Workshop Title: Enabling AI on AMD’s Hardware and Software Ecosystem
Presenters:
- Hari Sadasivan, Member of Technical Staff SDE, AMD
- Kalin Ovtcharov, AI Solutions Architect, AMD
- Mahesh Ravishankar, Senior Software Development Manager, AMD
Abstract:
This workshop is meant to provide an overview of AMD’s cutting-edge AI product portfolio and ecosystem. During the talks and demos, you will learn how to develop high-performance AI code for GPUs, how to build generative AI applications on RyzenAI NPUs, and how the open-source IREE compiler and runtime can be used to enable AI workloads on any device. Please join us to learn how you can use AMD technologies to power your AI ambitions!
Presentations:
- Hari Sadasivan: “High-Performance AI on AMD GPUs” (90 min)
This talk provides an overview of AMD’s cutting-edge AI product portfolio and ecosystem. We discuss running AI workloads on AMD GPUs, culminating in a deep dive into Composable Kernels, AMD’s high-performance AI backend. Attendees will gain insights into state-of-the-art GPU technology and its applications in accelerating AI computations.
- Kalin Ovtcharov: “Building GenAI Applications on RyzenAI NPU” (60 min)
- Mahesh Ravishankar: “IREE : An open-source compiler for AI on any device” (30 min)
Presenter Bios:
Hari Sadasivan, Member of Technical Staff SDE, AMD
Dr. Hari Sadasivan is a Member of Technical Staff SDE at AMD, a part-time faculty member at the University of Washington, Seattle, and an IEEE Senior Member. Hari focuses on systems for AI and life-sciences. Hari drives the AMD Center of Excellence in AI at the Allen School of CSE and is the co-founder of the AMD-omics focus group which collaborates with research institutes world over. Hari holds a PhD in CSE from the University of Michigan Ann Arbor and is a peer-reviewer for several IEEE/ACM venues.
Kalin Ovtcharov, AI Solutions Architect, AMD
Kalin Ovtcharov is an AI solutions architect at AMD in Seattle. As an entrepreneur, he has founded a company of researchers and builders to innovate engaging mobile experiences for artists of the future using the latest in generative AI.
Mahesh Ravishankar, Senior Software Development Manager, AMD
Mahesh Ravishankar is a Senior Software Development Manager, with a focus on the fast-growing Shark/IREE projects at AMD, working on front end integration with ML Frameworks, and optimizing generated code on CPUs, GPUs and other devices. He was previously with Google Federated Learning team and NVIDIA’s Deep Learning Compiler team. Mahesh is a graduate of Ohio State University with a PhD in CS&E in high-performance computing.