Modal taps Nvidia Vera CPUs after firm's internal tests show 2x throughput over Intel and AMD chips
Nvidia's Vera CPU delivers twice the performance of Intel and AMD chips in AI agent workloads, Modal claims.
Nvidia has secured a major design win with AI cloud provider Modal, after internal tests showed that its new Vera CPUs could deliver twice the throughput of AMD and Intel processors. Reuters reports that Modal currently relies on AMD and Intel processors for AI workloads, but its tests with Vera indicate a significant performance improvement.
Modal provides cloud infrastructure for AI developers to deploy agents that can perform complex operations independently over extended periods, requiring substantial CPU resources. The company's decision to adopt Vera's Arm instruction set architecture will necessitate substantial software modifications. However, Modal believes the potential performance gains justify the additional engineering effort.
The reported 2x throughput advantage is notable because agentic AI workloads involve numerous independent tasks competing for CPU cores, cache, and memory bandwidth. Modal's CEO, Erik Bernhardsson, stated that while the company will continue using x86 CPUs from AMD and Intel, it aims to operate a heterogeneous server fleet and choose the most suitable processors for each workload.
Nvidia expects Vera sales to generate at least $20 billion during its fiscal year and anticipates the potential total available market to be around $200 billion.
Written by urgent.news from Tom's Hardware's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.