Basic Information

News

Report

The final project reports are due 01/16/15. Please send them to timos@inf.ethz.ch.

Course overview

This course exposes students to the principal issues involved in software development for parallel computing and discusses a number of approaches to handle the problems and opportunities caused by the increased availability of parallel platforms.

The course includes lectures, assignments, self-study, and a project. 50% of your grade is determined by project work and 50% is determined by a written exam; the exam is given during the official examination period, and there is no makeup exam. Students must be able to program using Java and C/C++.

The course may cover: memory coherence and consistency models, implications for language-specific memory models, Java memory model, models of parallel programming and parallel program execution, performance models for parallel systems, transactional memory, compiler extraction of parallelism, language and compiler support for parallel programming, threads and their execution environment, synchronization, and implementation issues of these topics.

Course schedule

Lectures are given Mondays 13:15 - 16:00 in LEE D 101.

Recitation sessions take place Thursdays 13:15 -- 15:00 in LEE D 101 and take place when announced. Some of the lecture hours will be devoted to other activities (tutorials, reviews, etc) or will be devoted to group meetings. Please watch this page for updates and announcements.

Tentative schedule of lectures

Week Monday Thursday
0 09/15: no lecture due to master students information day 09/18: MPI Tutorial
2 09/22: Organization (1up, 6up) and Introduction (1up, 6up) 09/25: Projects (1up, 6up) and Advanced MPI tutorial
3 09/29: no lecture 10/02: OpenMP tutorial
4 10/06: Cache Coherence (1up, 6up), Additional Material to brush up your knowledge on caches here and here 10/09: Cache Coherence Tutorial
5 10/13: Memory Models (1up, 6up) 10/16: Sequential Consistency and TM Tutorial
6 10/20: Linearizability (1up, 6up) 10/23: Linearizability
7 10/20: Languages and Locks (1up, 6up) 10/23: Linearizability Solution, Project Presentation
8 11/03: Project Presentation, Locks and Lock Free(1up, 6up) 11/06: Locks solution, Quiz on OpenMP, MPI and General Concepts Quiz
9 11/10: Locks and Lock Free(1up, 6up) 11/13: Quiz Solution
9 11/17: Amdahl's Law(1up, 6up), Notes 11/20: Amdahl's Law, PRAM
10 11/24: Roofline Model, Balance Principles (1up, 6up), Notes 11/27: Project Presentations
11 12/01: Scheduling (1up, 6up), Lock Free and Distributed Memory (1up, 6up) 12/04:
12 12/08: Distributed Memory Algorithms (1up, 6up) 12/11:

Groups and assistants

Thursday 13:15 - 15:00
Room Assistant Email
LEE D 101 Timo Schneider timos at inf.ethz.ch
LEE D 101 Arnamoy Bhattacharyya arnamoy.bhattacharyya at inf.ethz.ch

Mailinglist

If you want to discuss issues related to the class, please subscribe to the class mailinglist. This list is read by the instructors as well as the TA, and any student of the class who voluntarily subscribed to it. So it is a great place to discuss questions about homework or the lecture slides.

Assignments

Assignments are an important part of the course. You will not learn this material from listening to a lecture alone -- you have to do the assignments.

Note: Do not hesitate to write an email to your TA if you have trouble with the assignments!

Number Assignment Out Description Solution
1 Assignment 1 09/18 Parallel Pi with MPI Solution
2 Assignment 2 10/02 Matrix Multiplication with OpenMP and MPI Solution
3 Assignment 3 10/09 Caches, MESI Protocol, False Sharing Solution
4 Assignment 4 10/16 Sequential Consistency Solution
5 Assignment 5 10/23 Linearizability Solution
6 Assignment 6 10/30 Locks Solution
7 Assignment 7 11/06 Locks 2 Solution
8 Assignment 8 11/14 Locks 3 Solution
9 Assignment 9 11/20 Amdahls Law, PRAM Solution
10 Tutorial 10 11/27 Tutorial Session on PRAM Slides
9 Assignment 11 12/11 Distributed Memory Models Solution

Teams

Number Members Team Name Project Description Final Presentation
1 Müller Nadja, Rothenberger Frederik Cutting Edge
2 Tobias Weber, Zsolt Mezei, Robert Meier returntozero Parallel Max Flow
3 Gustavo Segovia, Seraiah Walter, Fabian Meier The Parallelepipeds
4 Julian Viereck, Vytautas Astrauskas, Roman Cattaneo SAT solver?
5 Florian Frei, Fabian Thüring, Michel Breyer Yellow Lobster
6 Aristeidis Mastoras, Renato Marroquin, David Sidler PQE
7 Denny Lin, Chellakudam Vimal, Benjamin Mularczyk NP-Soft
8 Lucas Wittwer, Felix Thaler, Nicolas Bennett glinternet
9 Pawel Lenarczyk, Kehtari Sohrab, Anne Ziegler Nano.Calc
10 Evgeny Klimenkov, Stephanie Christ, Lukas Strebel Parallel BFS
11 Martin Hüsser, Jan Ebbe Orcs Must Die! Parallel Ripple Search
12 Vishnevskiy Valery
13 Yatao Bian Matrix

Template for project report

Grading

50% of your grade is determined by the project, and the other 50% of the grade is determined by a written 2 hr exam. You are not allowed to use any electronic devices or books, notes, etc. to the exam.

Resources

To implement your project you can utilize our Xeon Phi server. A single-page tutorial om how to run OpenMP programs on it can be found here. There exist a large number of books on programming multi-processors, multi-core system, or threads. These books may explore some topics in more depth than the lectures, or may provide background information. None of these books is mandatory. Copies of the first two books are "on reserve" the CS library.