aCSC cells are then studied and several high-performance algorithms are presented to optimize the system's performance and power efficiency. Among these, a new queuing policy - called tail early detection (TED) - is introduced to proactively drop packets in a way that the degree of detected information is maximized while saving power by avoiding spending cycles on less relevant traffic components. We also show that it is possible to use aCSC cells as core building blocks to construct arbitrarily large cyber-security clouds by structuring the cells using a hierarchical architecture. To demonstrate the utility of our framework, we implement one cyber-security \"mini-cloud\" on a single chip prototype based on the Tilera's TILEPro64 processor demonstrating performance of up to 10Gbps.","PeriodicalId":6346,"journal":{"name":"2012 SC Companion: High Performance Computing, Networking Storage and Analysis","volume":"1 1","pages":"1607-1616"},"PeriodicalIF":0.0,"publicationDate":"2012-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76311938","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}
Pub Date : 2012-11-10DOI: 10.1109/SC.Companion.2012.309
J. Booth
The ordering of a matrix vastly impact the convergence rate of precondition conjugate gradient method. Past ordering methods focus solely on a graph representation of the sparse matrix and do not give an inside into the convergence rate that is linked to the preconditioned eigenspectrum. This work attempt to investigate how numerical based ordering may produce a better preconditioned system in terms of faster convergence.
{"title":"Poster: Numeric Based Ordering for Preconditioned Conjugate Gradient","authors":"J. Booth","doi":"10.1109/SC.Companion.2012.309","DOIUrl":"https://doi.org/10.1109/SC.Companion.2012.309","url":null,"abstract":"The ordering of a matrix vastly impact the convergence rate of precondition conjugate gradient method. Past ordering methods focus solely on a graph representation of the sparse matrix and do not give an inside into the convergence rate that is linked to the preconditioned eigenspectrum. This work attempt to investigate how numerical based ordering may produce a better preconditioned system in terms of faster convergence.","PeriodicalId":6346,"journal":{"name":"2012 SC Companion: High Performance Computing, Networking Storage and Analysis","volume":"91 1","pages":"1534-1534"},"PeriodicalIF":0.0,"publicationDate":"2012-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79963520","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}
Pub Date : 2012-11-10DOI: 10.1109/SC.Companion.2012.146
Minoru Oikawa, A. Kawai, K. Nomura, K. Yasuoka, Kazuyuki Yoshikawa, T. Narumi
GPGPU (General-purpose computing on graphics processing units) has several difficulties when used in cloud environment, such as narrow bandwidth, higher cost, and lower security, compared with computation using only CPUs. Most high performance computing applications require huge communication between nodes, and do not fit a cloud environment, since network topology and its bandwidth are not fixed and they affect the performance of the application program. However, there are some applications for which little communication is needed, such as molecular dynamics (MD) simulation with the replica exchange method (REM). For such applications, we propose DS-CUDA (Distributed-shared compute unified device architecture), a middleware to use many GPUs in a cloud environment with lower cost and higher security. It virtualizes GPUs in a cloud such that they appear to be locally installed GPUs in a client machine. Its redundant mechanism ensures reliable calculation with consumer GPUs, which reduce the cost greatly. It also enhances the security level since no data except command and data for GPUs are stored in the cloud side. REM-MD simulation with 64 GPUs showed 58 and 36 times more speed than a locally-installed GPU via InfiniBand and the Internet, respectively.
{"title":"DS-CUDA: A Middleware to Use Many GPUs in the Cloud Environment","authors":"Minoru Oikawa, A. Kawai, K. Nomura, K. Yasuoka, Kazuyuki Yoshikawa, T. Narumi","doi":"10.1109/SC.Companion.2012.146","DOIUrl":"https://doi.org/10.1109/SC.Companion.2012.146","url":null,"abstract":"GPGPU (General-purpose computing on graphics processing units) has several difficulties when used in cloud environment, such as narrow bandwidth, higher cost, and lower security, compared with computation using only CPUs. Most high performance computing applications require huge communication between nodes, and do not fit a cloud environment, since network topology and its bandwidth are not fixed and they affect the performance of the application program. However, there are some applications for which little communication is needed, such as molecular dynamics (MD) simulation with the replica exchange method (REM). For such applications, we propose DS-CUDA (Distributed-shared compute unified device architecture), a middleware to use many GPUs in a cloud environment with lower cost and higher security. It virtualizes GPUs in a cloud such that they appear to be locally installed GPUs in a client machine. Its redundant mechanism ensures reliable calculation with consumer GPUs, which reduce the cost greatly. It also enhances the security level since no data except command and data for GPUs are stored in the cloud side. REM-MD simulation with 64 GPUs showed 58 and 36 times more speed than a locally-installed GPU via InfiniBand and the Internet, respectively.","PeriodicalId":6346,"journal":{"name":"2012 SC Companion: High Performance Computing, Networking Storage and Analysis","volume":"132 1","pages":"1207-1214"},"PeriodicalIF":0.0,"publicationDate":"2012-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80011066","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：