One Solution for Multiple Environments

Intel® Math Kernel Library (Intel® MKL) optimizes code with minimal effort for future generations of Intel® processors. It is compatible with your choice of compilers, languages, operating systems, and linking and threading models.

  • Features highly optimized, threaded, and vectorized math functions that maximize performance on each processor family
  • Utilizes industry-standard C and Fortran APIs for compatibility with popular BLAS, LAPACK, and FFTW functions—no code changes required
  • Dispatches optimized code for each processor automatically without the need to branch code

Explore Benchmarks

What's New

  • Optimized math functions that enable convolutional and deep neural networks
  • Extended Intel® Threading Building Blocks layer support that covers all BLAS Level 1 functions
  • Enhanced ScaLAPACK performance for symmetric eigensolvers on a high-performance computing (HPC) cluster
  • Improved optimizations for newer Intel processors, especially Intel® Xeon Phi™ processors

Release Notes


Community Forum
Connect to the developer community and our tech experts through this public forum.

Priority Customer Support
New software purchases include free updates and confidential priority customer support for a year through our Online Service Center. Get direct access to our technical experts when you purchase Intel MKL as a stand-alone product or bundled with Intel Parallel Studio XE or Intel System Studio.

Online Service Center | License FAQ

Key Specifications

Supported Hardware
Intel® Xeon Phi™ processor
Intel® Xeon® processor
Intel® Core™ processor family
Intel® Atom® processor

Operating Systems

Supported Integrated Development Environments
Microsoft Visual Studio* (Windows)
Eclipse* (Linux and macOS)

Programming Languages
C, C++, and Fortran development (native support)
Python through Intel Distribution for Python (optimizes standard Python libraries that include NumPy, SciPY, and scikit-learn)

System Requirements

Case Studies


1. Data from Evans Data Software Developer surveys, 2011-2016