Future workloads drive the need for high performant and adaptive computing hardware

As big data pushes the need for high-performance and adaptive computing beyond the exascale threshold, the pressure is on to find computing architectures that meet the right mix of price, performance, and power efficiency to support cost-effective data center scalability, acceleration of applications that drive higher end-user productivity and faster time to insights and lower power consumption for sustainability. This will require heterogeneous architectures that combine traditional CPUs and GPUs with innovative accelerators to meet the ever-growing demand of big-data-driven workloads. Endpoints connected to the cloud are being infused with intelligence through sensors, cameras and other devices and are creating massive amounts of mostly unstructured data. Processing this data is driving demand for new workloads such as machine learning. Adaptive computing allows for compute and connectivity hardware that can adapt to the workload and efficiently process data in use, in motion and at rest.