Sign up for our newsletter and get the latest HPC news and analysis.
Send me information from insideHPC:


MapD Open Sources High-Speed GPU-Powered Database

Today MapD Technologies released the MapD Core database to the open source community under the Apache 2 license, seeding a new generation of data applications.

Open source is sparking innovation for data science and analytics developers,” said Greg Papadopoulos, venture partner at New Enterprise Associates (NEA). “An open-source GPU-powered SQL database will make entirely new applications possible, especially in machine learning where GPUs have had such an enormous impact. We’re incredibly proud to partner with the MapD team as they take this pivotal step.”

MapD pioneered the use of graphics processing units (GPUs) to analyze multi-billion-row datasets in milliseconds, orders-of-magnitude faster than traditional CPU-based systems. By open sourcing the MapD Core database and associated visualization libraries, MapD is making the world’s fastest analytics platform available to everyone.

MapD has also released a free Community Edition of its software for non-commercial development and academic use. The MapD Community Edition includes the MapD Core database and MapD Immerse visual analytics client.

“The focus of my research group is developing faster algorithms for parallel compute devices, particularly GPUs,” said John Owens, Child family professor of engineering and entrepreneurship at the University of California, Davis. “We’ve been impressed for some time with the work MapD is doing, only wishing we could use it as a real-world test bed for our research. Now that they are open sourcing their database offering, our team is excited to use it as a research platform and to contribute to the code base.”

“MapD’s decision to open source its Core database is significant, as it will further energize an already active GPU analytics community,” said Jim McHugh, NVIDIA general manager of DGX Systems. “I expect this move by MapD will drive adoption, by enabling hundreds of thousands of GPU developers to experiment with database acceleration and build new GPU-accelerated application solutions.”

For customers that need advanced features such as Distributed Architecture, High Availability, ODBC connectivity and 24/7 support, MapD is introducing an Enterprise Edition. This commercial edition also includes the MapD Immerse visualization client, a server-side graphics rendering engine for visualizing the results of SQL queries, as well as enterprise-grade warranties and support.

With this launch, MapD product editions include:

MapD Core open source database – source code of the MapD Core database provided under the Apache 2 license.

  • MapD Analytics Platform Enterprise Edition – comprising the MapD Core database including Distributed and High Availability capabilities, GPU rendering engine, ODBC and LDAP features, and the MapD Immerse visualization client. Also included is a product warranty and enterprise support.
  • MapD Analytics Platform Community Edition – offering a non-commercial and academic use license of MapD Core database with rendering engine pre-installed, and MapD Immerse visual client. Support will be provided via community forums.
  • MapD visualization libraries – MapD is also providing open source Javascript libraries that allow users to build custom web-based visualization apps powered by a MapD Core database. The libraries contain functionality for producing charts, crossfiltering data and managing connections to the MapD Core database. The charting and crossfilter libraries are based on the popular DC.js Dimensional Charting project.

I was proud to be involved from the start, and to watch MapD set a new standard for high-performance analytics,” said Samuel Madden, professor of electrical engineering and computer Science at MIT CSAIL (Computer Science and Artificial Intelligence Laboratory), and an advisor to MapD. “Now I am just as proud that MapD is putting its technology in the hands of developers around the world. I foresee our research team, and many others, building on the MapD Core database to fuel innovation in real-time analytics and machine learning.”

“From the earliest days at MIT, it was my goal to release MapD to the open source community,” said Todd Mostak, co-founder and CEO of MapD Technologies. “Now that our product has matured and with backers who believe in open source, the time is right for us as a company to take that step. We’re at the beginning of a GPU era of analytics, and we believe that by open sourcing we can help take the space mainstream. I can’t wait to see what developers will do with the ability to query and analyze massive datasets with sub-second response times.”

Availability

  • MapD Core database – is available now on Github under the Apache 2 license.
  • MapD graphics and utility libraries – are available now on Github under an Apache 2 license.
  • MapD Community Edition – is available from the MapD website for non-commercial or academic use following registration.
  • MapD Enterprise Edition – is available for on-premises and cloud customers from MapD at sales@mapd.com.

Sign up for our insideHPC Newsletter

Resource Links: