November 10, 2021 By Amartey Pearson 3 min read

Time is the new metric for efficiency. Quickly accessing data how you want, from anywhere, at any time is what 3rd Gen AMD EPYC™ Processors can help deliver to our IBM Cloud Bare Metal Server clients.

Now that IBM Cloud has released Bare Metal Servers using the newly released third-generation AMD EPYC™ processors, it’s time to see what all the buzz is about. IBM has gone big with the high-end, dual-socket EPYC 7763 processors. Because this is IBM Cloud Bare Metal, you get full access to the hardware — and that’s a whopping 128 cores (256 threads) of processing power topping out at 3.5 GHz [1]. That’s plenty of processing power for the up to 4 TB of memory and 10 NVMe drives.

This is the first time IBM Cloud has offered 128 cores in anything other than an 8-socket server. This is a big win for you, getting peak efficiency in a 1U server that takes up just a single rack slot. Add in up to 4 TB of memory in the same package, and you’ve got an impressive server with raw performance at an excellent price/performance ratio.

At a glance

  • CPU: 64 cores per CPU (128 cores per server)
  • Frequency: 2.4GHz up to 3.5 GHz
  • Storage: up to 10 NVMe SSDs
  • Network: 2x10Gb Public + 2x10Gb Private
  • Price: Starting at $550/month

Aren’t 128 cores with 4 TB of memory overkill?

Yes, absolutely it is — for a lot of workloads. But some will truly benefit from the high core count (not to mention per-core performance), large memory capacity, high memory bandwidth and PCIe Gen4 I/O. Just what you need for compute-intensive 3D rendering, HPC workloads, large scale databases and virtualized environments — to name just a few.  

So, look at your workload. If this seems like overkill, it probably is. But chances are, if you’re running a workload that would benefit from a system like this, you’ll know it! Check out these AMD on IBM Cloud solution briefs to get an idea of some target workloads.

This all sounds great, but won’t switching be hard?

In most cases, no. Running on Intel vs. AMD processors should be drop-in seamless. All major operating systems provide full support for AMD. As with most things though, it won’t always work out that way. For example, you might find specific libraries you depend on that are optimized for one processor over another. Things will still work but might not perform as well as you were hoping. 

Finally, there are always questions about security. Processor security has been in the news a lot lately — and the processor vendors are paying attention. For those looking to run virtualized workloads and host a multi-tenant environment, it’s worth looking at AMD Secure Encrypted Virtualization (SEV) [2]. In short, this encrypts the memory for each virtual machine (VM) with its own key, adding an additional security layer between VMs.  

Get started  

Does this sound like it might be what you’re looking for? Go try it out today, or contact your sales representative. The ordering process is no different than ordering any other IBM Cloud Bare Metal Server — just a few clicks to customize it, wait a few hours for it to be built to your specs and away you go. You can be one of the first to experience all the AMD EPYC™ 7763 processor can deliver.

To learn more about AMD on IBM Cloud Bare Metal Servers, visit our website.

 

[1] Max boost for AMD EPYC processors is the maximum frequency achievable by any single core on the processor under normal operating conditions for server systems. EPYC-18

[2] AMD Infinity Guard features vary by EPYC™ Processor generations. Infinity Guard security features must be enabled by server OEMs and/or Cloud Service Providers to operate. Check with your OEM or provider to confirm support of these features. Learn more about Infinity Guard here. GD-183

More from Announcements

Success and recognition of IBM offerings in G2 Summer Reports  

2 min read - IBM offerings were featured in over 1,365 unique G2 reports, earning over 230 Leader badges across various categories.   This recognition is important to showcase our leading products and also to provide the unbiased validation our buyers seek. According to the 2024 G2 Software Buyer Behavior Report, “When researching software, buyers are most likely to trust information from people with similar roles and challenges, and they value transparency above other factors.”  With over 90 million visitors each year and hosting more than 2.6…

Manage the routing of your observability log and event data 

4 min read - Comprehensive environments include many sources of observable data to be aggregated and then analyzed for infrastructure and app performance management. Connecting and aggregating the data sources to observability tools need to be flexible. Some use cases might require all data to be aggregated into one common location while others have narrowed scope. Optimizing where observability data is processed enables businesses to maximize insights while managing to cost, compliance and data residency objectives.  As announced on 29 March 2024, IBM Cloud® released its next-gen observability…

Unify and share data across Netezza and watsonx.data for new generative AI applications

3 min read - In today's data and AI-driven world, organizations are generating vast amounts of data from various sources. The ability to extract value from AI initiatives relies heavily on the availability and quality of an enterprise's underlying data. In order to unlock the full potential of data for AI, organizations must be able to effectively navigate their complex IT landscapes across the hybrid cloud.   At this year’s IBM Think conference in Boston, we announced the new capabilities of IBM watsonx.data, an open…

IBM Newsletters

Get our newsletters and topic updates that deliver the latest thought leadership and insights on emerging trends.
Subscribe now More newsletters