Confidential Computing within an AI Accelerator
Offered By: USENIX via YouTube
Course Description
Overview
Explore a groundbreaking conference talk from USENIX ATC '23 that introduces IPU Trusted Extensions (ITX), a set of hardware extensions enabling trusted execution environments in Graphcore's AI accelerators. Delve into the innovative approach to confidential computing within AI hardware, offering strong confidentiality and integrity guarantees with minimal performance impact. Learn how ITX isolates workloads from untrusted hosts, ensures data and model encryption, and incorporates a hardware root-of-trust for attestation and trusted execution orchestration. Discover the on-chip programmable cryptographic engines that provide authenticated encryption at PCIe bandwidth. Gain insights into the accompanying software developments, including compiler and runtime extensions supporting multi-party training without CPU-based TEEs. Examine the experimental implementation of ITX in Graphcore's GC200 IPU, taped out at TSMC's 7nm node, and its impressive performance results showing less than 5% overhead and up to 17x better performance compared to CPU-based confidential computing systems using AMD SEV-SNP.
Syllabus
USENIX ATC '23 - Confidential Computing within an AI Accelerator
Taught by
USENIX
Related Courses
IoT Product SecurityCybrary Trusted Execution Environments Meet the Blockchain
Simons Institute via YouTube Cache Side Channel Attack - Exploitability and Countermeasures
Black Hat via YouTube Confidential Computing in Cloud and Edge
RSA Conference via YouTube The Rise of Confidential Computing
RSA Conference via YouTube