Skip to main content
  1. Blog
  2. Article

Mark Baker
on 13 May 2014

Fast with an extra helping of faster


Today AMD announced a set of industry benchmark performance records for hyperscale OpenStack running on Ubuntu OpenStack (Icehouse) and AMD’s SeaMicro SM15000™ system. The benchmarking, which is the largest known demonstration of OpenStack scalability ever, highlights how OpenStack can quickly and reliably provision on-demand computing. As a result, there are three new benchmark records set:

  • The first created 75,000 VMs and in just 6.5 hours; this is a whole 1.5 hours faster than any previous record and days faster than a usual implementation of this scale.

  • The second benchmark of 100,000 VMs on 380 hosts, blows past the previous record in a speedy 11 hours.

  • The third, possibly the most notable, is the number of VMs that could be launched with the hardware; the benchmark reached 168,000 VMs with 576 physical hosts.

These benchmark records were made possible thanks to the integration of our own Metal as a Service (MAAS) tool, combined with SeaMicro SM15000 provisioning API. MAAS automates the deployment of Ubuntu and is finely tuned to do so exceptionally quickly, meaning systems can be provisioned at scale. The solution is available today and is the most scalable, automated application for deploying OpenStack in hyperscale environments.

At the OpenStack summit this week, Disney’s Chris Launey talked about the need for speed in cloud is paramount. The previous choice of fast or cheap is now fast and fast and if you give a developer enough fast, they will make their own cheap. Speed matters and Ubuntu OpenStack on the SM15000 can deliver that – the numbers speak for themselves.

Read all about it at here in AMD’s press release.

Related posts


Canonical
27 May 2026

Introducing Workshop: launch sandboxed development environments on Ubuntu with a single command

Canonical announcements Article

Developers now benefit from consistency and repeatability for cutting-edge workflows, including agentic AI. Today, Canonical announced the release of Workshop, a solution for launching development environments with a single command. These environments are configured once, and can be reproduced on different machines. This means consistent ...


Youssef Eltoukhy
26 May 2026

Run agentic workloads on Arm and Ubuntu

AI Article

In the lead-up to Ubuntu Summit 26.04, Canonical and Arm are collaborating to certify the new Arm AGI CPU on Ubuntu 26.04 LTS (Resolute Raccoon). Learn what this means for developers and agentic AI. ...


Abdelrahman Hosny
21 May 2026

Developing web apps with local LLM inference

AI Article

I’ve yet to meet a developer that enjoys working with metered AI APIs. The need to pay for every API call in development works in direct opposition to the ethos of rapid iteration, and it’s easy for the costs to get out of hand. That’s why Canonical has created a different approach to building AI-powered ...