检索结果-内蒙古大学图书馆

JOURNAL OF INFORMATION SCIENCE AND ENGINEERING 2017年第5期33卷 1359-1374页

作者： Jabarov, Elkhan Park, Myong-Soon On, Byung-Won Choi, Gyu Sang Korea Univ Dept Comp & Radio Commun Engn Seoul 02841 South Korea Kunsan Natl Univ Dept Stat & Comp Sci Gunsan 54150 South Korea Yeungnam Univ Dept Informat & Commun Engn Gyeongbuk 38541 South Korea

Phase change memory (PCM) is a byte-addressable type of non-volatile memory. Compared to other volatile and non-volatile memories, PCM is two to four times denser than dynamic random access memory (DRAM). It has better read latency than NAND flash memory. Even though the write endurance of PCM is 10 times better than NAND flash memory, it is still limited to 106 times per PCM cell. Decreasing and balancing the number of writes among PCM cells can solve the endurance problem and, where possible, keep PCM cells usable. Our objective is to design a PCR*-tree a novel PCM-aware R*-tree that can store spatial data. Initially, we examine how R*-tree causes endurance problems in PCM, and then, we optimize it for PCM. Furthermore, the performance of R*-tree is very poor, especially for insertion, which needs to be solved since it will be used for in-memory databases. According to our experimental results, when the benchmark dataset is used, PCR*-tree dramatically reduced the number of write operations to PCM in average 30 times and also improve the performance in terms of processing time. These results suggest our new method outperforms existing ones for the PCM endurance problem, as well as in its performance.

关键词： PCM R*-tree R-tree in-memory databases spatial tree endurance

来源：评论

学校读者我要写书评

暂无评论

Balancing Performance and Energy for Lightweight Data Compression Algorithms 1

引用

21st European Conference on Advances in databases and Information Systems (ADBIS)

作者： Ungethum, Annett Damme, Patrick Pietrzyk, Johannes Krause, Alexander Habich, Dirk Lehner, Wolfgang Tech Univ Dresden Database Syst Grp Dresden Germany

ISBN: (数字)9783319671628

ISBN: (纸本)9783319671628;9783319671611

Energy consumption becomes more and more a critical design factor, whereby performance is still an important requirement. Thus, a balance between performance and energy has to be established. To tackle that issue for database systems, we proposed the concept of work-energy profiles. However, generating such profiles requires extensive benchmarking. To overcome that, we propose to approximate work-energy-profiles for complex operations based on the profiles of low-level operations in this paper. To show the feasibility of our approach, we use lightweight data compression algorithms as complex operations, since compression as well as decompression are heavily used in in-memory database systems, where data is always managed in a compressed representation. Furthermore, we evaluate our approach on a concrete hardware system.

关键词： Energy efficiency in-memory databases Compression

来源：评论

学校读者我要写书评

暂无评论

Advancing Dynamic Evolutionary Optimization Using In-memory Database Technology 20th

Advancing Dynamic Evolutionary Optimization Using In-Memory ...

引用

20th European Conference on the Applications of Evolutionary Computation (EvoApplications)

作者： Jordan, Julia Cheng, Wei Scheuermann, Bernd Univ Appl Sci Hsch Karlsruhe Karlsruhe Germany CAS Software AG Karlsruhe Germany SAP Innovat Ctr Network Potsdam Germany

ISBN: (纸本)9783319557922;9783319557915

This paper reports on IMDEA (In-memory database Dynamic Evolutionary Algorithm), an approach to dynamic evolutionary optimization exploiting in-memory database (IMDB) technology to expedite the search process subject to change events arising at runtime. The implemented system benefits from optimization knowledge persisted on an IMDB serving as associative memory to better guide the optimizer through changing environments. For this, specific strategies for knowledge processing, extraction and injection are developed and evaluated. Moreover, prediction methods are embedded and empirical studies outline to which extent these methods are able to anticipate forthcoming dynamic change events by evaluating historical records of previous changes and other optimization knowledge managed by the IMDB.

关键词： Dynamic evolutionary algorithm Associative memory Prediction in-memory databases

来源：评论

学校读者我要写书评

暂无评论

ACTiCLOUD: Enabling the Next Generation of Cloud Applications 37

ACTiCLOUD: Enabling the Next Generation of Cloud Application...

引用

37th IEEE International Conference on Distributed Computing Systems (ICDCS)

作者： Goumas, Georgios Nikas, Konstantinos Lakew, Ewnetu Bayuh Kotselidis, Christos Attwood, Andrew Elmroth, Erik Flouris, Michail Foutris, Nikos Goodacre, John Grohmann, Davide Karakostas, Vasileios Koutsourakis, Panagiotis Kersten, Martin Lujan, Mikel Rustad, Einar Thomson, John Tomas, Luis Vesterkjaer, Atle Webber, Jim Zhang, Ying Koziris, Nectarios Natl Tech Univ Athens ICCS Athens Greece Numascale Oslo Norway Kaleao Cambridge England OnApp London England Univ Manchester Manchester Lancs England MonetDB Solut Amsterdam Netherlands Neo Technol San Mateo CA USA Umea Univ Dept Comp Sci Umea Sweden Red Hat Raleigh NC USA

ISBN: (纸本)9781538617915

Despite their proliferation as a dominant computing paradigm, cloud computing systems lack effective mechanisms to manage their vast amounts of resources efficiently. Resources are stranded and fragmented, ultimately limiting cloud systems' applicability to large classes of critical applications that pose non-moderate resource demands. Eliminating current technological barriers of actual fluidity and scalability of cloud resources is essential to strengthen cloud computing's role as a critical cornerstone for the digital economy. ACTiCLOUD proposes a novel cloud architecture that breaks the existing scale-up and share-nothing barriers and enables the holistic management of physical resources both at the local cloud site and at distributed levels. Specifically, it makes advancements in the cloud resource management stacks by extending state-of-the-art hypervisor technology beyond the physical server boundary and localized cloud management system to provide a holistic resource management within a rack, within a site, and across distributed cloud sites. On top of this, ACTiCLOUD will adapt and optimize system libraries and runtimes (e.g., JVM) as well as ACTiCLOUD-native applications, which are extremely demanding, and critical classes of applications that currently face severe difficulties in matching their resource requirements to state-of-the-art cloud offerings.

关键词： cloud computing resource management in-memory databases resource disaggregation scale-up rackscale hypervisor

来源：评论

学校读者我要写书评

暂无评论

PaMeCo join: A parallel main memory compact hash join

引用

INFORMATION SYSTEMS 2016年 58卷 105-125页

作者： Begley, Steven He, Zhen Chen, Yi-Ping Phoebe La Trobe Univ Dept Comp Sci & Informat Technol Bundoora Vic 3086 Australia

This paper presents a memory-constrained hash join algorithm (PaMeCo Join) designed to operate with main-memory column-store database systems. Whilst RAM has become more affordable and the popularity of main-memory database systems continues to grow, we recognize that RAM is a finite resource and that database systems rarely have an excess of memory available to them. Therefore, we design PaMeCo to operate within an arbitrary memory limitation by processing the input relations by parts, and by using a compact hash table that represents the contained tuples in a compact format. Coupled with a radix-clustering system that lowers memory latencies, we find that PaMeCo can offer competitive performance levels to other contemporary hash join algorithms in an unconstrained environment, while being up to three times faster than a high-performing hash join when memory constraints are applied. (C) 2015 Elsevier Ltd. All rights reserved.

关键词： in-memory databases Hash join memory constrained OLAP Column store

来源：评论

学校读者我要写书评

暂无评论

Comparing Tabular And Multidimensional Model In A Real BI Solution

引用

IEEE LATIN AMERICA TRANSACTIONS 2016年第7期14卷 3393-3399页

作者： Simon, A. Torres, M. Garcia, L. Simon, A. Ravelo, R. Grp Empresarial CIMEX Havana Cuba Univ La Habana Havana Cuba Univ Tecnol La Habana Jose Antonio Echeverria CUJAE Havana Cuba

The increase of accumulated data amount in organizations have provoked the emergence of new requirements of more complex and efficient analysis tools, context in which the Business Intelligence spring up as a discipline for boarding this problem. The improvement of the efficiency in the storage and access to analytical databases has been reported in many researches, upon which results several companies have introduced commercial products. Microsoft SQL Server 2012 offers two independent alternatives for creating analytical models, the classic multidimensional model and the more recent tabular model. In this paper was carried a comparative analysis of both models out looking deeply into their features and potentialities. Several important considerations for undertaking a new BI project based on Microsoft platform are suggested. A BI solution that provides particular and integrated visions of the business status of CIMEX Co. was developed as real context to perform the comparative analysis. In order to testing the proposed solution and identifying the strengths and weaknesses of each model in different scenarios some experiments were performed.

关键词： Business Intelligence Multidimensional Model Tabular Model Columnar databases in-memory databases

来源：评论

学校读者我要写书评

暂无评论

ParTime: Parallel Temporal Aggregation 16

ParTime: Parallel Temporal Aggregation

引用

ACM SIGMOD International Conference on Management of Data

作者： Pilman, Markus Kaufmann, Martin Kohl, Florian Kossmann, Donald Profeta, Damien Swiss Fed Inst Technol Syst Grp Zurich Switzerland Microsoft Res Redmond WA USA Amadeus Grp Sophia Antipolis France

ISBN: (纸本)9781450335317

This paper presents ParTime, a parallel algorithm for temporal aggregation. Temporal aggregation is one of the most important, yet most complex temporal query operators. It has been extensively studied in the past, but so far there has only been one attempt to parallelize this operator. ParTime supports data parallelism and has a number of additional advantages: It supports the full bitemporal data model, it requires no a-priori indexing, it supports shared computation, and it runs well on modern hardware (i.e., NUMA machines with large main memories). We implemented ParTime in a parallel database system and carried out comprehensive performance experiments with areal workload from the airline industry and a synthetic benchmark, the TPC-BiH benchmark. The results show that ParTime significantly outperforms any other available temporal database system. Furthermore, the results show that ParTime is competitive as compared to the Timeline Index, the best known technique to process temporal queries from the research literature and which is based on pre-computation and indexing.

关键词： in-memory databases temporal query processing temporal data shared scans query processing

来源：评论

学校读者我要写书评

暂无评论

Footprint Reduction and Uniqueness Enforcement with Hash Indices in SAP HANA 27th

Footprint Reduction and Uniqueness Enforcement with Hash Ind...

引用

1st International Workshop on Consistency and Inconsistency (COIN) at 27th International Conference on Database and Expert Systems Applications (DEXA)

作者： Faust, Martin Boissier, Martin Keller, Marvin Schwalb, David Bischoff, Holger Eisenreich, Katrin Faerber, Franz Plattner, Hasso Hasso Plattner Inst Potsdam Germany SAP SE Walldorf Germany

ISBN: (纸本)9783319444062;9783319444055

databases commonly use multi-column indices for composite keys that concatenate attribute values for fast entity retrieval. For real-world applications, such concatenated composite keys contribute significantly to the overall space consumption, which is particularly expensive for main memory-resident databases. We present an integer-based hash representation of the actual values for the purpose of reducing the overall memory footprint of a system while maintaining the level of performance. We analyzed the performance impact as well as the memory footprint reduction of hash-based indices in SAP HANA in a real-world enterprise database setting. For a live production SAP ERP system, the introduction of hash-based primary key indices alone reduces the entire memory footprint by 10% with comparable performance.

关键词： in-memory databases Hash indices Footprint reduction Enterprise systems

来源：评论

学校读者我要写书评

暂无评论

NUMA-Aware Scalable and Efficient In-memory Aggregation on Large Domains

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2015年第4期27卷 1071-1084页

作者： Wang, Li Zhou, Minqi Zhang, Zhenjie Shan, Ming-Chien Zhou, Aoying E China Normal Univ Software Engn Inst Shanghai 200062 Peoples R China Illinois Singapore Pte Ltd Adv Digital Sci Ctr Singapore Singapore SAP Res Palo Alto CA USA

Business Intelligence (BI) is recognized as one of the most important IT applications in the coming big data era. In recent years, non-uniform memory access (NUMA) has become the de-facto architecture of multiprocessors on the new generation of enterprise servers. Such new architecture brings new challenges to optimization techniques on traditional operators in BI. Aggregation, for example, is one of the basic building blocks of BI, while its processing performance with existing hash-based algorithms scales poorly in terms of the number of cores under NUMA architecture. In this paper, we provide new solutions to tackle the problem of parallel hash-based aggregation, especially targeting at domains of extremely large cardinality. We propose a NUMA-aware radix partitioning (NaRP) method which divides the original huge relation table into subsets, without invoking expensive remote memory access between nodes of the cores. We also present a new efficient aggregation algorithm (EAA), to aggregate the partitioned data in parallel with low cache coherence miss and locking costs. Theoretical analysis as well as empirical study on an IBM X5 server prove that our proposals are at least two times faster than existing methods.

关键词： Aggregation radix-partitioning in-memory databases cache miss

来源：评论

学校读者我要写书评

暂无评论

Gather-Scatter DRAM: In-DRAM Address Translation to Improve the Spatial Locality of Non-unit Strided Accesses 48

Gather-Scatter DRAM: In-DRAM Address Translation to Improve ...

引用

48th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO)

作者： Seshadri, Vivek Mullins, Thomas Boroumand, Amirali Mutlu, Onur Gibbons, Phillip B. Kozuch, Michael A. Mowry, Todd C. Carnegie Mellon Univ Pittsburgh PA 15213 USA Intel Labs Santa Clara CA USA

ISBN: (纸本)9781450340342

Many data structures (e.g., matrices) are typically accessed with multiple access patterns. Depending on the layout of the data structure in physical address space, some access patterns result in non-unit strides. In existing systems, which are optimized to store and access cache lines, non-unit strided accesses exhibit low spatial locality. Therefore, they incur high latency, and waste memory bandwidth and cache space. We propose the Gather-Scatter DRAM (GS-DRAM) to address this problem. We observe that a commodity DRAM module contains many chips. Each chip stores a part of every cache line mapped to the module. Our idea is to enable the memory controller to access multiple values that belong to a strided pattern from different chips using a single read/write command. To realize this idea, GS-DRAM first maps the data of each cache line to different chips such that multiple values of a strided access pattern are mapped to different chips. Second, instead of sending a separate address to each chip, GS-DRAM maps each strided pattern to a small pattern ID that is communicated to the module. Based on the pattern ID, each chip independently computes the address of the value to be accessed. The cache line returned by the module contains different values of the strided pattern gathered from different chips. We show that this approach enables GS-DRAM to achieve near-ideal memory bandwidth and cache utilization for many common access patterns. We design an end-to-end system to exploit GS-DRAM. Our evaluations show that 1) for in-memory databases, GS-DRAM obtains the best of the row store and the column store layouts, in terms of both performance and energy, and 2) for matrix-matrix multiplication, GS-DRAM seamlessly enables SIMD optimizations and outperforms the best tiled layout. Our framework is general, and can benefit many modern data-intensive applications.

关键词： Strided accesses DRAM memory bandwidth in-memory databases SIMD Performance Energy Caches

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：