February 14, 2012
Cloud-based scaling takes in-memory data grids (IMDGs) to the next level
SANTA CLARA, Calif., Feb. 14 — ScaleOut Software, a leading provider of in-memory data grids (IMDGs), today announced the immediate availability of ScaleOut StateServer Version 5.0 beta. IMDGs provide distributed, in-memory storage which scales application performance and enables powerful query and analysis of stored data. Version 5.0 introduces an innovative new architecture designed to run in cloud infrastructures and easily scale to hundreds of servers. This version also adds the ability to transparently combine multiple IMDGs into a single virtual data grid and other key innovations.
"Distributed, in-memory data grids are being rapidly adopted for both on-premise and cloud use," said Dr. William L. Bain, founder and CEO of ScaleOut Software. "Enterprise applications increasingly require immediate access to data globally from a variety of sources, and developers are faced with the challenge of how to share information across logical and geographical boundaries. Addressing these challenges is one of the focus areas for Version 5.0."
With its ScaleOut GeoServer option, Version 5.0 introduces a full range of features for multi-site integration. In addition to asynchronous data replication for disaster recovery, GeoServer now lets users combine in-memory data grids at multiple sites into a single, logically coherent, virtual grid, enabling seamless data access across sites without the need to explicitly track which site is hosting requested data. This breakthrough capability saves both development time and resources at a time when IT head count and budgets continue to be under scrutiny. This helps increase both efficiency and productivity across the enterprise.
With the enhanced feature set in ScaleOut AnalyticsServer (formerly Grid Computing Edition), Version 5.0 enables in-memory data grids to offer industry-leading capabilities and performance in parallel query and data analysis. AnalyticsServer now supports optimized parallel query of stored data based on Java or C# object properties, and it fully supports the Microsoft Language Integrated Query (LINQ) standard. These capabilities have been integrated into its proven map/reduce engine to provide a powerful platform for memory-based data analysis. Its intuitive, object-oriented map/reduce model saves development time, and its fast, memory-based analysis dramatically lowers latency in comparison to other map/reduce platforms.
"Big data, rapid data churn and the need to minimize latency present huge obstacles for enterprises performing data analysis," said Dr. Bain. "Popular analytical techniques like Hadoop's map/reduce work well for petabyte-sized datasets but are complex to use for many problems, requiring significant effort to develop and tune applications."
Continued Dr. Bain, "ScaleOut has integrated the industry's powerful map/reduce analysis model into its scalable IMDG architecture to create an intuitive and extremely high performance platform for analyzing memory-based datasets. We also expect that hosting ScaleOut AnalyticsServer in a cloud environment will create a breakthrough opportunity by enabling users to easily take advantage of a very powerful and elastic computing platform for their data analysis."
"2012 holds an exciting new opportunity to leverage the cloud, as many datasets now can be held entirely in memory," said David Brinker, COO of ScaleOut Software. "Cloud computing makes it practical to harness hundreds of servers to perform data analyses. As global enterprises begin to adopt private and eventually, public clouds, a new generation of IMDGs pioneered by ScaleOut StateServer Version 5.0 will revolutionize data analysis."
With version 5.0, the ScaleOut GeoServer option now offers the flexibility to support multiple usage models in sharing stored data across multiple IMDGs. Customers needing fast data retrieval worldwide for data principally stored and updated at a central site now can efficiently access these data and receive timely updates over wide area networks. For example, financial institutions can easily make slowly changing portfolio information available to their satellite offices through a network of IMDGs. In a separate usage model, applications can seamlessly transfer ownership of shared data among sites as needed for efficient, synchronized updating. For example, Web sites can expand into a cloud-host Web farm to handle high traffic loads and transparently migrate shopping carts to requesting Web servers as needed.
Version 5.0 of ScaleOut AnalyticsServer integrates parallel query with an intuitive but powerful map/reduce development model to sidestep many of the complexities found in popular map/reduce platforms, such as Hadoop. Called parallel method invocation (PMI), ScaleOut's approach identifies objects to be analyzed using an intuitive parallel query on relevant object properties; queries can be formulated using either Java filters or C# LINQ expressions. Also, PMI offers a self-tuning parallel architecture that automatically extracts full parallelism in both the map and reduce phases and takes advantage of all IMDG servers, processors, and cores. In addition to PMI, Version 5.0 also adds a columnar computation model called single method invocation for very fast analysis and updating of specific objects in the IMDG.
ScaleOut StateServer 5.0 will be showcased at CloudConnect booth #819 in Santa Clara from 13-16 February 2012.
About ScaleOut Software
ScaleOut Software develops software products that provide scalable, highly available caching and analysis for workload data in server farms and compute grids. It has offices in Bellevue, Washington, Beaverton, Oregon, and New York City. The company was founded by Dr. William L. Bain, whose previous company, Valence Research, developed and distributed Web load-balancing software that was acquired by Microsoft Corporation and is now called Network Load Balancing within the Windows Server operating system. Visit www.scaleoutsoftware.com or follow us on Twitter @scaleout_inc for more information.
Source: ScaleOut Software, Inc.
The ever-growing complexity of scientific and engineering problems continues to pose new computational challenges. Thus, we present a novel federation model that enables end-users with the ability to aggregate heterogeneous resource scale problems. The feasibility of this federation model has been proven, in the context of the UberCloud HPC Experiment, by gathering the most comprehensive information to date on the effects of pillars on microfluid channel flow.
Large-scale, worldwide scientific initiatives rely on some cloud-based system to both coordinate efforts and manage computational efforts at peak times that cannot be contained within the combined in-house HPC resources. Last week at Google I/O, Brookhaven National Lab’s Sergey Panitkin discussed the role of the Google Compute Engine in providing computational support to ATLAS, a detector of high-energy particles at the Large Hadron Collider (LHC).
Frank Ding, engineering analysis & technical computing manager at Simpson Strong-Tie, discussed the advantages of utilizing the cloud for occasional scientific computing, identified the obstacles to doing so, and proposed workarounds to some of those obstacles.
May 23, 2013 |
The study of climate change is one of those scientific problems where it is almost essential to model the entire Earth to attain accurate results and make worthwhile predictions. In an attempt to make climate science more accessible to smaller research facilities, NASA introduced what they call ‘Climate in a Box,’ a system they note acts as a desktop supercomputer.
May 16, 2013 |
When it comes to cloud, long distances mean unacceptably high latencies. Researchers from the University of Bonn in Germany examined those latency issues of doing CFD modeling in the cloud by utilizing a common CFD and its utilization in HPC instance types including both CPU and GPU cores of Amazon EC2.
05/10/2013 | Cleversafe, Cray, DDN, NetApp, & Panasas | From Wall Street to Hollywood, drug discovery to homeland security, companies and organizations of all sizes and stripes are coming face to face with the challenges – and opportunities – afforded by Big Data. Before anyone can utilize these extraordinary data repositories, however, they must first harness and manage their data stores, and do so utilizing technologies that underscore affordability, security, and scalability.
04/02/2012 | AMD | Developers today are just beginning to explore the potential of heterogeneous computing, but the potential for this new paradigm is huge. This brief article reviews how the technology might impact a range of application development areas, including client experiences and cloud-based data management. As platforms like OpenCL continue to evolve, the benefits of heterogeneous computing will become even more accessible. Use this quick article to jump-start your own thinking on heterogeneous computing.