SAS High-Performance Analytics
Big Data Requires Fast, Powerful Analytics
Analyzing Big Data is a complex, multifaceted endeavor, characterized by extreme data volumes, high velocity, and a broad variety of data generated by people, machines, and the Internet of Things. These characteristics break current models of data management, experimentation, and analysis. As a result, many attempts to analyze big data falter as they encounter:
- Reduced ability to develop and test timely new models and analytical applications.
- Reduced accuracy, caused by over-reliance on subsets rather than detailed data.
- Increased resource contention between teams sharing an analytical infrastructure.
- Reduced analyst productivity and increased backlog, caused by system delays.
SAS users are not immune. In fact, due to their analytical maturity, many SAS users encounter these challenges early in their analysis and come to view them as the critical issues in delivering on the promise of big data analytics using SAS.
For companies that are using SAS to embrace big data analytics, scaling the SAS infrastructure is critical to effectively deriving business value from big data.
Big Data Meets its Match
To meet the challenges of big data analytics, SAS and EMC Greenplum have joined forces to drive innovations that deliver big data agility to SAS users. SAS High Performance Analytics for Greenplum accelerates the performance and capacity of SAS, enabling users to embrace big data in their analytical applications while accelerating the pace of model development, testing, and execution. Having analytical agility enables developers to build increasingly accurate models that deliver business value from big data and lead to timely business decisions.
SAS + EMC Greenplum: A Powerful Combination
SAS and Greenplum have introduced a new architecture for SAS High Performance Analytics (HPA) that speeds up SAS applications by executing SAS procedures within the Greenplum Data Computing Appliance (DCA). Once installed, SAS HPA leverages three key innovations to accelerate SAS models and applications during development, validation, and execution:
- In-Memory Analytics – SAS High-Performance Analytics moves all needed data into the CPU memory of each segment processor of the Greenplum DCA nodes, accelerating data access by 10 times or greater during analytical computations.
- Massively Parallel Computation – In-memory analytics run on a grid of servers within the Greenplum DCA – dividing even the most complex computation into many parts to run in parallel on 192 processor cores.
- In-Database Analytics – SAS functions are integrated directly into the Greenplum DCA, executing them side-by-side with the Greenplum Database segments to eliminate I/O bottlenecks found in traditional server-based infrastructures.
Shortened Time to Value
Greenplum DCA's running SAS High-Performance Analytics for Greenplum software accelerate analytical processing to deliver insights in a fraction of the time required when using traditional SAS infrastructures. SAS HPA for Greenplum delivers:
- Superior Performance and Scalability – Leveraging 192 dedicated Intel processor cores per rack; large amounts of physical memory; and the MPP, shared-nothing Greenplum Database; Greenplum DCAs run SAS HPA at maximum performance and minimum cost.
- Accelerated Modeling and Analysis Processes – The increased computational capacity of HPA permits SAS analysts to execute more iterations of development, testing, and validation processes, resulting in better, more accurate models and applications.
- Immediate Value – Complex systems are only valuable if they’re easy to install and maintain. Greenplum DCAs are preconfigured to install quickly, and include comprehensive administration software that manages the DCA – including its grid of processors, memory, storage, and database software – as if it were a single platform. Coupled with storage solutions from EMC, Greenplum DCAs assure enterprise-class reliability and service for mission-critical SAS applications.
Making the Impossible Possible and the Unsolvable Solvable
SAS High-Performance Analytics and the Greenplum DCA make previously unsolvable analytical problems solvable by achieving levels of performance, capacity, and availability that were previously unattainable. By making impossible tasks possible, Greenplum and SAS deliver big data analytic agility that accelerates time-to-insight, leading to better business decisions and quantifiable financial benefits.
To investigate the potential of SAS HPA for your big data analytical needs:
SAS High-Performance Analytics solves complex business problems that require sophisticated, high-end analytics and access to large data sources.
Product overview of the Greenplum Data Computing Appliance: UAP Edition. The EMC® Greenplum® Data Computing Appliance (DCA) is an integrated analytics platform that accelerates analysis of Big Data assets within a single integrated appliance. Integrating Greenplum Database for analytics-optimzed SQL on structured data, Greenplum HD for Hadoop-based processing of unstructured data and Greenplum partner analytics, BI and ETL applications provides flexibility.
Product overview of Greenplum Database - massively parallel processing (MPP) database built to support the next generation of “Big Data” warehousing and large-scale analytics processing.
In order to succeed with big data and high-performance analytics, organizations require not only new technologies, but also a new set of human capabilities. A key component of these capabilities are data scientists—hybrids of analytical and computational skills, typically with science backgrounds. Data scientists are motivated not just to support internal decisions with analytics, but to create new products and processes for customers. In addition, big data and high-performance analytics require new approaches to deciding and acting on the part of executives and decision-makers.
SAS partners always bring valuable thought-leadership and industry perspectives to customer at events like Analytics 2012 and The Premier Business Leadership Series. Joining Deloitte and Teradata to talk about big data opportunities and trends is Jarrod Vawdrey, data scientist with Greenplum, a division of EMC. Vawdrey will be hosting one of many roundtables and other special events going on at this year’s conference, giving attendees a chance to have one-on-one discussions and ask critical business questions. Here’s a preview of what Vawdrey sees on the analytics horizon.
Careers and companies are built or buried by the judgments of a few, even a single individual. Decisions mould company strategy - which markets to enter or what products to develop, for example - and impact company resources. Today, as the world globalises and the pace of change quickens, managers must make high-pressure decisions faster.