Monte Carlo Simulations: Parallelism in CS1/CS2
David Valentine, Slippery Rock University of Pennsylvania
Use Monte Carlo Simulations in CS1/CS2 to expose students to parallel programming with OpenMP.

Timing Operations in CUDA
Joel Adams, Calvin College, and Jeffrey Lyman, Macalester College
Through completion of vector addition, multiplication, square root, and squaring programs, students will gain an understanding of when the overhead of creating threads and copying memory is worth the speedup of GPU coding.

Introducing Students to MapReduce using Phoenix++
Suzanne Matthews, United States Military Academy
MapReduce using Phoenix++, which is shared-memory implementation of the map-reduce framework. Through code provided students learn to implement a mapper and reducer function for the classic word count example in C++ to use with Phoenix++.

Map-reduce Computing for Introductory Students using WebMapReduce
Professor Richard Brown, St. Olaf College Professor Libby Shoop, Macalester College
This module emphasizes data-parallel problems and solutions, the so-called 'embarrassingly parallel' problems where processing of input data can easily be split among several parallel processes. Students use a web application called WebMapReduce (WMR) to write map and reduce functions that operate on portions of a massive dataset in parallel.

Multicore Programming with OpenMP
Richard Brown, Saint Olaf College; Elizabeth Shoop, Macalester College
In this lab, we will create a program that intentionally uses multi-core parallelism, upload and run it on the MTL, and explore the issues in parallelism and concurrency that arise. This module uses OpenMP.

MPI Programming Exemplars
Elizabeth Shoop, Macalester College
Four complete examples that use MPI. They can be used to study parallel patterns and learn how to time code.

Pandemic Exemplar using MPI
Yu Zhao, Macalester College
This module will develop a simple agent-based infectious disease model, develop a parallel algorithm based on the model, provide a coded implementation for the algorithm, and explore the scaling of the coded implementation on high performance cluster resources.

Parallel Processes in Python
Steven Bogaerts, DePauw University
This module is designed for use in the latter half of a semester-long CS1 course. It introduces students to the concepts of forking child processes to do work in parallel and how multiple concurrent processes can coordinate using a shared data queue.

Instructor Example: Optimizing CUDA for GPU Architecture
Elizabeth Shoop, Macalester College
This module, designed for instructors to use as an example, explains how to take advantage of the CUDA GPU architecture to provide maximum speedup for your CUDA applications using a Mandelbrot set generator as an example.

WMR Exemplar: LastFM million-song dataset
Elizabeth Shoop, Macalester College
This module demonstrates how hadoop and WMR can be used to analyze the lastFM million song dataset. It incorporates several advanced hadoop techniques such as job chaining and multiple input.

WMR Exemplar: Flickster network data
Elizabeth Shoop, Macalester College
The exercises in this module use a network of friendships on the social movie recommendation site Flixster. Students will use it to learn how to analyze networks and chain jobs, using the WebMapReduce interface.

WMR Exemplar: UK Traffic Incidents
Elizabeth Shoop, Macalester College
Using data published by the United Kingdom department of Transportation about traffic incidents, students can explore and perform analyses using map-reduce techniques.

Visualize Numerical Integration
Elizabeth Shoop, Macalester College
This is an activity with working code supplied that enables students to see how various forms of the data decomposition pattern map processing units to computations.

Concept: Data Decomposition Pattern
Elizabeth Shoop, Macalester College
This module consists of reading material and code examples that depict the data decomposition pattern in parallel programming, using a small-sized example of vector addition (sometimes called the "Hello, World" of parallel programming.

Drug Design Exemplar
Richard Brown, Saint Olaf College
An important problem in the biological sciences is that of drug design: finding small molecules, called ligands, that are good candidates for use as drugs. We introduce the problem and provide several different parallel solutions, in the context of parallel program design patterns.

Pandemic Exemplar
Elizabeth Shoop, Macalester College
Sequential and parallel versions of a Monte Carlo simulation of the spread of infectious disease are presented in detail. Students can run the code and examine performance of sequential and parallel versions.

Patternlets in Parallel Programming
Material originally created by Joel Adams, Calvin College Compiled by Libby Shoop, Macalester College
Short, simple C programming examples of basic shared memory programming patterns using OpenMP and basic distributed memory patterns using MPI.

Heterogeneous Computing
Elizabeth Shoop, Macalester College; , Macalester College
Message Passing Interface (MPI) is a programming model widely used for parallel programming in a cluster. NVIDIA®'s CUDA, a parallel computing platform and programming model, uses GPU for parallel computation problems. This module will explore ways to combine these two parallel computing platforms to make parallel computation more efficient.

Distributed Computing Fundamentals
Elizabeth Shoop, Macalester College; , Macalester College
Message Passing Interface (MPI) is a programming model widely used for parallel programming in a cluster. Using MPI, programmers can design methods to divide large data and perform the same computing task on segments of it and then and distribute those tasks to multiple processing units within the cluster. In this module, we will learn important and common MPI functions as well as techniques used in 'distributed memory' programming on clusters of networked computers.

GPU Programming
Elizabeth Shoop, Macalester College; Yu Zhao, Macalester College
In this module, we will learn how to create programs that intensionally use GPU to execute. To be more specific, we will learn how to solve parallel problems more efficiently by writing programs in CUDA C Programming Language and then executes them on GPUs based on CUDA architecture.