Intel has created a data analytics acceleration project on github, to help accelerate data analytics applications. The Intel® Data Analytics Acceleration Library (Intel® DAAL), the high performance analytics (for "Big Data") library for x86 and x86-64, has been placed into open source to create this project.
Intel DAAL helps accelerate big data analytics by providing highly optimized algorithmic building blocks for all data analysis stages (preprocessing, transformation, analysis, modeling, validation, and decision making) for batch, online and distributed processing modes of computation. It’s designed for use with popular data platforms including Hadoop*, Spark*, R, and Matlab* for highly efficient data access. Intel DAAL is available for Linux*, OS X* and Windows* and is licensed with the Apache 2.0 license. The DAAL project is available on github for download, feedback and contributions.
Intel DAAL has benefited from customer feedback since its initial release in 2015. Following a year of intense feedback and additional development as a full product, Intel is excited to introduce it as a very solid open source project ready for use and participation. Intel DAAL remains an integral part of Intel's software developer tools and is backed by Intel with support and future development investments.
The Intel Data Analytics Acceleration Library (Intel DAAL) is a library delivering high performance machine learning and data analytics algorithms. Intel DAAL is an essential component of Intel’s overall machine learning solution including Intel® Xeon® Processor E7 Family, the Trusted Analytics Platform and Intel® Xeon Phi™ Processors (Knights Landing). Intel DAAL works with a wide selection of data platforms and programming languages including Hadoop, Spark, Python, Java and C++. Intel DAAL was first released in 2015 without source code to provide time to evolve some interfaces on the path to open sourcing this year. The Intel DAAL team appreciates the many users who have given feedback and encouragement to get Intel DAAL where it is today. Previous versions of Intel DAAL required separate installation of the Intel Math Kernel Library (Intel MKL) and Intel Integrated Performance Primitives (Intel IPP). The latest version of Intel DAAL actually comes with the necessary binary parts of Intel MKL (for BLAS and LAPACK) as well as Intel IPP (compression and decompression) so that the tremendous performance from these key routines are available automatically with no additional downloads needed! In order to make the most of multicore and many-core parallelism, and for superior threading interoperability, it is notable that the threading in Intel DAAL relies on the open source project known as "TBB" (Intel Threading Building Blocks).
In the exciting and rapidly-evolving data analytics market, this key Intel performance library can really boost performance. At the Intel Developer Forum in 2015, Capital One discussed significant acceleration (over 200X - see slide 26) as an early user of Intel DAAL. There have been numerous examples across many industries in the first year of product of substantial performance improvements using Intel DAAL - it is definitely worth a try!
DAAL is currently speeding toward a "2017" release (expected in late Q3 2016) in conjunction with Intel's award winning Intel Parallel Studio suite of developer tools. Precompiled binaries with installers are available for free as part of the beta program. Registration for the beta is available at tinyurl.com/ipsbeta2017.
The open source project feeds the product; there are no features held exclusively for the product version. The only difference when purchased is that priority support at Online Service Center is included for the entire product.
Intel's compilers may or may not optimize to the same degree for non-Intel microprocessors for optimizations that are not unique to Intel microprocessors. These optimizations include SSE2, SSE3, and SSSE3 instruction sets and other optimizations. Intel does not guarantee the availability, functionality, or effectiveness of any optimization on microprocessors not manufactured by Intel. Microprocessor-dependent optimizations in this product are intended for use with Intel microprocessors. Certain optimizations not specific to Intel microarchitecture are reserved for Intel microprocessors. Please refer to the applicable product User and Reference Guides for more information regarding the specific instruction sets covered by this notice.
Notice revision #20110804