Workhorse in the Computing Cloud for Next Generation HPC Data Centers
IBM has been the leading provider of High Performance Computing (HPC) solutions across a wide range of application and industry segments over the last few decades. This strategy of alleviating customer pain points by delivering a rich portfolio of innovative solutions has been the cornerstone of IBM’s long term success in HPC. With the iDataPlex, a new system design that leverages industry standard processor to address the needs of next generation data centers, IBM plans to extend current HPC cluster solutions by providing an economical architecture that can increase computing density in a standard enterprise rack and scale‐out to 1000s of racks.
HPC Cluster Growth is Robust … but Data Center Challenges Must be Overcome
Scientists, engineers, and analysts eager to solve challenging problems in engineering, financial markets, and the life and earth sciences rely on high performance systems. These users are some of the most demanding clients of IT solutions. Their insatiable demand for computational performance continues to drive high performance computing platforms towards increasing system scalability, larger computing density, lower power consumption, efficient system cooling, easier and more reliable system management, and adaptable programming environments.
Multiple industry studies indicate that revenue from HPC servers will continue to grow much faster than overall server revenues with clusters being the dominant platform –almost 70 percent of HPC servers.1 But, these studies also suggest that the costs of server management, power and cooling, and facilities management in HPC data centers will outpace the costs of buying new servers. This has caused a severe crisis in HPC data centers. And IT solution providers such as IBM have responded by designing innovative solutions that address these issues while retaining all the attractive attributes of industry‐standard cluster architectures for HPC.