Optimize Budgets and Performance with AMD EPYC™ Processors
Jun 09, 2023

Reducing Server Counts to Save TCO
In the same scenario above, running those same 2,000 VMs on 11 AMD CPU-powered servers could lower CAPEX an estimated 46%, and have 21% lower first year TCO per VM versus the 17 servers powered by the competition.
In addition to saving energy costs, IT leaders will find that deploying 4th Gen AMD EPYC processors will help with managing other expenses such as freeing up rack space as well by requiring fewer servers to do the same work, benefitting the bottom line.
Imagine being able to meet the computing needs of the business, all while generating OPEX savings and shrinking your data center footprint.
The Cost of Doing Nothing
Even with dramatically increasing energy costs and pressure to deliver data center performance for new and emerging workloads, it can be tempting to wait to upgrade your data center. The average age of servers in data centers is three to five years. The potential cost and effort to upgrade can appear overwhelming, even when there are more powerful, more efficient servers requiring less footprint available.
However, there is a cost to choosing to wait. Older servers can be more costly to maintain than newer servers. They can have more downtime. They can’t always keep pace with increased business demands, and new workloads such as advanced analytics, artificial intelligence/machine learning, and new use cases and delivery models, including containers and other cloud-native software. There is a cost to choosing to do nothing.
Consider a scenario based upon using 380 VMs using the Intel® Xeon® 2P Platinum 8180 “Skylake” server, which was very popular about five years ago. Running this number of VMs would require five of these servers compared to only one server using a pair of 96-core EPYC 9654 processors. This server consolidation results in 80% fewer servers, resulting in an estimated 65% less power and a 58% lower TCO over three years. ³ This kind of savings allows for not just cost savings, but flexibility for future growth and the ability to meet the needs of newer workloads without sacrificing performance.
Cost Savings, No Trade-offs
4th Gen AMD EPYC™ processors enable significantly reduced TCO with exceptional time to results for business-critical applications. Find out more about what the latest AMD server processors can do for you.
Today, more than ever, the pressure is on for IT departments to manage spending and optimize their investments. The 4th Gen AMD EPYC™ processor can play a major role in helping manage CAPEX and OPEX spending by maximizing energy efficiency while still delivering leadership performance, allowing IT leaders to deliver the exceptional time to results required by their business-critical applications while enabling reduced total cost of ownership.
Virtualization and Energy Efficiency
Efficiency is critical to reducing TCO for virtualization deployments, including packing the most compute into the smallest space and power consumption. 4th Gen AMD EPYC™ processors power the most energy efficient x86 servers.¹ At the top of the stacks, compare a 2P AMD EPYC™ 96 core 9654 CPU powered server with the competition: a 2P server based on the Intel® Xeon® Platinum 8490H. Only 11 AMD servers are needed to deliver 2,000 VMs, compared with 17 competitively powered servers; requiring up to 35% fewer servers and saving an estimated 29% on energy costs – over three years. That is the carbon sequestration equivalent of 38 acres of US forest each year of the analysis.²
And that’s just for a small number of servers. An enterprise running thousands of servers could realistically save millions of dollars by adopting 4th Gen AMD EPYC™ processors, all while helping their larger organizations advance their broader sustainability goals.
Resources
- SP5-072: A 4th Gen EPYC 9654 powered server has highest overall scores in key industry-recognized energy efficiency benchmarks SPECpower_ssj®2008, SPECrate®2017_int_energy_base and SPECrate®2017_fp_energy_base. See details at https://www.amd.com/en/claims/epyc4#SP5-072
- SP5TCO-036: As of 01/18/2023 based on AMD Internal analysis using the AMD EPYC™ Server Virtualization & Greenhouse Gas Emission TCO Estimation Tool - version 12.10 estimating the cost and quantity of 2P AMD 96 core EPYC™ 9654 powered server versus 2P Intel® Xeon® 60 core Platinum 8490H based server solutions required to deliver 2000 total virtual machines (VM), requiring 1 core and 8GB of memory per VM for a 3-year period. This includes VMware software license cost of $6,558.32 per socket + one additional software for every 32 CPU core increment in that socket. Environmental impact estimates made leveraging this data, using the Country / Region specific electricity factors from the '2020 Grid Electricity Emissions Factors v1.4 – September 2020', and the United States Environmental Protection Agency 'Greenhouse Gas Equivalencies Calculator'. This scenario contains many assumptions and estimates and, while based on AMD internal research and best approximations, should be considered an example for information purposes only, and not used as a basis for decision making over actual testing. For additional details, see https://www.amd.com/en/claims/epyc4#SP5TCO-036.
- SP5TCO-022B: As of 02/28/2023 based on AMD Internal analysis using the AMD EPYC™ Bare Metal Server & Greenhouse Gas Emission TCO Estimation Tool - version 8.22, estimating the cost and quantity of 2P AMD EPYC™ 9654 (96 core/CPU) powered server versus 2P Intel® Xeon® Platinum 8130 (28 core/CPU) based server solutions required to deliver 380 total virtual machines (VM), requiring 1 core and 8GB of memory per VM. Environmental impact estimates made leveraging this data, using the Country / Region specific electricity factors from the '2020 Grid Electricity Emissions Factors v1.4 – September 2020', and the United States Environmental Protection Agency 'Greenhouse Gas Equivalencies Calculator'. This scenario contains many assumptions and estimates and, while based on AMD internal research and best approximations, should be considered an example for information purposes only, and not used as a basis for decision making over actual testing. For additional details, see https://www.amd.com/en/claims/epyc4#SP5TCO-022B.