Webinar: Demystifying Vectorization

Abstract

Have you heard of code vectorization, but not sure how it applies to your work? Rest assured, you are in a good company. Furthermore, even seasoned computing professionals have a good excuse for not being familiar with this concept!

That said, now is a great time to learn about writing vectorized code. That is because in modern Intel processors, vector instructions may speed up arithmetic instructions by up to a factor of 16. However, you must design computational code in a way that makes vector processing possible.

In this 1-hour webinar I will explain what to expect from vectorization, and how to make sure that your code has it:

• Manual and compiler-assisted vectorization
• Assessing your success with vectorization
• Loop was vectorized – what’s next?

Speaker

Andrey Vladimirov, Head of HPC Research, Colfax International

Dr. Andrey Vladimirov’s primary research interest is the application of modern computing technologies to computationally demanding scientific problems. Prior to joining Colfax, Andrey was involved in theoretical astrophysics research at the Ioffe Institute (Russia), North Carolina State University, and Stanford University (USA), where he studied cosmic rays, collisionless plasmas and the interstellar medium using computer simulations. He is the lead author of a book on parallel programming and optimization, a regular contributor to Colfax Research, an author of invited papers in industry-leading publications (1, 2) and an author or co-author of over 10 peer-reviewed publications in the fields of theoretical astrophysics and scientific computing.

Recording

Slides:

 Colfax-Demystifying-Vectorization-Webinar-2017.pdf (1 MB)

Colfax-Monte-Carlo-Vectorization-Demo.zip (11 KB)

Video: this webinar aired on June 7, 2017.