This post announces the completion of my new tutorial presentation and YouTube video: "Thrill Tutorial: High-Performance Algorithmic Distributed Computing with C++".

YouTube video link: https://youtu.be/UxW5YyETLXo (2h 41min)

Slide Deck: slides-20200601-thrill-tutorial.pdf (21.3 MiB) (114 slides)

In this tutorial we present our new distributed Big Data processing framework called Thrill (https://project-thrill.org). It is a C++ framework consisting of a set of basic scalable algorithmic primitives like mapping, reducing, sorting, merging, joining, and additional MPI-like collectives. This set of primitives can be combined into larger more complex algorithms, such as WordCount, PageRank, and suffix sorting. Such compounded algorithms can then be run on very large inputs using a distributed computing cluster with external memory.

After introducing the audience to Thrill we guide participants through the initial steps of downloading and compiling the software package. The tutorial then continues to give an overview of the challenges of programming real distributed machines and models and frameworks for achieving this goal. With these foundations, Thrill's DIA programming model is introduced with an extensive listing of DIA operations and how to actually use them. The participants are then given a set of small example tasks to gain hands-on experience with DIAs.

After the hands-on session, the tutorial continues with more details on how to run Thrill programs on clusters and how to generate execution profiles. Then, deeper details of Thrill's internal software layers are discussed to advance the participants' mental model of how Thrill executes DIA operations. The final hands-on tutorial is designed as a concerted group effort to implement K-means clustering for 2D points.

The video on YouTube (https://youtu.be/UxW5YyETLXo) contains both presentation and live-coding sessions. It has a high information density and covers many topics.

Table of Contents

• Thrill Motivation Pitch
  • 0:04:08 Benchmarks and Introduction
  • 0:15:08 Tutorial: Clone, Compile, and Run Hello World
• Introduction to Parallel Machines
  • 0:20:20 The Real Deal: Examples of Machines
  • 0:24:50 Networks: Types and Measurements
    • 0:27:02 Round Trip Time (RTT) and Bandwidth
    • 0:29:19 MPI Random Async Block Benchmark
  • 0:31:47 Models
  • 0:35:58 Implementations and Frameworks
• The Thrill Framework
  • 0:39:28 Thrill's DIA Abstraction and List of Operations
    • 0:44:00 Illustrations of DIA Operations
  • 0:55:32 Tutorial: Playing with DIA Operations
  • 1:08:21 Execution of Collective Operations in Thrill
  • 1:21:10 Tutorial: Running Thrill on a Cluster
  • 1:27:02 Tutorial: Logging and Profiling
  • 1:32:14 Going Deeper into Thrill
    • 1:32:49 Layers of Thrill
    • 1:37:59 File - Variable-Length C++ Item Store
    • 1:43:54 Readers and Writers
    • 1:46:43 Thrill's Communication Abstraction
    • 1:48:07 Stream - Async Big Data All-to-All
    • 1:49:46 Thrill's Data Processing Pipelines
    • 1:51:29 Thrill's Current Sample Sort
    • 1:54:14 Optimization: Consume and Keep
    • 1:59:34 Memory Allocation Areas in Thrill
    • 2:01:17 Memory Distribution in Stages
    • 2:02:22 Pipelined Data Flow Processing
    • 2:08:48 ReduceByKey Implementation
  • 2:12:06 Tutorial: First Steps towards k-Means
  • 2:35:56 Conclusion

Due to the coronavirus this year's IPDPS conference is held in a virtual fashion, and we sadly missed a chance to visit New Orleans. Instead, I recorded a YouTube video of our conference talk, because the slides usually are illustrations requiring more explanation.

The paper "Communication-Efficient String Sorting", which I coauthored with Peter Sanders and Matthias Schimek, will still be published in the IEEE proceedings. A preprint of the full paper is available on arXiv:2001.08516 and also from this webpage:

2001.08516v1-Communication-Efficient-String-Sorting.pdf ,

There are two versions of the slides: the longer presentation version below used for the YouTube recording and a short ten page teaser version for the virtual conference.

The source code and more documentation about the implementations of our communication-efficient distributed string sorting algorithms can be found on my GitHub repository https://github.com/bingmann/distributed-string-sorting.

Matthias Schimek's master thesis, on which this paper and presentation are based on, can be downloaded from this website as well.

Below you can watch the video recording of my presentation, or head over to YouTube: https://youtu.be/uWro8fsfs5I.

Today, I presented our paper "COBS: A Compact Bit-Sliced Signature Index" at the 26th International Symposium on String Processing and Information Retrieval (SPIRE) 2019 in Segovia, Spain. The full paper is available from this webpage:

paper-COBS-A-Compact-Bit-Sliced-Signature-Index.pdf ,

from the Springer proceedings in LNCS (same content, somewhat differently typeset), and also from arXiv:1905.09624.

I am honored that our paper won the best paper award at SPIRE'19: bestPaperAward.pdf

The slides of my presentation at the SPIRE conference are available here: slides-20191008-cobs-spire.pdf .

The source code and more documentation about COBS can be found on GitHub:

https://github.com/bingmann/cobs.

Abstract

Today, I gave a presentation of our paper "Scalable Construction of Text Indexes with Thrill" at the IEEE International Conference on Big Data 2018 in Seattle, WA, USA.

The slides of the presentation at the IEEE conference are available here:
slides-Scalable-Construction-of-Text-Indexes-with-Thrill.pdf .

The full paper is available from this webpage: paper-Scalable-Construction-of-Text-Indexes-with-Thrill.pdf or refer to the longer version in my dissertation on scalable suffix array construction.

Abstract

On September 12th, 2018, I gave another 90min talk with live-coding examples in German at the C++ User Group Karlsruhe in rooms of the Karlsruhe Institute of Technology (KIT).

This time I was asked to present a more advanced topic around C++ and libraries and I chose to present a tutorial on Boost.Spirit.

Boost.Spirit is a parser and generator template meta-programming framework and maybe one of the most crazy and advanced uses of C++. It enables one to write context-free grammars inline as C++ code, which are translated into recursive descent parsers and fully optimized by the compiler.

This powerful framework is however not easy to get started with. I hope my tutorial helps more people to skip the steep learning curve and use Boost.Spirit for securely parsing user input and other structure data.

The tutorial consisted of a set of introduction slides: slides-2018-09-12-Cpp-Meetup.pdf . Followed by a live-coding session in German which was recorded by the KIT (see below for the youtube video).

The extensive code examples presented in the live coding session are available on this webpage
or on github: https://github.com/bingmann/2018-cpp-spirit-parsing.

The examples can be seen as instructive templates and copy & paste sources for new development. The examples are:

1. Learn to walk and parse simple integers and lists.
   Parse 5, [5, 42, 69, 256].
2. Create a parser for a simple arithmetic grammar (and part two).
   Parse 5 + 6 * 9 + 42 and evaluate correctly.
3. Parse CSV data directly into a C++ struct.
   Parse AAPL;Apple;252.50; into a struct.
4. Create an abstract syntax tree (AST) from arithmetic (and part two).
   Parse y = 6 * 9 + 42 * x and evaluate with variables.
5. Ogle some more crazy examples, e.g. how to parse.
   <h1>Example for <b>C++ HTML Parser<b></h1>
This HTML <b>snippet</b> parser can also interpret
*Markdown* style and enables additional tags
to <% invoke("C++", 42) %> functions.

Furthermore, a recording of the live-coding in German is available on Youtube:
https://www.youtube.com/watch?v=gYAheppw73U

The road to a Dr. title (PhD in the Anglo-Saxon world) is often long, rough, and twisted. First you have to do original research, produce novel results, publish articles, and then write and ultimately publish a dissertation. Defending your research in the dissertation in front of a panel of professors is one of the final milestones on that journey.

On July 3rd, I successfully defended my dissertation at the Karlsruhe Institute of Technology and the dissertation text has now been published as a book.

Published Dissertation

My final dissertation PDF is available here: dissertation-Bingmann-Scalable-String-and-Suffix-Sorting.pdf .

It has also been published at the KIT library, on arXiv:1808.00963, and finally as a print-on-demand paperback from Amazon.

The published book cover's background shows a list of most common words in the Wikipedia. The words are sorted and their distinguishing prefix is marked in blue. The cover is available as a double-page PDF: dissertation-cover.pdf , and as front and back separately: dissertation-cover-front.pdf and dissertation-cover-back.pdf .

The LaTeX source code for my dissertation is available for download: dissertation-source.zip (791 KiB). The complete text is in one .tex file, all figures (except the creative commons logo) are generated from the LaTeX code.

Dissertation Defense Presentation

The slides of my presentation during the defense are available for download here: dissertation-defense-slides.pdf .

The presentation was only part of the whole defense. My actual slide set also had almost 200 more backup slides, which however were collected from all the other talks already available on this homepage. These backup slides helped greatly in the examination question after the presentation.

On March 8th, 2017, I gave a 90min talk in German at the C++ User Group Karlsruhe which consisted mostly of live-coding examples of how to use new C++11/14/17 features in a practical setting. The contents were:

• Rvalue References and Move Semantics (with Excursions into Lambdas and std::function)
• Virtual Final Override
• Variadic Template Parameter (Un-)Packing
• Random Bits of Thrill

The source code I wrote for the presentation and the slides
are available in a github repository https://github.com/bingmann/2017-cpp-goodies.

Direct link to the slides PDF.

Furthermore, a recording of talk in German is available on Youtube: https://www.youtube.com/watch?v=EvSZHXmXR1M

Today, I gave a presentation of our paper "Thrill: High-Performance Algorithmic Distributed Batch Data Processing with C++" at the IEEE International Conference on Big Data 2016 in Washington D.C., USA. An extended technical report of our paper is also available on this website or on arXiv.

The slides of the presentation at the IEEE conference are available here:
slides-Thrill-High-Performance-Algorithmic-Distributed-Batch-Data-Processing-with-CPP-TalkAsGiven.pdf .

Below a longer version of the slides is available for download:
slides-Thrill-High-Performance-Algorithmic-Distributed-Batch-Data-Processing-with-CPP.pdf .
These slides contain additional figures which are useful to understand the DIA operations in Thrill, along with many extra design slides omitted from shorter talks.

Today, I gave a technical presentation comparing STXXL and Project Thrill at the STXXL Workshop organized within the DFG SPP 1736. The main topic of the workshop was to determine the future development course of STXXL, and the biggest question in this regard was how to bring more multi-core parallelization into STXXL. Thrill or an adaptation of its ideas may be the solution to this challenge: 2016-09-21 STXXL and Thrill Slides.pdf .

Today, we gave an overview presentation of the vision behind Project Thrill, its current state, and how it will be used to implement suffix and LCP array construction, and many other distributed algorithms: 2015-10-01 Massive Suffix Array Construction with Thrill.pdf .

At our institute I gave an ambitious presentation today which showcased much of my daily work flow in emacs. People have titled it the "emacs lightshow" due to the speed of flashing and changing lights on my screens. Of course, the idea is to show people what emacs can do and at the same time get them to try it. Emacs is different from other editors in that it is a life operating system that is infinitely complex, is constantly extended, and adapts to what you need.

For this presentation I made an emacs tutorial. There are many emacs tutorials online, and they are probably better than this one. However, I focused on listing something like the top 100 key command sequences that you need in real day-to-day editing life, instead of the most flashy features. This makes this tutorial something that you can print out, and go through step-by-step once to try everything out; and then start over and learn the most important keys from the top.

The emacs tutorial is available as a PDF: emacs Tutorial - Beating the Learning Curve - From Zero to Lightspeed.pdf

or available as the org-mode source file: emacs Tutorial - Beating the Learning Curve - From Zero to Lightspeed.org

and in my github .emacs.d repo: https://github.com/bingmann/dot-emacs.git

We are very glad to have been given the opportunity to present our work on bulk-parallel priority queues for external memory at the 14th International Symposium on Experimental Algorithms (SEA 2015) in Paris. Our paper is in the proceedings and also available here: paper-SEA15-Bulk-Parallel-Priority-Queue.pdf

The talk was given by Thomas Keh, and the slides of the presentation are available online: 2015-06-29 A Bulk-Parallel Priority Queue in External Memory with STXXL.pdf . The implementation is available in the current master branch of STXXL at github.

Today, I presented our work in progress on a distributed computation platform for Big Data algorithms at the LSDMA All-Hands-Meeting in Berlin. One of the currently proposed names is DALKIT. The talk covers the current state our student project is in, which consists mainly of the design of the framework's interface, architecture and future components.

The slides of the presentation 2015-03-27 Project DALKIT.pdf are available online. However, as usual, my slides are very difficult to understand without the audio track. For future "final" version presentations there will probably be more videos.

This is a recording of a talk that I gave last week at the 3rd LSDMA Topical Meeting in Berlin. The talk covers a basic introduction into the STXXL library's features and contains many short code examples that serve as a tutorial.

The slides of the presentation 2014-06-22 STXXL 1.4.0 and Beyond.pdf are available online and the recorded talk can be seen on Youtube video below.

And here is the video of the recording: https://www.youtube.com/watch?v=UswxcAOJKBE

Today, we presented a shorter version of our work on "Inducing Suffix and LCP Arrays in External Memory" at the MASSIVE Workshop 2013, held adjacently with ESA at ALGO 2013 in Sophia Antipolis, France.

The slides of our presentation 2013-09-05 eSAIS @ MASSIVE'13.pdf and the corresponding short paper massive13esais.pdf are available online via this webpage.

Please refer to the first eSAIS posting for details and source code.

Our thanks goes to all the organizers for making such an inspiring workshop possible.

Today I gave the final completion presentation for my diploma thesis. The talk showcased a selection of results published in the thesis. Results and experiments are only sketched, as all further detailed information can be found in the thesis PDF itself.

The talk contains side-by-side comparison plots of feature enhancements made to ns-3 and verifications thereof using ns-2. Furthermore, the EDCA extensions implemented in ns-3 are tested against analytically calculated reference values. In the end, a speed test comparison is done between ns-2 and ns-3, which uses the implemented classes to run an experiment scenario identically on both simulators.

The slides are available as PDFs in following two variants:

Here the table of contents:

1. Thesis Objectives
2. Enhancements
   1. Propagation Loss Models
   2. Reception Criteria
   3. Frame Capture Effect
   4. EDCA Implementation
3. Speed Comparison
4. Conclusion
5. Appendix
   1. Enlarged Plots and Figures
      1. Propagation Loss Models
      2. Reception Criteria
      3. Frame Capture Effect
      4. EDCA Implementation

For the last three months I have been working intensely on my diploma thesis. The thesis will be about 802.11 enhancements and EDCA QoS extensions in the new network simulator ns-3.

Today I gave my halftime presentation about the current status of my efforts. The talk is composed of a short introduction into ns-3, followed by a detailed discussion of WLAN packet reception criteria and finishes with a review of DCF and how EDCA extends it.

Be warned: many slides are not all self-explanatory and therefore less suitable as a casual introduction into the topics. They are slides meant for presentation.

The slides are available as PDFs in following three variants:

Here the table of contents:

1. ns-3 Basics
   1. Introduction
   2. Showcase: Design Patterns
   3. Current State
2. Wifi in ns-3
   1. State of 802.11
   2. PHY Layer
   3. Signals, Noise and Interference
   4. Short Recapitulation of DCF
   5. QoS with EDCA
3. Conclusion

Following up on the technical report, today Dimitar and myself gave a 70min presentation on Robert Gallager's Minimum Delay Routing Algorithm Using Distributed Computation. It finished my work for the NetFundamentals seminar, which was organized by Decentralized Systems and Network Services Research Group at the Institute of Telematics. The seminar was very profound and extensively dug into the mathematics of six fundamental networking papers. Besides that it was great fun and opened some new horizons.

Our presentation can be downloaded as PDF (553 KB), with two slides per page or even with four per page.

Furthermore our listeners were given an equation sheet (139 KB) to aid them in following the many formulas.

At the University of Karlsruhe it is common to give a concluding talk after finishing a study thesis (Studienarbeit). I presented my study thesis "Visualisation of Very Large Graphs" today at the mid-day seminar of the Theoretical Computer Science Group. The slides of the talk are available as PDFs below:

studythesis-talk-visualisation.pdf (1.6 MB) - also available with two slides per page (1.6 MB)or four slides per page (1.6 MB).

During the talk I showed a movie, in which a r-tree of the autobahnen of Germany is constructed incrementally. I actually produced two movies for this purpose: in the first the edges are added in a given sequential order and in the second the order is randomized. Both movies are encoded using transcode and the XviD codec.

Sequential Movie (3.6 MB)
Randomized Movie (5.1 MB)

The talk was received very well, and I may continue in this field with my diploma thesis.

The visualisation library is used by a route planning algorithm developed at the Theoretical Computer Science Group. By integrating my study thesis it was possible to create a Java web applet which animates the route planning algorithm. The Java applet is currently available at http://algo2.iti.uni-karlsruhe.de/schultes/hwy/demo/.

As part of my work for the SDI Lab work this summer, I held a short talk about how to design a name service in a multi-server operating system like L4.

The slides are available here:

Here the table of contents:

1. Goals
2. Name Catalogs
   1. Object Representation
   2. Catalogs
3. IDL Interfaces
   1. Resolve Interface
   2. Bind Interface
4. Extension / Ideas

Im Sommersemester 2005 habe ich am Praktikum "Real-Life Programming" am IPD Lehrstuhl der UniKa teilgenommen. Hier platt die Beschreibung von der Homepage zitiert:

In diesem Zusammenhang haben zwei Komilitonen und ich einen Vortrag über "Objekt-orientiertes Programmieren in C" (ohne ++) ausgearbeitet und gehalten. Weiteres Schwerpunktthema war die Darstellung von C++ in Maschine, also wie der C++ Übersetzer dann die Klassen abbildet.

Hier noch ein Auszug des Inhaltsverzeichnisses:

1. Objekt-Orientierte Konzepte
2. OO in C
   • Kapselung und Geheimnisprinzip
   • Vererbung und Polymorphie
   • Generiztiät
3. Darstellung von C++ in Maschine
   • vtable
   • Name-Mangling
   • Run-Time-Type Information (RTTI)

Diese Folien geben einen kompetenten Überblick über den Themenbereich.