Arm Virtual Hardware Lab Series - Lab 2: Model Conditioning and Optimisation

Logo
Presented by

Elham Harirpoush, AI Ecosystem Evangelist & Sebastian Goscik, Senior Software Engineer, Arm

About this talk

This session is part of the Arm Virtual Hardware Lab Series, introducing Arm Virtual Hardware and how it can accelerate product design by up to two years. This session includes a workshop covering: • Get started running code for Arm Cortex-M55 processor and Ethos-U55 microNPU • Compile a neural network model and run a classical ML application on these processors • Evaulate pre-silicon technology, ready for when it becomes available Prerequisites • Arm and AWS are providing 100 hours of free AWS EC2 CPU credits for the first 1000 qualified users. Redeem these credits here: https://www.arm.com/company/contact-us/virtual-hardware • You will need a GitHub account to fully participate. Visit GitHub to sign in or create an account: https://github.com/ What is Arm Virtual Hardware? Arm Virtual Hardware provides a modern development flow, delivering flexibility, simplicity, and the opportunity for rapid IoT device development. It’s an evolution of Arm's modelling technology delivering functionally accurate models of Arm-based SoCs in the cloud for developers to build and test software before and after hardware availability. Arm Virtual Hardware is currently available as a beta. Learn more about Arm Virtual Hardware and the sessions in this series by viewing the attachments. For more information on how Arm processes your personal data, please visit the Arm Privacy Policy available here: https://www.arm.com/company/policies/privacy
Related topics:

More from this channel

Upcoming talks (0)
On-demand talks (102)
Subscribers (17907)
From providing the IP for the chip to delivering the cloud services that allow organizations to securely manage the deployment of products throughout their lifecycle, Arm delivers a complete Internet of Things (IoT) solution for our partners and customers. It’s rooted in our deep understanding of the future of compute and security.