AIX > Trends > What's New

Study Outlines Benefits of SAS Grid Computing on AIX

Any organization deploying analytics in the current technology-driven business environment must keep in mind performance, costs and benefits provided by their chosen IT platform and architecture. The research and analysis departments of many companies depend on business analysis products to assemble data pools, manipulate them into usable information, and to summarize their findings.

One of the most prevalent business-analysis software products is SAS, which offers a comprehensive suite that can be implemented on a grid architecture. Grid computing refers to the combination of computer resources from multiple administrative domains, working toward a common purpose. In this topology, analytic workloads are processed by a shared pool of loosely coupled, distributed servers or partitions.

This architecture allows flexible resource allocation and increased system utilization across multiple analytic applications and multi-user environments. Organizations with large, diverse analytic workloads benefit from greater job and task parallelization, improved prioritization and efficient workload balancing.

To evaluate the impact of IBM platforms running the SAS Analytics suite in a grid environment, IBM engaged Solitaire Interglobal Ltd. (SIL) to conduct surveys, gather data and perform analysis to better understand the benefits of implementing SAS Grid Computing on IBM platforms running AIX. The resulting report, “Selecting a Strategic Platform for SAS Grid Computing,” is now available.

Analyzing the Platforms

SAS Grid Computing is designed to address complexity, availability, effectiveness and flexibility. Therefore SIL’s analysis focuses on how AIX feeds into centralized management and reduced complexity; maintains high availability; leverages applications with existing IT architecture; and increases flexibility to smooth future pathways.

During the study, the main behavioral characteristics of software and hardware were examined closely at more than 19,300 customer sites. These customers include organizations that have deployed SAS Grid Computing, as well as those running SAS in non-grid topologies. The platforms represented included AIX, Lintel and Windows.

The information from these customer reports and the accompanying mass of real-world details are invaluable, because they provide a realistic, rather than theoretical, understanding of how analytics deployed to a SAS Grid Computing environment can be affected by the platform it’s deployed on. Although the raw operational performance of the analytics software is an important metric, the translation of that performance into business terms is more germane, researchers determined. This business perspective encompasses a myriad of factors, including reliability, staffing levels and time-to-market effects. This ties directly into the decisions that IT managers, CTOs, project managers and business leadership have to make daily.

Kat Lind is chief systems engineer for Solitaire Interglobal Ltd., with over 43 years in the data processing and industrial psychology arenas. She has published extensively on performance, system implementation, risk evaluation and programming productivity subjects, and has done considerable research in the performance modeling and tuning areas.

Like what you just read? To receive technical tips and articles directly in your inbox twice per month, sign up for the EXTRA e-newsletter here.

comments powered by Disqus



2019 Solutions Edition

A Comprehensive Online Buyer's Guide to Solutions, Services and Education.

IBM Systems Magazine Subscribe Box Read Now Link Subscribe Now Link iPad App Google Play Store
IBMi News Sign Up Today! Past News Letters