Intel® oneAPI Math Kernel Library
Ask questions and share information with other developers who use Intel® Math Kernel Library.

Intel Math Kernel Library 11.0 beta program


We're no longer accepting new participants in our beta program. If you are very interested in providing feedback on new functionality, let us know via Intel Premier support.

Intel MKL 11.0will introduce:

  • Conditional Bitwise Reproducibility (CBWR): New functionality in Intel MKL now allows you to balance performance with reproducible results by allowing greater flexibility in code branch choice and by ensuring algorithms are deterministic. See the Intel MKL User's Guide for more information. All of Intel MKL supports this new capability except ScaLAPACK, cluster FFTs, data fitting functions, summary statistics functions, and the vsRngBeta random number generator on 32-bit operating systems. Learn more this feature from our recorded training session and technical details.
  • Optimizations using the new Intel Advanced Vector Extensions 2 (AVX2) which include the new FMA3 instructions. Many functions have been optimized in the following areas: BLAS, LINPACK, FFTs, Vector math, Data fitting functions, Random number generators, and Summary statistics. See our knowledgebase article for further information.

Other new Features

  • FFT: Completed support for real-to-complex transforms with large sizes specified by 64-bit integers
  • Random number generators: Added support for a non-deterministic random number generator (VSL_BRNG_NONDETERM) based on the RdRand instruction

For more information on Intel MKL 11.0 read our release notes online or visit our knowledgebase article.

Intel MKL team

0 Kudos
3 Replies
I informed Intel MKL that they implemented many important functions was ineffectively. In the new version these functions are implemented better?
0 Kudos
quote: ...many important functions was ineffectively.
Yuri, how can you prove this statement?
0 Kudos