Flow Computing Podcast Series: Prof. Dr. Jörg Keller on PPU Technology (Episode 1: Introduction to PPU Technology)

In this episode, Professor Dr. Jörg Keller, a professor with the Faculty of Mathematics and Computer Science at FernUniversität in Hagen, introduces the concept of Flow Computing's Parallel Processing Unit (PPU) and explains how it differs from traditional multi-core processors. Having conducted the technical due diligence on Flow’s PPU, Professor Keller brings a wealth of expertise to the discussion.

He highlights the limitations of current CPUs with independent cores, which often experience significant overhead when executing parallelizable code. The PPU addresses these challenges with its innovative architecture, featuring a set of cores that work in unison. This design drastically reduces overhead and enables efficient parallelization.

Additionally, PPU cores are smaller and consume less power than traditional CPU cores, making them an appealing choice for modern computing needs.

This first episode lays the foundation for understanding the unique advantages of the PPU and sets the stage for deeper exploration into its performance gains, use cases, adaptability, and impact on the future of computing in upcoming episodes.

Transcript

JÖRG KELLER: Today, we have multi-core processors—processors with a larger number of cores to increase computing performance. 

JK: For quite some time, these computing cores have all been the same. Then, some time ago, manufacturers started to introduce processors with different types of cores, like ARM's big.LITTLE technology. Still, these cores have remained independent of each other. Now, when we have code that can be parallelized, it would be nice to have a number of cores that basically do the same thing, and do it without the overhead caused by each core operating independently. This is where Flow's technology and the PPU cores come in. 

JK: Next to the standard CPU cores, there is a set of PPU cores that largely perform the same tasks at certain times. Thus, they can speed up some code without each having to fetch their program for themselves, because they all do the same and don’t need to maintain the structures that normal CPU cores require to run a program. So, we have an easy way to parallelize with less overhead.

JK: Moreover, PPU cores can be smaller than a typical CPU core, so their power consumption is also lower.

Curious to dive deeper into Flow Computing's PPU technology?

Discover the technical details and insights from Professor Dr. Jörg Keller, a renowned professor at the Faculty of Mathematics and Computer Science at FernUniversität in Hagen, who conducted the technical due diligence on the PPU.

Request access to the full report by contacting us at info@flow-computing.com, and we’ll gladly share it with you!