Pervasive Software has
announced Pervasive TurboRush for Hive,
new software that makes Hive queries run faster on less hardware.
Pervasive will be showing TurboRush
for Hive at the Yahoo! Hadoop Summit 2011 June
29. Now available through an early access program, Pervasive TurboRush for Hive
is the first in a series of big data accelerators
currently being developed and all powered by Pervasive DataRush.
Pervasive DataRush is a software
development platform that lets you rapidly build parallel applications that
deliver high throughput on big data. Pervasive DataRush fully leverages the
parallel processing capabilities of multicore processors to deliver enhanced
performance on a multicore server, SMP machine, cluster or Hadoop cluster.
Hive is the data warehouse system built on top of
Hadoop. Pervasive TurboRush
for Hive accelerates Hive by using the Pervasive DataRush dataflow engine on
the back end, providing faster execution of Hive programs without needing to
modify any code. It provides the power of Pervasive DataRush parallelism to the full
spectrum of SQL and Hive developers.
“Our Pervasive DataRush team
continues to deliver powerful innovations to benefit the Hadoop
ecosystem,” Ray Newmark, vice president of sales and marketing for
Pervasive DataRush, said in a statement. “Our engineers and our early access
users have seen Hive acceleration of 2-4x using the Pervasive TurboRush accelerator.
We look forward to extending this model to deliver out-of-the-box accelerators
for other languages and frameworks as well. In addition, we’ll be making
details available in the coming weeks about a community edition of Pervasive
DataRush for Hadoop.”
“I am seeing more and more
organizations turn to the Hadoop ecosystem to see what kind of practical
strategies they can adopt for processing big data,” said David Linthicum,
CTO of Blue Mountain Labs. “This is a promising offer to deliver
enterprise-scale performance for Hive developers tackling big data challenges.”
“Pervasive TurboRush for Hive is
exciting news for SQL analysts looking to discover trends, patterns and value
in their Big Data on Hadoop,” Martin Hall, co-founder, chairman and executive
vice president of corporate development at Karmasphere, said in a statement.
“The faster their Hive SQL queries perform, the faster their insights are
achieved. Our work with Pervasive is another important step in Karmasphere’s
commitment to deliver products that help developers, analysts and business
users unlock the power of Big Data on Hadoop and expand its use beyond IT
departments.”
In a June 28 statement, Pervasive
CTO Mike Hoskins cited two “cool new technologies” coming out of Pervasive. One
is TurboRush for Hive and the other is DataRush CE—a planned free Community
Edition for Hadoop users, bringing the benefits of dataflow and fine-grained
parallelism to MapReduce.
“We’re onboarding a record number of
customers on our next-generation cloud integration platform, including launch
of a private cloud platform that extends our current AWS [Amazon Web Services]-based
solution to support private and hybrid clouds,” Hoskins said. “We kicked off
Pervasive Galaxy, a fast-growing community of integration offerings in a
marketplace that connects buyers and sellers—with 30+ connectors already
available.”
For more information on Pervasive
TurboRush for Hive, and to participate in the early access program, go to http://www.pervasivedatarush.com/Products/TurboRushforHive.aspx.