Shimon Ben-David

A decade’s worth of moving compute to the data has led to great focus on "data gravity": the tendency of a data store to attract a mass of applications that need to be near to it. The concept is often invoked as an obstacle to moving data stores, such as from on prem to the cloud.

Innovations like NVMe over fabrics, storage class memory, and the software to leverage them have promised radical shifts in throughput/latency/cost tradeoff curves. These technologies have now been in the market long enough to undergo considerable tire kicking, proofs of concept, and initial implementations.

Ever-increasing demands from the business, the growth of new AI workloads, and the increasing pull of public clouds call for faster and more flexible ways to get data where it’s needed in computations. Fortunately, the vendor community is competing and collaborating to solve these problems.