Visit additional Tabor Communication Publications
February 17, 2009
NSF grant focuses on making cloud computing clusters more researcher-friendly
Feb. 17 -- Researchers from the San Diego Supercomputer Center (SDSC) at the University of California, San Diego, have been awarded a two-year, $450,000 grant from the National Science Foundation (NSF) to explore new ways for academic researchers to manage extremely large data sets hosted on massive, Internet-based commercial computer clusters, or what have become known as computing "clouds."
The NSF award focuses on the Cluster Exploratory (CluE), a distributed, large-scale computing resource formed in late 2007 between Google and IBM. The NSF joined the Google-IBM partnership early last year, hailing the CluE initiative as a partnership between private enterprise and the federal science agency to expand access to this research infrastructure to academic institutions across the nation. Last April, the NSF issued a solicitation for research projects aimed at developing software to make CluE a researcher-friendly resource to analyze and manage extremely large amounts of data.
Specifically, SDSC researchers will explore the use of compute clouds to dynamically provision and manage large-scale scientific datasets. This is in contrast to the current approach using a traditional parallel relational database management system (RDBMS) architecture, which is more structured but also more static. The SDSC team will investigate the feasibility of the cloud computing approach versus known conventional approaches, while evaluating the trade-offs, advantages, and disadvantages.
"The CluE system provides access to a cloud computing environment characterized by relatively vast amounts of computational and storage resources," said SDSC Distinguished Scientist Chaitan Baru, who is heading the SDSC research project, called 'Performance Evaluation of On-Demand Provisioning of Data-Intensive Applications.' "This creates opportunities to rethink some of our strategies and ask ourselves some key questions: Could we use more dynamic strategies for resource allocation? Can this result in better overall performance for the user?"
Cloud computing -- defined by the ACM Computer Communication Review as a large pool of easily usable and accessible virtualized resources that can be dynamically reconfigured to adjust to a variable load and operated on a pay-per-use model -- has been generating considerable attention throughout the high-performance computing community, in both the commercial and academic sectors. This new model is seen as a possible way for researchers to move from processing and managing their own data sets locally, to relying on large, off-site, commercially-managed data clusters.
Amazon.com, for example, although primarily an e-commerce retailer, has made pay-as-you-go, on-demand computing and storage available via its "Elastic Compute Cloud" or EC2 platform. Introduced in mid-2006, EC2 is now being used by both startup companies and established businesses as a 'virtual' computing resource.
Like many other supercomputer scientists, Baru is concerned that the ever-increasing volume of scientific data is beginning to overwhelm current approaches to data management.
"The broader impact of this research will be to reassess how scientific data archives are implemented, and how data sets are hosted and served to the scientific community at large, using on-demand and dynamic approaches for provisioning data sets as opposed to the current static approach," said Baru. "This project has the potential to offer scientific researchers compute clouds as a complement to conventional supercomputing architectures used today, while creating new tools and techniques for commercial cloud computing."
SDSC's research will focus on using its already widely accepted GEON LiDAR Workflow (GLW) application, which is part of the Center's GEON Project, an open, collaborative project funded by the NSF's Information Technology Research (ITR) and Geoinformatics programs to develop cyberinfrastructure for the integration of three- and four-dimensional earth science data. LiDAR data have broad applicability in the areas of earth sciences, hydrology, ecology, environmental sciences, and hazards. The GLW application allows users to subset remote sensing data stored as "point cloud" data sets, process it using different algorithms, and visualize the output.
SDSC researchers will use the Google-IBM CluE cluster in combination with the Apache Hadoop programming environment, an open-source volunteer project developed under the Apache Software Foundation, a not-for-profit enterprise dedicated to open, collaborative software development projects by supplying hardware, communication, and business infrastructure. During the next 24 months, researchers will evaluate hybrid approaches that dynamically deploy a database instance for some subsets of the data, based on user directives or workload analysis, while the rest of the data are served using Hadoop.
"The resource-rich CluE environment represents the type of systems that are becoming available to real-world applications, as opposed to the resource-constrained environments that are currently common in most production systems for large scientific data management, especially in academia," said Baru. "The Google-IBM CluE cluster is a natural environment for implementing GLW, which is highly data-parallel in nature. Our plan is to evaluate a series of implementations using the database system, as well as the distributed file system and MapReduce implementations provided by Hadoop."
In addition, SDSC researchers believe that the CluE-based or similar cluster-based implementations can be exposed to user communities via a Services Oriented Architecture (SOA) for access via other scientific workflow environments, visualization tools, and portals, such as the GEON Portal and GEON's new Open Topography portal, which now contains GEON's LiDAR data access and processing capabilities.
"This in turn will bring the benefits of massively-scaled computing resources to a large community of users," noted Baru.
Sriram Krishnan, a senior distributed systems researcher with SDSC, is co-principal investigator on the project, which runs until Jan. 31, 2011. Other SDSC research team members include Viswanath Nandigam and Chris Crosby. NSF will provide support to researchers to conduct their work, while Google and IBM would cover the costs associated with operating the cluster. The project is being conducted under NSF Award No. IIS-0844530.
As an organized research unit of UC San Diego, the San Diego Supercomputer Center is a national leader in creating and providing cyberinfrastructure for data-intensive research, and has the largest archival storage capacity of any academic institution in the world. Cyberinfrastructure refers to an accessible and integrated network of computer-based resources and expertise, focused on accelerating scientific inquiry and discovery.
Source: San Diego Supercomputer Center
Contributing commentator, Andrew Jones, offers a break in the news cycle with an assessment of what the national "size matters" contest means for the U.S. and other nations...
Today at the International Supercomputing Conference in Leipzing, Germany, Jack Dongarra presented on a proposed benchmark that could carry a bit more weight than its older Linpack companion. The high performance conjugate gradient (HPCG) concept takes into account new architectures for new applications, while shedding the floating point....
Not content to let the Tianhe-2 announcement ride alone, Intel rolled out a series of announcements around its Knights Corner and Xeon Phi products--all of which are aimed at adding some options and variety for a wider base of potential users across the HPC spectrum. Today at the International Supercomputing Conference, the company's Raj....
Jun 18, 2013 |
The world's largest supercomputers, like Tianhe-2, are great at traditional, compute-intensive HPC workloads, such as simulating atomic decay or modeling tornados. But data-intensive applications--such as mining big data sets for connections--is a different sort of workload, and runs best on a different sort of computer.
Jun 18, 2013 |
Researchers are finding innovative uses for Gordon, the 285 teraflop supercomputer housed at the San Diego Supercomputer Center (SDSC) that has a unique Flash-based storage system. Since going online, researchers have put the incredibly fast I/O to use on a wide variety of workloads, ranging from chemistry to political science.
Jun 17, 2013 |
The advent of low-power mobile processors and cloud delivery models is changing the economics of computing. But just as an economy car is good at different things than a full size truck, an HPC workload still has certain computing demands that neither the fastest smartphone nor the most elastic cloud cluster can fulfill.
Jun 14, 2013 |
For all the progress we've made in IT over the last 50 years, there's one area of life that has steadfastly eluded the grasp of computers: understanding human language. Now, researchers at the Texas Advanced Computing Center (TACC) are utilizing a Hadoop cluster on its Longhorn supercomputer to move the state of the art of language processing a little bit further.
Jun 13, 2013 |
Titan, the Cray XK7 at the Oak Ridge National Lab that debuted last fall as the fastest supercomputer in the world with 17.59 petaflops of sustained computing power, will rely on its previous LINPACK test for the upcoming edition of the Top 500 list.
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.
04/15/2013 | Bull | “50% of HPC users say their largest jobs scale to 120 cores or less.” How about yours? Are your codes ready to take advantage of today’s and tomorrow’s ultra-parallel HPC systems? Download this White Paper by Analysts Intersect360 Research to see what Bull and Intel’s Center for Excellence in Parallel Programming can do for your codes.
Join HPCwire Editor Nicole Hemsoth and Dr. David Bader from Georgia Tech as they take center stage on opening night at Atlanta's first Big Data Kick Off Week, filmed in front of a live audience. Nicole and David look at the evolution of HPC, today's big data challenges, discuss real world solutions, and reveal their predictions. Exactly what does the future holds for HPC?
Join our webinar to learn how IT managers can migrate to a more resilient, flexible and scalable solution that grows with the data center. Mellanox VMS is future-proof, efficient and brings significant CAPEX and OPEX savings. The VMS is available today.