back to list

Project: Achieving main-memory query processing performance on secondary storage on graph query workloads

Description

Since DRAM is still relatively expensive and contemporary graph database workloads operate with billion-node-scale graphs, contemporary graph database engines still have to rely on secondary storage for query processing. 

In this project, we explore how novel techniques such as variable-page sizes and pointer swizzling can help building a buffer manager in a modern graph database with the aim of achieving near main-memory speeds.

Prerequisites: very good C++ knowledge, taken and succeeded in the "Engineering Data Systems" (2IMD10) course.

Details

Supervisor

Nick Yakovets

Secondary supervisor

Bram van de Wall

Interested?

Get in contact