Launched in May 2003, Intel® Math Kernel Library has long been a developer’s go-to for compute-intense applications that depend on math routines—linear algebra, vector math, statistics, deep neural networks (DNNs), and more.
And for the majority of its existence, Intel® MKL has been focused on CPU-based platforms.
But that’s changed.
Enter Intel® oneAPI MKL (oneMKL) optimized for applications deployed on CPU- and/or GPU-based architectures.
Intel Math Algorithm Engineer Peter Caday will discuss how oneMKL enables developers to program with GPUs beyond the traditional CPU-only support.
Topics covered include:
- An overview of how to improve your math library experience by developing once for GPUs and CPUs
- How industry-leading oneMKL1 enables developers to program with GPUs beyond the traditional CPU-only support
- Walking through a GPU-specific example of oneMKL API call from the Data Parallel C++ (DPC++) language to demonstrate the new, streamlined development process for linear algebra, random number generators, and more
Get the software
Download Intel® oneAPI Math Kernel Library as part of the Intel® oneAPI Base Toolkit.
1. Data from Evans Data Software Developer surveys, 2011-2019