Seminar: Techniques for implementing main memory database systems

Information

Content

In this seminar we deal with techniques for implementing main memory database systems and related topics.

Prerequisites

  • lecture Fundamentals of Databases (Grundlagen Datenbanken, GDB) or similar course
  • very good knowledge in data bases, good programming skills in C++

Dates & Deadlines

  • Organizational meeting: Wednesday, July 07, 2021 at 14:00 (online on BigBlueButton)
  • Slides of the organizational meeting: slides
  • Register for the course through the matching platform
  • Regular meeting: Monday, 16:00 - 18:00, MI 02.09.014 (we may have to switch to BBB)
  • First session: 15.11.2021

Schedule

15.11.2021 - Session 1

  • Filter Representation in Vectorized Query Execution
  • Scalable garbage collection for in-memory MVCC systems
Deadlines
  • 18.10.2021: General Structure
  • 08.11.2021: Slides
  • 15.11.2021: Presentation Date
  • 29.11.2021: Paper & Implementation

22.11.2021 - Session 2

  • Automatic Optimization of Matrix Implementations for Distributed Machine Learning and Linear Algebra
  • Contention and Space Management in B-Trees
Deadlines
  • 25.10.2021: General Structure
  • 15.11.2021: Slides
  • 22.11.2021: Presentation Date
  • 06.12.2021: Paper & Implementation

29.11.2021 - Session 3

  • Scalable Structural Index Construction for JSON Analytics
  • Small Selectivities Matter: Lifting the Burden of Empty Samples
Deadlines
  • 01.11.2021: General Structure
  • 22.11.2021: Slides
  • 29.11.2021: Presentation Date
  • 13.12.2021: Paper & Implementation

06.12.2021 - Session 4

  • FSST: Fast Random Access String Compression
  • Optimistic Lock Coupling: A Scalable and Efficient General-Purpose Synchronization Method (moved from 13.12)
Deadlines
  • 08.11.2021: General Structure
  • 29.11.2021: Slides
  • 06.12.2021: Presentation Date
  • 20.12.2021: Paper & Implementation

13.12.2021 - Session 5

  • Optimistic Lock Coupling: A Scalable and Efficient General-Purpose Synchronization Method (moved to 06.12)
Deadlines
  • 15.11.2021: General Structure
  • 06.12.2021: Slides
  • 13.12.2021: Presentation Date
  • 27.12.2021: Paper & Implementation

Topic List

Topic Supervisor Student
Optimistic Lock Coupling: A Scalable and Efficient General-Purpose Synchronization Method Jan Böttcher L.W.
Scalable garbage collection for in-memory MVCC systems Jan Böttcher J.O.
Releasing Locks As Early As You Can: Reducing Contention of Hotspots by Violating Two-Phase Locking Dominik Durner A.P.
Rethink the Scan in MVCC Databases Dominik Durner tbd
Scalable Structural Index Construction for JSON Analytics Dominik Durner J.K.
Small Selectivities Matter: Lifting the Burden of Empty Samples Philipp Fent M.F.
Contention and Space Management in B-Trees Philipp Fent C.R.
FLAT: Fast, Lightweight and Accurate Methodfor Cardinality Estimation Philipp Fent tbd
FSST: Fast Random Access String Compression Michael Freitag L.H.
Interleaving with Coroutines: A Practical Approach for Robust Index Joins Michael Freitag tbd
Filter Representation in Vectorized Query Execution Alice Rey J.S.
KallaxDB: A Table-less Hash-based Key-Value Store on Storage Hardware with Built-in Transparent Compression Alice Rey tbd
Automatic Optimization of Matrix Implementations for Distributed Machine Learning and Linear Algebra Maximilian Schüle tbd
LIMA: Fine-grained Lineage Tracing and Reuse in Machine Learning Systems Maximilian Schüle tbd
Fast CSV Loading Using GPUs and RDMA for In-Memory Data Processing (GPU required) Maximilian Schüle tbd

Material