UNIVERSAL COMPUTATIONAL SCIENCE EDUCATION: CHALLENGES AND OPPORTUNITIES – Valerie Taylor (Texas A&M University)

Today, with the availability of processors with multiple cores or multicore processors, all computer systems, even the home computers, include parallel processing. We are seeing an increase in the number of cores per processor with future computer chips. Further, many applications include significant computations for multi-media displays in addition to control decisions. Hence, it is important that our students are exposed to parallel processing or computational science education as early as possible. Such exposure should excite students about the field of computational science, with special focus on the engagement of underrepresented groups in math and science. Given the use of computers in so many disciplines, exposure to computational science is important for students to be leaders in their careers.

COLLABORATION TOOLS FOR K-12 ESCIENCE – Adam Frey (Wikispaces), Thomas Loughran (University of Notre Dame)

This session will introduce Web 2.0 collaboration tools (wikis, blogs, forums, maps, calendars, readers, chat, video conferencing, etc.) and investigate the possibilities they bring for organizing online community among K-12 SC Education Program participants and their students.

DIGITAL LIBRARIES AND HPC PHYSICS EDUCATION – Norman Chonacky (Yale University), Richard Gass (University of Cincinnati), Dave Joiner (Kean University), Rubin Landau (Oregon State University), Robert Panoff (Shodor), Mario Belloni & Wolfgang Christian (Davidson College)

A variety of digital library projects are available for physics educators interested in incorporating computation into the classroom and this session will present an overview of such projects. Participants will be exposed to physics search engines and get experiences searching for, reviewing and submitting resources to ComPADRE, the OSP digital library, CSERD and UCOMP. A panel discussion will be held to discuss future collaboratory efforts between digital libraries in computational physics.

MOLECULAR DYNAMICS (LEVEL 1, BEGINNER) – Clyde Metz (College of Charleston), Shawn Sendlinger (North Carolina Central University)

The basis of molecular dynamics will be discussed and participants will have hands-on time to investigate the Odyssey software package.

TERAGRID & HPC UNIVERSITY RESOURCES – Brad Armosky (Texas Advanced Computing Center), Scott Lathrop (Blue Waters and TeraGrid)

This session will provide an overview of TeraGrid and HPC University, and the resources available to educators and students, as well as opportunities for faculty and students to become involved in various programs and activities. TeraGrid is an open scientific discovery infrastructure combining leadership-class resources at eleven partner sites to create an integrated, persistent computational resource. TeraGrid integrates high-performance computers, data resources and tools, and high-end experimental facilities around the country. TeraGrid resources include more than a petaflop of computing capability and more than 30 petabytes of online and archival data storage, with rapid access and retrieval over high-performance networks. See http://www.teragrid.org.
      The HPC University is a virtual organization that provides a cohesive, persistent, and sustainable on-line environment to share educational and training materials for a continuum of high-performance computing environments that span desktop computing capabilities to the highest-end of computing facilities offered by HPC centers. See http://www.hpcuniv.org.

INTERMEDIATE MODELING SKILLS FOR ENGINEERS: MECHANICAL ENGINEERING EXAMPLES (PART 3) – Dan Warner (Clemson University)

This session will showcase material from a new course at Clemson University that has been developed for sophomore and junior students in Mechanical Engineering. Three of the recurring problems in this course are trusses, spring-mass-damper systems and bungee jumpers. These problems raise a number of different questions regarding both statics and dynamics.

VIDEO IN THE 21ST CENTURY CLASSROOM – Kent Robertson (Shodor)

Video is a very important part of 21st Century learning and is vital for visual learners including deaf students. Video can be linked to or collected from a variety of sources and formats on the Internet. You can create your own video using digital video cameras and web cams. The raw video you create can be processed for content and special effects. For example, closed captioning can be added. The final video can be published in PowerPoint presentations, on CDs and DVDs, or added to web pages and Internet sites. This session will show you how to collect, process and present video and pictures for your class.

THE BIOLOGY AND ALGORITHMS OF SEQUENCE ALIGNMENT AND PHYLOGENETIC TREE CONSTRUCTION – Gloria Rendon (National Center for Supercomputing Applications, University of Illinois at Urbana-Champaign)

Biology is related to medicine, mathematics and computer science. Understanding those relationships is therefore the first step in the path to making those connections useful in our daily lives. For instance, sequence homology – an open problem in Biology – is closely related to the problem of string matching – an active area of research in algorithms and computer science. We will explore two of the most fundamental and fascinating areas of bioinformatics: sequence alignment and phylogenetic tree reconstruction. The session will focus on the biology aspect while at the same time including hands-on exercises to address the algorithmic aspect of the two areas. No previous experience in programming is required.

TURNING MULTIVARIABLE MODELS INTO INTERACTIVE ANIMATED SIMULATIONS – Susan Ragan (Maryland Virtual High School), Scott Sinex (Prince George's Community College, Maryland Virtual High School)

Using tools available in Excel, we will turn a multivariable model into an interactive animated simulation. Projectile motion, Boyle's Law, nuclear decay and population growth are just a few examples of the types of models for which a simulation can be useful to deepen a student’s understanding. Knowledge of the basic aspects of Excel as covered in the earlier Excel workshops is required.

N-BODY PHYSICS PROBLEMS SOLVED WITH MESSAGE PASSING (PART 1) – Norman Chonacky (Yale University), David Joiner (Kean University)

N-body problems for the physics classroom will be discussed. Participants will get experience running a variety of cluster-based N-body models. Participants will use MPI to parallelize a simple N-body code.

CHEMICAL KINETICS (LEVEL 1, BEGINNER) – Clyde Metz (College of Charleston)

A basic review of chemical kinetics will be followed with hands-on use of Excel. The idea of a graphical interface differential equation solver (GIDES) will be introduced, followed by hands-on exercises using Vensim PLE software.

USING OPEN SCIENCE GRID RESOURCES – Alina Bejan (University of Chicago)

This workshop introduces basic techniques of grid and distributed computing for science and engineering involving the use of national grid computing resources. The focus will be on enabling the use of the Open Science Grid, a major contributor to the national cyberinfrastructure, to perform large-scale computations and data-intensive processing in various fields of research, such as bioinformatics, molecular dynamics, and climate modeling among many others. OSG is a collaborative interdisciplinary project that provides a computing infrastructure of more than 40,000 CPUs distributed across 70 sites and 30 virtual organizations, sustaining a throughput of more than 100,000 jobs per day with 4,000 concurrent job submissions and 50,000 CPU hours per day usage. Participants will be provided with technical information and guidelines that will allow them to continue exploring grid technologies to improve computations related to their own research. Researchers, faculty, graduate students and professionals in any computational discipline are encouraged to attend.

USING PARALLEL MATLAB TO SOLVE MORE COMPLEX ENGINEERING PROBLEMS (PART 1) – Ashok Krishnamurthy & Siddarth Samsi (Ohio Supercomputer Center)

This session will present methodologies on exploiting parallelism in MATLAB programs using the Parallel Computing Toolbox™ (PCT) and the MATLAB Distributed Computing Server™ (MDCS). Participants will be introduced to concepts of task and data parallel programming. The session will specifically cover various parallel programming constructs offered by the PCT including parallel for-loops, distributed arrays and message passing. Example code will be presented and made available to participants for modification and/or incorporation into their own applications. Participants will also have the opportunity to develop a series of real-world signal and image processing examples intended to reinforce the concepts of task parallel and data parallel programming with MATLAB.

INTRODUCTION TO VOICETHREADS FOR TEACHERS & STUDENTS – Kent Robertson (Shodor)

A VoiceThread is a collaborative, multimedia slide show that displays images, documents like PowerPoint, PDF files and video. People who visit the online thread can leave voice, text and video comments. They can draw on the original document to add clarity to their comments. VoiceThread’s online multimedia format allows instruction to extend beyond the classroom. The ability to use webcams to add video comments provides several unique opportunities for Deaf students. This session will demonstrate how to create VoiceThreads and add different kinds of comments. Sample Threads will be presented to demonstrate their use in hearing and deaf classrooms.

ONE TO MANY AND MANY TO MANY SEQUECE COMPARISONS: BLAST-ING TO METAGENOMICS – Ananth Kalyanaraman (Washington State University)

Metagenomics, the study of environmental microbial communities, is a rapidly emerging field that is poised to transform the landscape of research conducted in several critical areas including alternative energy, medicine, agricultural biotechnology and bioremediation. Due to recent technological breakthroughs in sequencing there has been an explosion of metagenomic sequence data in public databases. This data accumulation automatically lends itself to large-scale challenges in computing. In this session, we will discuss algorithms and applications for two of the major operations for metagenomic data analysis:
     i) One-to-many sequence comparison: A typical application of this sequence database search; and
     ii) Many-to-many sequence comparison: Typical applications of this include metagenomic assembly, clustering and protein family identification.
Throughout the discussion, emphasis will be on the role of high-performance computing to conduct these analyses. We will also identify hands-on exercises and lesson plans that can help carry these cutting-edge research advances into classrooms.

ADVANCED MODELS – Susan Ragan (Maryland Virtual High School), Scott Sinex (Prince George’s Community College, Maryland Virtual High School)

This is a continuation of the Turning Multivariable Models into Interactive Animated Simulations session. More interactive features will be introduced. We will explore the use of "if statements" for turning on-and-off text as well as data on graphs. We will examine the introduction of random error into a model to show the effect of goodness-of-fit. Animation techniques such as using a bar graph to make a thermometer or using a scatter plot and random variation to simulate vibrating atoms will be demonstrated.

N-BODY PHYSICS PROBLEMS SOLVED WITH MESSAGE PASSING (PART 2) – Norman Chonacky (Yale University), David Joiner (Kean University)

Continuation of 1:30 pm session, N-body problems for the physics classroom will be discussed. Participants will get experience running a variety of cluster-based N-body models. Participants will use MPI to parallelize a simple N-body code.

CHEMICAL KINETICS WITH EXCEL AND VENSIM PLE (LEVEL 2, INTERMEDIATE) – Clyde Metz (College of Charleston), Shawn Sendlinger (North Carolina Central University)

This is a hands-on continuation of the 1:30 pm session with exercises for participants to follow that will enable them to learn and manipulate the software tools. Sufficient time will be provided for investigation of kinetics situations of the participant's own choosing.

MODELING AND SIMULATION – Andrew Fitz-Gibbon & Brad Johnson-Stahlhut (Earlham College)

This session will introduce a number of modeling tools and methods with a focus on cell-based automaton and NetLogo (a cell-based simulation program). We will present a detailed overview of NetLogo usage including understanding a current model, extending pre-existing models, and the basis for creating new models. Other topics to be covered include NetLogo parallelism with HubNet and parameter sweeps with NetLogo's Behavior Spaces.

USING PARALLEL MATLAB TO SOLVE MORE COMPLEX ENGINEERING PROBLEMS (PART 2) – Ashok Krishnamurthy & Siddarth Samsi (Ohio Supercomputer Center)

Continuation of the parallel MATLAB session.

CUDA INTRODUCTIONS – Christian Trefftz & Greg Wolffe (Grand Valley State University)

The Graphics Processing Units (GPUs) that power modern video cards have demonstrated a remarkable growth in computing capacity. Today’s GPUs have highly parallel architectures that support massive multi-threading. Recently, the improved programmability of these chips has enabled General-Purpose computing on GPUs (GPGPU). The Compute Unified Device Architecture (CUDA), is one such language environment developed for NVIDIA graphics cards. This tutorial will begin with an overview of GPU architecture, followed by an introduction to the CUDA programming model. Participants will obtain hands-on experience writing and compiling CUDA programs via simple examples in C and executing them using a GPU emulator.

PATTERN DISCOVERY AND PATTERN MATCHING IN BIOLOGICAL SEQUENCES: FINDING MEANING BY FINDING MOTIFS AND DOMAINS – Eric Jakobsson (University of Illinois at Urbana-Champaign, National Center for Supercomputing Applications), Jeff Krause (Shodor)

Patterns are everywhere in biology and biological sequence data. As the quantity of available sequence data continues to grow exponentially, it has become imperative that we codify expert methods for initial identification of patterns, distinguishing meaningful patterns from noise and recognition of known patterns in new data. These are tasks that have been carried out in other fields for decades. In this session we will describe algorithms and tools for carrying out these tasks on biological sequence data. Information about the mathematical foundations and computational implementation of common approaches will be related to the biological significance of various patterns that have been identified.

THERE IS NO MORE SEQUENCE PROGRAMMING. WHY ARE WE STILL TEACHING IT? - Wen-Mei Hwu (University of Illinois at Urbana-Champaign), David Kirk, (NVIDIA Chief Scientist), Christoph Lameter (Kernel Developer, The Linux Foundation), Charlie Peck (Earlham College), Michael Wrinn (Senior Architect, Intel Software College)

There have been urgent voices since at least 1995 calling for the introduction of parallel programming into the undergraduate curriculum, yet academic institutions are still teaching sequential programming. This is true despite the fact that all major manufacturers have moved to a many core architecture and the current generation CPU, GPU or ASIC designs cannot be efficiently programmed without knowledge of parallel programming. What should we do to train engineers and scientists to exploit the modern compute platform? This panel debates this issue and kicks off a working group of academic and industry experts that will develop and recommend a practical means for creating an undergraduate curriculum with parallelism at its core. Come to participate in the discussion and to ensure that your voice is heard.