In-Memory Databases: Algorithms and Data Structures on Modern Hardware (Sommersemester 2013)

Lecturer: , Christian Schwarz (Enterprise Platform and Integration Concepts)
Course Website: https://epic.hpi.uni-potsdam.de/Home/InMemoryDatabasesSeminarSoSe2013

General Information

• Weekly Hours: 4
• Credits: 6
• Graded: yes
• Enrolment Deadline: 10.2.2013 - 30.4.2013
• Teaching Form: Seminar
• Enrolment Type: Compulsory Elective Module
• Maximum number of participants: 15

Programs, Module Groups & Modules

Description

The goal of the research seminar is to teach the students the basics of scientific research and a basic knowledge of the inner mechanics of in-memory databases. The seminar is focused on implementation concepts for columnar in-memory database systems on modern hardware. Hence, each student will work individually on a topic, resulting in a final paper (10-12 pages, IEEE) plus a midterm and final presentation. The topics vary from basic data structure concepts to in-memory optimised algorithms. Each topic will have an implementation component, which should be evaluated in the resulting paper.

 

Goals of the Seminar:

Understand:

• In-Memory Database technology
• Scientific Working

Do:

• Performance experiements on modern hardware
• Evaluation of findings

Improve:

• Presentation skills
• Coding skills
• Scientific writing

 

Seminar Topics:

 Data Structures:

• Partitioned Bitvector
• Vertical Bitvector
• Unsorted Dictionaries

Indices:

• Default Value Index
• Multi Column Indices

Join Algorithms:

• Multi Column Join Algorithms
• Join Algorithms on shared Dictionaries
• Cache-Optimized Parallel Join

Database Co-Processor:

• Execution model for co-processors
• Co-processor integration into databases
• Automatic execution unit detection in a heterogeneous system
• Optimized co-processor data structures
• Automatic code optimization for co-processors

User-Interface:

• Analytical User Interface for HYRISE
• Set-based Query Language

Other:

• Branching Deltas (Simulation)
• Result Set Compression
• Memory Compression Algorithms in Hardware (PPC)

Literature

We will provide relevant literature to the project teams according to §52a UrhG. The provided literature shall be used as an introduction into the topic. It does not cover the complete topic.

Examination

The following components determine the final mark:

• Mid-term Presentation (10%)
• Final Presentation (20%)
• Research Results (30%)
• Paper (30%)
• General Participation (10%)

All of the components must be passed in order to pass the seminar.

Dates

Dienstag/Mittwoch 9:15-10:45. The seminar will mostly be held in individual meetings.

Meetings (Room V-2.16):

• 16.04.2013 - 9:15: Introduction and Topics
• 17.04.2013 - 9.15: Main Memory DB Introduction
• 28./29 Mai: Zwischenpräsentation (voraussichtlich)
• 9./10. Juli: Abschlusspräsentation (voraussichtlich)
• 26. Juli: Abgabge Paper

Zurück