AMD says that 5th Gen AMD EPYC processors are now powering the host infrastructure for Google Cloud TPU 8tx – the first cloud Tensor Processing Unit (TPU) system to deliver hardware-enforced confidential computing.
The expanded collaboration between the companies combines AMD EPYC CPU performance, AMD Infinity Guard security capabilities and x86 software compatibility with Google Cloud TPU AI acceleration to help enterprises deploy inference, fine-tuning and reinforcement learning workloads. With Google Cloud’s confidential computing architecture on TPU 8tx supported by 5th Gen AMD EPYC host processors, organisations can run their most sensitive AI workloads at scale in the cloud without compromising on data protection.
The deployment extends the role of AMD EPYC processors as a foundation for accelerated AI infrastructure.
Across systems built with GPUs and custom accelerators, AMD EPYC CPUs are the choice for host processing – preparing data, coordinating workloads and managing communication with accelerators. With TPU 8tx, AMD and Google Cloud bring those capabilities together with hardware-rooted security to address a critical requirement for production AI: protecting data while it is in use.
“The most capable AI systems need a CPU foundation that can match the demands of the accelerators they host,” says Dan McNamara, senior vice-president and GM, Compute and Enterprise AI at AMD. “Across generations of EPYC, we have built leadership capabilities in the performance, memory bandwidth and I/O that keep accelerated systems productive, backed by years of engineering collaboration with the world’s leading cloud providers.
“Our work with Google Cloud brings that strength to TPU 8tx, helping customers scale AI with the performance and protection their most important workloads demand,” he says.
“When teams move AI agents into production, they need confidence that their data and intellectual property stay private, even from the underlying infrastructure,” says Mark Lohmeyer, vice-president and GM for AI and Computing Infrastructure at Google Cloud. “By pairing 5th Gen AMD EPYC processors with our 8th-generation TPU architecture inside the AI Hypercomputer, we are bringing hardware-enforced confidential computing to cloud TPUs for the first time. Customers get silicon-level data protection alongside the low-latency performance needed for modern reasoning models.”