Blending Big Data analytics-enabling technology into the company's business database offering, IBM today announced the general availability of IBM DB2 10.5 with BLU Acceleration.
According to IBM, the product's home-grown innovations can have a game-changing effect on an organization's ability to extract insights from massive amounts of data. "IBM's work with beta clients and internal tests show significant speed and simplicity," Bob Picciano, general manager of IBM Information Management, said in a statement.
"In one example, BLU Acceleration was shown to be 10 times faster than another well-known in-memory database system. Some queries that took 7 minutes were shown to have dropped to 8 milliseconds, thanks to the innovations in BLU Acceleration," added Picciano.
The secret to DB2's newfound Big Data analytics prowess, apart from its speedy in-memory processing capabilities, is compression. In a June 4 blog post, IBM Software Group's Douglas Gibbs detailed how BLU Acceleration helps bring Big Data down to size.
"With DB2 10.5, you have the option to insert data into the database as columnar-ordered data sets that compress the data as it is being loaded. Because of the high compression rate, DB2 can work with more data in memory than before," explained Gibbs.
Due to BLU's compression tech, which can squeeze a 5 TB database to less than 2 TB, more of the data "can reside in memory and cache, which decreases the response time of loading and querying the data," added Gibbs. As a result, DB2 can execute more queries, in less time and with a larger data set."
Additionally, BLU can often use the data in its compressed state and "the compressed data does not have to fit in memory. BLU can handle compressed data regardless if it's in physical memory or on disk," he stated.
By shrinking the data footprint, flash storage gets to shine. The technology allows IT shops to leverage "a smaller number of faster SSDs versus a larger number of slower HDDs" for performance and energy efficiency gains.
DB2 10.5's other technical advancements include the ability to process row-based and column-based tables in the same system simultaneously. The software also exploits the multi-core and single instruction multiple data (SIMD) CPU features in IBM POWER and Intel processors to enhance performance.
BLU is already proving its worth to select customers, including Beijing's Yonyou Software, an enterprise management software and cloud service company. "ERP and accounting software applications run a lot of reports. We used DB2 BLU Acceleration and saw our reports run faster by up to 40 times. This type of technology is an ideal fit for Yonyou's Big Data Analytic Services," said Liu in company remarks.
Pedro Hernandez is a contributing editor at Database Journal and InternetNews.com. Follow him on Twitter @ecoINSITE.