EduPar-13: Third NSF/TCPP Workshop on Parallel and Distributed Computing Education Sushil K Prasad Georgia State University

Welcome to Boston! Undergraduate PDC education Review – 24 submissions – 3-5 reviews for each submission – Selected 6 regular papers and 7 short papers. – 21 posters – early adopters of the NSF/TCPP PDC curriculum – Thanks to PC – Special Thanks to 4 core members: Anshul Gupta, Arnold Rosenberg, Alan Sussman, and Chip Weems – NEW: Lightning Talks by each early adopters 5 min/talk, no Q&A First row seats – reserved for speakers Webcast to students and colleagues – Posters “manned” during both coffee breaks (and possibly lunch)

Funding/Sponsorships – NSF NSF/TCPP Curriculum Initiative Early adopter competitions (stipend, travel) EduPar workshop series. CDER center ( ) – Intel international early adopter institutions ((stipend, travel) – nVIDIA GPU cards to all the 50+ early adopters from Spring'11, Fall'11 and Spring'12 rounds. – IEEE TCPP, IBM Keynotes in the past

Center for Parallel and Distributed Computing Curriculum Development and Educational Resources (CDER) Develop PDC core curricula flexible enough for a broad range of programs and institutions; collaborate with all stakeholders Develop, collect, and synthesize pedagogical and instructional materials for teaching PDC curriculum topics* – Website setupsetup Facilitate access to state-of-the-art hardware and software resources for PDC instruction and training by instructors and students* Organize Early Adopter Competitions and EduPar workshops, and related events* * Call for participation and contribution

CDER Courseware Website Upload and Search Course Material Type: – Slides, Syllabus, Tutorial, Video – Animation, Article, Award, Blog, Book, Competition – Course Template, Course Module, Data – Hardware Access, Software/Tools – Proposal, Report Courses: – CS1, CS2, Systems, Data Structures and Algorithms, … NSF/TCPP Topic/Subtopic Classification: ALGORITHMS Parallel and Distributed Models and Complexity Algorithmic Paradigms Divide & conquer (parallel aspects) Algorithmic problems ARCHITECTURE PROGRAMMING CROSS-CUTTING

Early Adopter Program Total 80 institutions worldwide – Spring-11: 16 institutions ; Fall’11: 18; – Spring-12: 21; Fall-12: 25 institutions – Most from US (4 year to research institutions); some from South America, A few from Europe, fewer from Asia (India, China). Fall-13 round of competition: Deadline June 30, 2013 – NSF/Intel funded cash awards ranging from $1k-2.5K + certificate – Which course(s), topics, evaluation plan? Instructors for core CS/CE courses such as CS1/2, Systems, Data Structures and Algorithms – department-wide multi-course multi-semester adoption preferred – Elective courses; graduate courses, – Computational Science, computational courses of STEM disciplines

Algorithms - Topics DS/A Totals for Topics KCAAvera ge Asymptoptic0062 Time0031 Space Speedup0000 Cost Reduction: Space Compression,etc Time vs Space Power vs Time, etc.0301 Scalability in Algorithms and Architectures 0211 Notions from Complexity- Theory: P-Completelness #P-Completeness Cellular Automata Dependencies Course Templates - Data Structures and Algorithms (DS/A) course - Sampled over 3 courses Algorithms - Topics DS/A Totals for Topics KCAAvera ge Divide and Conquer (Parallel Aspects) 0211 Recursion (Parallel Aspects) Scan (Parallel Prefix) Reduction Map-Reduce Series-Parallel Composition Asynchrony Sorting0242 Selection Graph Algorithms Search Path Selection Specialized Computations 0031 Matrix Computations Matrix Product Hour totals per Course2696

Syllabus for a sample Data Structure and Algorithms (Second semester with only programming as their prior background, IIIT Hyderbad, India) 1.Introduction to data structures (Week 1) 2.Introduction to asymptotic analysis – mainly O(.) notation (Week 2) 3.Array as a data structure, sorting, parallel sorting, parallel prefix (Week 3) 4.Stacks and queues (Week 4) 5.Linked lists, ideas from list representation and ranking and its difficulty in the parallel setting. (Week 5) 6.Trees, applications to evaluation, searching, balanced search trees, scope for parallel operations (Week 6-7) 7.Graph traversal techniques, shortest paths, spanning trees, solutions in the parallel setting (Week 8-10) 8.Advanced data structures such as Union-Find, B-trees, Suffix tree, trie (Week )

CDER Book Project Lack of suitable textbooks to integrate PDC topics into the core courses – CS1, CS2, Systems, and Data Structures and Algorithms Part I - For instructors: Basic Concepts and References on what and how to teach Sample essays on Asymptotics, Scalability, and Synchronization posted Part 2: For students: Supplemental teaching material for core courses Invitation to help shape the project and to review/write chapters with authorship for writers – participate in reviewing Early adopter competition and EduPar-14 submissions Teleconference in June

EduPar-13 Organization/Logistics Keynote – David Luebke, NVIDIA – Session 1 (2 papers, 4 lightning talks) AM Break + Posters – Session 2 (3 papers) – Session 3 (5 lightning talks) Lunch + Posters Invited Talk – Dan Katz, NSF – Session 4 (3 papers) – Session 5 ((5 lightning talks) PM Break + Posters – Session 6 (5 papers) Posters Session

Keynote Democratizing Parallel Computing, Democratizing Education: Teaching a MOOC about GPU computing David Luebke, Senior Director of Research, NVIDIA