AI-powered
podcast player
Listen to all your favourite podcasts with AI-powered features
The Benefits of Partition Parallelism in Data Mining
The idea is that if we clump this data together geographically across the different servers, so each server has a geographic area where the data is. When we run our queries, we're more likely to be instead of trying to pull geographies from four or five different servers for all of those geographies which exist on the same server because they're close to each other. So in that case, you did what we call partition parallelism where you partition the data and go partition the due data set based on the spatial proximity following the first law of geography.