AMD and Google Cloud Put Confidential AI Inside the TPU Path
Google Cloud is bringing hardware-backed confidential computing to TPU-based AI, protecting sensitive workloads across the host and accelerator path.
What is this trend?
Google Cloud is extending confidential computing from CPUs into TPU-based AI, using AMD EPYC and SEV/Infinity Guard to protect prompts, weights, and data during inference and training.
- First cloud TPU deployment with hardware-enforced confidential computing
- Protects sensitive AI data across the EPYC host and TPU path
- Extends trusted execution beyond CPU-only confidential AI
- Raises the bar for secure inference, fine-tuning, and RL on shared cloud
- Signals a broader race to make attestation and key release default AI controls
What’s the latest?
On November 9, AMD and Google Cloud pushed the story further: Google Cloud’s new TPU 8tx runs on 5th-generation AMD EPYC processors with AMD SEV/Infinity Guard, and Google says it is the first cloud T
How it developed
- AI Governance Becomes the New Control Plane, Confidential Computing Enters Kubernetes Control Plane
- Confidential Computing Moves Into the Kubernetes Control Plane
Go deeper
Curated long-form picks on this trend — podcasts, videos, and analysis, by vantage.
If you operate in this industry
If you sell into this industry
AMD lands a key role in Google's new TPU 8tx AI system
A news analysis of a chipmaker's role in confidential AI computing for cloud-based inference and reinforcement learning.
Crypto Briefing · News
Read →AMD EPYC Expands Its Leadership at the Foundation of AI
A promotional announcement on confidential AI protection in cloud TPU workloads, powered by server CPUs.
AMD · News
Read →Cisco and Fortanix help make confidential AI verifiable from data to Kubernetes
An explainer on bringing hardware-based confidential AI, attestation, and secure key release to Kubernetes.
Cisco Blogs · News
Read →