European Parliament Endorses EuroHPC Exascale Initiative

Throughout the year, Hyperion Research uses our surveys to ask buyers about near-term expectations for their spending on HPC. We ask whether, in the next quarter, they expect the amount they spend to increase, decrease or stay the same. If they expect spending to go up or down in the next quarter, we ask by what percentage. The questions and resulting data are not limited to servers but also include anticipated spending on cloud usage and on desktop computers. We then use this data collected over multiple quarters, along with historical revenue patterns and other sources, to help us generate our HPC market forecasts.

Traditional HPC architectures have typically been designed to address either homogenous workloads (such as physics-based modeling and simulation) with similar, and perhaps more important, fixed, compute, memory, and I/O requirements or, more recently, heterogenous workloads with a diverse range of compute, memory, and I/O requirements. Most HPC data center planners and operators, however, don't have the luxury of focusing on one main type of workload; they typically must support many HPC users and their associated workloads sporting a wide range of compute, memory, and I/O profiles. Architectures have typically consisted of a fixed set of resources, resulting in an underutilized system with expensive elements often sitting idle for long periods of time. One approach being explored to increase system utilization by exposing resources that would otherwise sit idle to appropriately matched jobs waiting in a queue is via composable systems.