Accelerating data-intensive ML applications with the Graphcore IPU by Tim Santos

Traditional processing architectures for data science and machine learning are hindering where the industry can go next in Machine Intelligence. New hardware is required to run complex ML models and handle large-scale data workloads. This talk will outline how Graphcore’s IPU architecture and Poplar® Software Stack enables world-class performance and efficiency – and how the IPU has powered breakthroughs in finance, healthcare and scientific research.

Supported by