Reducing Data Movement Costs Using Energy-Efficient, Active Computation on SSD
Source: North Carolina State University
Modern scientific discovery often involves running complex application simulations on supercomputers, followed by a sequence of data analysis tasks on smaller clusters. This offline approach suffers from significant data movement costs such as redundant I/O, storage bandwidth bottleneck, and wasted CPU cycles, all of which contribute to increased energy consumption and delayed end-to-end performance. Technology projections for an exascale machine indicate that energy-efficiency will become the primary design metric. It is estimated that the energy cost of data movement will soon rival the cost of computation. Consequently, the authors can no longer ignore the data movement costs in data analysis.