Making the Benefits of AI Pervasive

AI is defining the next era of computing, and this is just the beginning. We see the benefits of AI every day—enabling medical research, curbing credit card fraud, reducing congestion in cities, or simply making life easier. 

We believe the full potential of AI will be realized when the technology is pervasive and spans from the cloud to the edge to endpoints. AMD is helping drive this with a focus on three key areas.

Solutions Portfolio

Delivering a broad portfolio of high performance and adaptive hardware and software solutions that make AI possible 

Open Ecosystem

Enabling an open, proven, and ready software strategy and co-innovating with partners across the open ecosystem

Compelling User Experiences

Right-sizing AI solutions to fit the use and capabilities of the device and simplifying complex workloads into compelling user experiences

Abstract background

Advancing AI

Discover our end-to-end AI infrastructure products, solutions, and ecosystem.

Watch the Replay
SILO AI logo with teal glow

Silo AI brings a team of world-class AI scientists and engineers to AMD

Learn how the acquisition of Silo AI brings together expert teams – developing cutting-edge AI models, platforms, software, and solutions for our customers.

Read the Press Release
mi300x

AMD Instinct™ MI300 Series Accelerators

Explore how AMD Instinct™ MI300 Series accelerators are supercharging AI inference and training.  

Discover MI300
mi300-face

AMD Pervasive AI Developer Contest 

Test your AI development skills from your desk to the cloud and compete to win multiple cash prizes.

Register Now

Powering Generative AI and Large Language Models

Generative AI is already transforming the way we work, live, and play. Training generative AI models—from large language models, to generative adversarial networks, and more—can involve billions of parameters, requiring massive compute capability. 

AMD powers some of the world’s fastest supercomputers, including Lawrence Livermore National Laboratory’s El Capitan, EuroHPC’s LUMI, and Oak Ridge National Laboratory’s Frontier—the first to break the Exascale barrier.1 AMD Exascale-class compute technologies are uniquely well suited to deliver the processing power needed by even the most complex Generative AI models. 

green leaf water drop

Deploying AI Responsibly

With the opportunity of AI comes the challenge of keeping the technology focused on positive outcomes: namely, helping solve some of the world's most vexing issues. AMD is committed to working with industry to innovate and deploy AI in a responsible manner.

Learn More

Applications

Data Center and Cloud

Whether you are running Generative AI LLMs, video analytics, recommendation engines, or any other data-intensive AI workloads, AMD solutions deliver the high performance, energy efficiency, and security features you need.

AMD Ryzen Radeon laptop

AI PCs

AMD delivers AI to laptops, desktops, and mobile workstations—supporting new applications that improve business productivity and collaboration, boost creativity, and offer security features.

Adaptive and Embedded

From industrial to healthcare to automotive to aerospace, AMD delivers adaptive and embedded computing solutions that drive AI inferencing to enable real-time decision-making.

male gamer using desktop pc with ai female future gamer looking on

Gaming

AMD is enabling AI-powered immersive gaming experiences on PCs, consoles, and mobile devices.

Featured Solutions

Advanced Research

Discover how AI solutions powered by AMD are helping drive advanced research.

Watch on YouTube

To watch YouTube content on this site, please change your privacy settings to enable cookies. Alternatively, click 'Watch on YouTube' to view the video directly on YouTube. Your personal data will be processed by YouTube in compliance with its own privacy policy and cookies policy available on its website.

El Capitan: Advancing Exascale Computing

AMD Instinct is the accelerator of choice for some of the world’s fastest and greenest supercomputers, including Lawrence Livermore National Laboratory’s El Capitan system.1,2 See how this two-Exascale supercomputer will use AI to run first-of-its-kind simulations to advance scientific research.

More Advanced Research Case Studies

Nasa Case Study Image Mars Rover

NASA

The NASA Mars rover uses AMD FPGAs to accelerate image detection, matching, and rectification. AMD FPGAs also help with analyzing and filtering out irrelevant data before sending information back to Earth.

Read Case Study
CERN Case Study Image AMD

CERN

At CERN, AMD accelerates AI inference with performance-critical sensor processing. Additionally, AMD accelerates machine learning neural network algorithm development and deployment.

Read Case Study

AI Architectures

AMD products are built on scalable, power-efficient, and adaptable architectures designed for workloads ranging from large-scale AI model training to real-time inferencing.

AMD CDNA

AMD CDNA™ architecture is built to accelerate compute-intensive AI and HPC workloads, offering an advanced platform for tightly connected GPU systems that can share data quickly and efficiently. 

Learn More
AMD XDNA™

AMD XDNA™ is a spatial dataflow NPU architecture consisting of a tiled array of powerful, custom-designed AI Engines that enable high compute density, ideal for DNN and signal processing workloads.

Learn More
AMD RDNA

The AMD RDNA™ architecture features AI accelerators delivering incredible performance, efficiency, and features to gamers across desktops, laptops, gaming consoles, mobile devices, and the cloud. 

Learn More
ZEN Architecture

AMD "Zen” architecture underlies AMD Ryzen™ processors and AMD EPYC™ server processors, offering the ultimate performance, scalability, and efficiency.

Learn More

Portfolio

AMD is the only technology provider in the industry that delivers a comprehensive product portfolio to support AI deployment from the cloud to the edge to endpoints.

AMD Instinct Accelerators

AMD Instinct MI325X and MI300X accelerators offer large on-chip memory ideal for Generative AI, while AMD Instinct MI300A accelerated processing units combine the power of AMD CPUs and GPUs.

Discover MI300

AMD EPYC Server Processors

AMD EPYC server processors deliver exceptional performance, energy efficiency, and security features for certain AI inferencing workloads. 

Discover EPYC

AMD Adaptive SoCs

AMD Versal™ AI Core, Versal AI Edge, and Zynq adaptive SoCs enable breakthrough AI inference in the data center and across a broad range of embedded applications. 

Discover Adaptive SOCs

AMD Ryzen Processors

AMD Ryzen™ AI processors feature built-in AI engines3 and enable accelerated muti-tasking and greater productivity.

For Businesses For Consumers

AMD Radeon™ Graphics Cards

AMD Radeon™ PRO and RX 7000 Series graphics cards enable users to harness the power of on-device AI processing with strong performance and platform support, all while delivering incredible value.

Discover Radeon AI

AMD Pensando DPU Accelerators

AMD Pensando™ DPU accelerators are optimized to execute a software stack delivering cloud, compute, network, storage, and security services at cloud scale.

Discover Pensando

Making AI Open and Accessible

Developers and partners can leverage AMD software tools to optimize AI applications on AMD hardware. Today, the stack includes AMD ROCm™ for AMD Instinct accelerators and AMD Radeon graphics cards, AMD Vitis™ AI for adaptive accelerators, SoCs, and FPGAs, as well as AMD ZenDNN open-source libraries for AMD EPYC processors.

In parallel, AMD is building towards a Unified AI Software Stack that will empower developers across our entire portfolio, enabling them to stay within familiar AI frameworks and target any AMD device.

Developers

Hugging Face

AMD is building a hub of AI models on Hugging Face to help make it easier to deploy AI on AMD platforms.

Learn More

PyTorch

AMD is aligning with the PyTorch Foundation on the value of an open software ecosystem for AI and is driving AMD ROCm support for PyTorch.

Learn More

AMD ROCm Software

AMD ROCm software includes the broad set of libraries, runtimes, compilers, and tools for AI and HPC solution development on AMD GPUs.

Learn More

AMD Vitis AI Platform

The AMD Vitis AI platform is a comprehensive AI inference development solution. It consists of a rich set of AI models, optimized deep learning processor unit cores, tools, libraries, and example designs for AI at the edge and in the data center.

Learn More Vitis AI on GitHub

AMD ZenDNN Library

The AMD ZenDNN library enables deep learning application and framework developers to improve AI inferencing performance on AMD EPYC processors.

Learn More
AMD Ryzen AI Software

Ryzen AI Software

Take ML models trained in PyTorch or TensorFlow and run them on select laptops powered by AMD Ryzen AI technology.

Learn More

Developer Central

Find the resources you need to develop your AI applications using AMD products. Access software downloads, documentation portals, training resources, communities, support forums, and more.

Developer Central
Footnotes
  1. Source: Top 500 list, June 2023
  2. Source: Green500 List - https://www.top500.org/lists/green500/2023/06/
  3. As of May 2023, AMD has the first available dedicated AI engine on an x86 Windows processor, where 'dedicated AI engine' is defined as an AI engine that has no function other than to process AI inference models and is part of the x86 processor die. For detailed information, please check: https://www.amd.com/en/technologies/xdna.html. PHX-3a