This blog describes the potential Speculative Return Stack Overflow (SRSO) vulnerability, why AMD believes that the overall security risk associated with this potential vulnerability is low in typical production environments, and points to resources with additional information.

There is no one set journey to AI enablement.  AI (and the infrastructure to run it) will take many forms. Many enterprises will follow different paths based on their specific goals, business and technical priorities and other considerations. But no matter where your enterprise is ultimately headed in the AI era, AMD EPYC processor-powered servers offer the platform to take you there as your needs evolve.

The tech industry is in a perpetual struggle to achieve equilibrium between compute, storage and networking for maximum performance. For now, storage—or, more precisely, the location of large data sets—is the problem, and chiplets, pioneered by AMD, is one solution.

The new AMD EPYC 97X4 Processors, are the highest-performing members of the processor family formerly code-named “Bergamo”. These processors offer no-compromise performance, density, and energy efficiency for containers, cloud native computing, and modern applications.

This week, we introduced two additional processor models to the 4th Gen AMD EPYC™ processor family at the Datacenter and AI Technology Premier. I am excited to take this opportunity to provide an update on the software ecosystem readiness and showcase some of the performance proof points for the AMD EPYC 97x4 processors.

The Tencent Accelerated Computing Optimizer (TACO) Kit integrates the ZenDNN AI inference library for improved inference performance on AMD EPYC™ CPU backends, enabling Tencent's end customers to evaluate and deploy optimal solutions for their diverse workloads, particularly in the face of growing hardware heterogeneity.

Microsoft Azure Confidential Computing Powered by 3rd Gen EPYC™ CPUs Deliver Advanced Data Protection With Minimal Workload Performance Impact

To meet its customers’ computing needs, AMD and AWS have collaborated to create distinct types of cloud instances designed to meet specific application needs: AMD-powered Amazon Elastic Compute Cloud (EC2) instances are available in four categories: general-purpose (M5a & M5ad), general-purpose burstable (T3a), memory optimized (R5a & R5ad), and now compute-optimized (C5a & C5ad).

It is exciting to observe the rapid evolution of the cloud high-performance computing market and to think of what it can mean for customer innovation. Just a year ago, Microsoft Azure was the first to run a 10,000 core Simcenter STAR-CCM™+ job in the cloud with AMD EPYC processor-based HB-series VMs. This run proved the viability of large-scale cloud HPC while showcasing impressive performance that rivals on-premises HPC clusters. Azure customers shared resoundingly positive feedback about how this newfound scale helped them to accelerate research and be more productive.