"An ERP Platform Strategy Based on Industry-standard Servers
IT@Intel White Paper, Intel Information Technology Enterprise Resource Planning, March 2010
Executive Overview
Many large organizations have a centralized enterprise resource planning (ERP) environment based on proprietary mainframes or RISC-based systems. In contrast, Intel IT has successfully implemented a decentralized ERP environment that is based on industry-standard servers and supports more than 10,000 active users. We have found that this approach offers several advantages, including lower server acquisition costs and increased flexibility and agility.
Four-socket servers perform essential roles within this environment, providing the performance, memory capacity, I/O expandability, and reliability required to run our larger production ERP instances. These servers also provide enough headroom for anticipated growth of large production ERP databases over the depreciation cycle of the server. We use two-socket servers for smaller production instances and a variety of non-production uses.
Compared with two-socket servers based on Intel® Xeon® processor 5600 series, four-socket servers based on Intel® Xeon® processor 7500 series have key characteristics that enable them to support more demanding ERP requirements: greater performance headroom to support workload growth, demand spikes, and failover situations
Four-socket servers perform essential roles within this environment, providing the performance, memory capacity, I/O expandability, and reliability required to run our larger production ERP instances. These servers also provide enough headroom for anticipated growth of large production ERP databases over the depreciation cycle of the server. We use two-socket servers for smaller production instances and a variety of non-production uses. Compared with two-socket servers based on Intel® Xeon® processor 5600 series, four-socket servers based on Intel® Xeon® processor 7500 series have key characteristics that enable them to support more demanding ERP requirements: Greater performance headroom to support workload growth, demand spikes, and failover situations.
Read the full

