Speed Up Math Computations on GPUs with Intel® oneMKL

Learn how to speed up computation on GPUs using Intel® oneAPI Math Kernel Library (oneMKL), an award-winning, high-performance library that contains optimized threaded and vectorized math routines used for science, engineering, and financial applications.

Topics covered include:

• An overview of oneMKL and its current support coverage across different domains.
  
• Elemental methods to offload oneMKL tasks on GPUs, including using OpenMP* offload, SYCL* buffers, and SYCL interfaces.
• Implicit and explicit scaling on multistack GPUs.

Discussion points are elaborated with sample code.

Skill level: Intermediate

Download the stand-alone version of oneMKL or as part of the Intel® oneAPI Base Toolkit.
 

Download a variety of samples on GitHub* for oneMKL, including:

• Matrix Multiply: Shows how to use the oneMKL optimized matrix multiplication routines.
• Fourier Correlation: Learn how to implement 1D and 2D Fourier correlation using SYCL, oneMKL, and Intel® oneAPI DPC++ Library (oneDPL) kernel functions.
• Monte Carlo European: Shows how to use the library’s random-number generation (RNG) functionality to compute European option prices.

View All