atuladya

Right - this is not about sharding data/datasets. This is for sharding in-memory state that a service might have. The problem of building services at low cost, high scale, low latency and high throughput is common in many environments including our services at Databricks, and Dicer helps with that.

It is similar to Slicer in terms of the abstraction (I built Slicer at Google) but the architecture, implementation and algorithms have a lot of differences