AI Without GPUs: Using Your Existing CPU Resources to Run AI Workloads

This is a talk Keith Bradley and I gave at VMware Explore 2024 Las Vegas. Keith Bradley is the Vice President of IT and Security at Nature Fresh Farms. Nature Fresh Farms uses AI to control every aspect of their agricultural operations and they’re using CPUs to process those AI workloads.

Graphics processing units (GPUs) are expensive, hard to acquire and extremely powerful, but there are many AI/ML applications that can run just fine without GPUs. This session covers how to use your existing central processing unit (CPU) resources to run AI workloads, what you can do, what you shouldn’t do and what types of problems you can solve without using any GPUs at all.

AI without GPUs: Using Intel AMX CPUs on VMware vSphere for LLMs

This is a talk I gave at AI Field Day 4, February 2024 in Santa Clara. I demonstrate using Intel Sapphire Rapids Xeon CPUs with AMX to fine tune and run large language models without using any GPUs at all.

AI without GPUs: Using Intel AMX CPUs on VMware vSphere with Tanzu Kubernetes

This is a talk I gave at AI Field Day 4, February 2024 in Santa Clara. I demonstrate using vSphere 8 and Tanzu Kubernetes with Intel Sapphire Rapids Xeon CPUs with AMX to run AI workloads on CPUs.

AI without GPUs: Run AI/ML Workloads on Intel AMX CPUs

This is a talk that Chris Gully and I gave at VMware Explore 2023 in Barcelona. It covers how to use the AMX instructions present in Intel Sapphire Rapids CPUs to accelerate AI/ML workloads without using any GPUs at all.

Unlock AI everywhere with VMware Private AI and Intel

This is a panel discussion that I took part in at VMware Explore 2023 in Barcelona, discussing CPU+AMX and GPU acceleration of AI/ML workloads.

Machine Learning Hybrid Cloud

Intel Sapphire Rapids CPUs accelerate on-premises Machine Learning

This is a talk I gave at VMware Explore 2023 in Las Vegas. In the first half I cover how to use Sapphire Rapids CPUs to run AI/ML workloads without using GPUs at all.

Policy-based Cloud Storage

This is a talk I gave in September 2015 at the SF Microservices Meetup. In it I cover Apcera‘s approach to storage for containers and how to use policy to manage very large scale application deployments.

Validating Distributed Application Workloads

This is the talk I gave at RICON 2014, October 28, 2014, on Validating Distributed Application Workloads. It’s about how we set up test environments at Seagate for validating storage system performance at the petabyte scale. This talk centers around the testing done to validate performance of a 2PB rack running Riak CS.