Nathan Nadarajah, Senior Fellow and Security Architect at AMD, recently sat down with me to answer some questions about GPU security. In his two decades with the company, Nadarajah has worked on GPU drivers, GPU firmware and security firmware, and his expertise spans both the use of GPUs in enterprise data centers and in consumer gaming workstations.

Cloud computing providers and leading technology companies are investing in cutting-edge AI chips to power the next generation of innovation.

Today, we continue to celebrate the dedication of  the El Capitan supercomputer with Lawrence Livermore National Laboratory (LLNL), in collaboration with the National Nuclear Security Administration (NNSA) and Hewlett Packard Enterprise (HPE).

The AI era is here, and it's hungry—hungry for performance, scalability, and efficiency. Whether you're building next-gen data centers, fine-tuning your AI/ML workloads, or crafting cutting-edge HPC solutions, one thing is clear: the right ingredients matter.  This blog will guide you through the AMD recommended ingredients, the secret sauce, and the cooking techniques needed to create an AI/HPC infrastructure that’s as efficient as it is powerful. Let’s get cooking.

The power of AMD Instinct GPUs is now available from leading cloud providers, so that enterprises, and AI innovators can now tap into these accelerators easily through their preferred cloud solution providers.

Partner Spotlight: Nscale Cloud Service Provider
Strategically located near the Arctic Circle in Norway, Nscale's Glomfjord data center leverages the environment’s natural cooling to optimize energy efficiency. Powered by 100% renewable energy, the data center features advanced adiabatic cooling, ensuring streamlined operations, scalable solutions and an eco-friendly footprint.

Nscale has launched its latest GPU cluster, powered by AMD Instinct^TM MI250X accelerators in its Glomfjord data center in Norway. Currently powering some of the world’s top supercomputers, AMD Instinct^TM MI250X GPUs are designed to supercharge HPC workloads and meet the growing demands of AI training, fine-tuning, and inference.