Teaching

• CSE 191: Discrete Structures (Spring, 2013)

  In this course, we present fundamental material that will be used as the foundation for more advanced courses in computer science and engineering. Topics are expected to include, but are not limited to, recursion, iteration, recurrence relations, asymptotic notation, evaluating resources for algorithms, graphs, logic, sets, and some basic counting theory. CSE 191 is required for computer science and computer engineering majors.

  • Spring 2013

• CS 237: Introduction to Scientific Computing

This course offers an introduction to the fundamental numerical techniques used in high-performance scientific computing. These methods include sorting, numerical integration, root finding for nonlinear systems, elementary linear algebra, and basic ordinary differential equations. The emphasis of this course is on an experimental approach to scientific computing. The students will learn the basics of Unix, will write and debug programs in FORTRAN, and will use computational and visualization tools in Matlab.

• Fall, 1995

• CSE 331: Introduction to Algorithms

  • Spring 2009

• CSE 4/529: Algorithms for Modern Computing Systems

  The objective of this course is to teach computational STEM (Science, Technology, Engineering, and Mathematics) students the fundamental concepts of design and analysis of algorithms for modern computing systems, including network-based fine-grained parallel computers, shared-memory computers, general multi-core and multiple processor systems, GPU-based systems, clusters, grids, and clouds. The first part of the course will focus on the introduction of these computational models, as well as the traditional von Neumann architecture, and methods of analysis. The second part of the course will focus on fundamental computational paradigms and their implementation on a variety of modern computational systems. Much of the analysis will be considered in terms of running time, size of data, number of processors/cores, and interconnection networks, to name a few. Asymptotic analysis will be used as a measure of these performance metrics and design options. Note that this is the ever-evolving popular and effective course in Analysis of Algorithms (CSE4/531) that I have taught in the Department of CS/CSE at UB since 1986, which was recently relabeled by the department. The required text for the course is Algorithms Sequential and Parallel: A Unified Approach (Third Edition). NB: First or second edition of book will not suffice.

  • Fall 2013

• CSE 4/531: Analysis of Algorithms

  This course focuses on the design and analysis of algorithms targeted at modern computational systems, including fine- and coarse-grained multi-core and multi-processor systems. The required text for the course is Algorithms Sequential & Parallel: A Unified Approach (Second Edition).

  • Spring 2014 - I have not been scheduled to teach this course. My apologies, while I would love to teach this course, the scheduling is out of my control.
  • Spring 2013 - I have not been scheduled to teach this course. My apologies, while I would love to teach this course, the scheduling is out of my control.
  • Spring 2012
  • Spring 2011
  • Spring 2010
  • Spring 1998
  • Spring 1997
  • Spring 1996

• CSE 633: Parallel Algorithms

  The focus of this course is on the design, implementation, and analysis of student-chosen parallel solution(s) to disciplinary problems of interest to the student and their implementation on modern large-scale multiprocessor/multi-core/GPGPU-based systems. Students will have access to a variety of large multiprocessor systems and will receive instruction on the efficient utilization of such systems in addition to a variety of means (MPI, OpenMP, CUDA) of implementing algorithms to run efficiently on such systems. The required text is Parallel Algorithms for Regular Architectures. A recommended book for students interested in CUDA is CUDA by Example: An Introduction to General-Purpose GPU Programming.

  • Fall 2012: Covers both theoretical parallel algorithms and experimental (hands-on) parallel computing.
    • Talks by Dr. Matt Jones and Cynthia Cornelius, both on staff at CCR, covered an introduction to CCR and their systems, logging into and submitting jobs to CCR's clusters, MPI programming, OpenMP programming, and debugging, to name a few. Notes on this material may be found at CCR Training Material.

    • Computational Science & Engineering, Structural Biology, and 21st Century Academia, Russ Miller
    • Parallelized Hash Collision Attacking, Benedikt F. Budig.
    • Parallel PageRank Computation using MPI, Eric Li.
    • Parallel Convex Hull using MPI, Alex Vertlieb.
    • Cellular Automata, Nils Wisiol.
    • An Implementation of Parallelizing Dijkstra's Algorithm, Zilong Ye.
    • Parallelized Random Forests Learning, Jie Hu.
    • Finite-size Facility Placement in an Existing Layout Using MPI and C, Ketan Date.
    • Parallel Algorithm for Dense Matrix Multiplication, Patricia Ortega.
    • Parallel Implementation of Gradient Descent, Hui Li.
    • Artificial Bee Colony Algorithm using MPI, Pradeep Yenneti.
    • N-Body Simulation, Sanjeev Pandey.
    • Determining Line Segment Visibility with MPI, Jayan Patel.
    • Parallel implementation of Apriori algorithm and association of mining rules using MPI, Sujith Mohan Velliyattikuzhi.
    • Global Sequence Alignments using C/MPI, Ravi Patel.
    • Parallel K-means Clustering, Ajay Padoor Chandramohan.
    • Polynomials and Coding, Jimmy Dobler.
    • Parallel Nash Equilibria in Bimatrix Games, Isaac Elbaz.
    • Parallel Apriori Algorithm and Frequent itemsets with Gene Expression Data, Hyunwoo Sung.

  • Fall 2011: Covers both theoretical parallel algorithms and experimental (hands-on) parallel computing.
    • Talks by Dr. Matt Jones and Cynthia Cornelius, both on staff at CCR, covered an introduction to CCR and their systems, logging into and submitting jobs to CCR's clusters, MPI programming, OpenMP programming, and debugging, to name a few. Notes on this material may be found at CCR Training Material.

    • The QR Algorithm for Finding Eigenvectors, Eric Mikida

    • Parallelizing Matrix Multiplication, Sandeep Raghuraman

    • Finding Prime Numbers Using MPI and C, Andrew Wantuch

    • Parallel AES Implementation, Chris Norman

    • Parallelized Convolution, Venkata Nanda Kishore Buddhiraju

    • Implementation of Quadratic Sieve Algorithm using MPI, Kiran Kamisetty

    • Ant Colony System using MPI, Sachin Bhatt

    • Implementing a Point Domination Query using MPI, Eric Nagler

    • Height Map Generation with GPUs, Ravi Kiran Chilakapati

    • Transfer Learning on Unsupervised Imbalanced Dataset, Kang Li

    • Parallel Spectral Clustering in Distributed Systems, Liang Ge

    • Construction Gene coexpression Network, Nan Du

    • Parallel Solution of Marginal Fisher Analysis, Suxin-Guo

    • Parallel Knuth Morris Pratt String Matching, Laurie Dening

  • Fall 2010: Covers both theoretical parallel algorithms and experimental (hands-on) parallel computing.
    • Overviews of MPI, OpenMP, and CCR systems provided by guest lecturers from CCR, Cynthia Cornelius and Dr. Matt Jones. Details and links below (under Spring 2009).

    • Introducation to CUDA, Matt Heavner, guest lecturer.

    • Generating RSA Primes, James Townsend

    • Parallel Connected Component Labeling for Image Analysis, Yang Fei

    • HADOOP AND RDBMS HOOK UP, Xiao Li

    • A Parallelized Solution for the Traveling Salesman Problem using Genetic Algorithms, Sagar Keer

    • Parallel String Match, Rohit Bal

    • Study of parallel sorting algorithm, Zhihong Wei

    • MPI simulation of a MIMO node choosing algorithm, Xiaoxing Yu

    • Parallel Implementation of Mining Highly Interacted Attribute Pairs, Jianmei Yang

    • Parallel Computing with Browsers: Bin Packing Edition, John Longanecker

    • Mandelbrot Real Time Zooming in DSM Architecture, Prakash Nair

    • N-Body Simulation using CUDA, Suraj Balchand

    • CUDA Implementation of the Lattice Boltzmann Method, Andrew Leach

    • Exploring Reversi Endgames via Parallelization, Devanshu Pandey

  • Spring 2009: Covers both theoretical and experimental (hands-on) parallel algorithms.
    • Supercomputing in Plain English: A High Performance Computing Workshop Series, Spring 2009 Workshop. Lectures and Exercises available as well as live meetings via Access Grid, Polycom, QuickTime Broadcaster, etc.
    • Short Homework Assignment, which was used as Hwk #3 in HPC1, Fall 2008. The MPI version of this assignment implemented on U2 (CCR) is due in 1 week. Thanks to Dr. Matt Jones for providing this.
    • Introduction to Using the High Performance Cluster at the Center for Computational Research, guest lecture by Ms. Cynthia Cornelius, Center for Computational Research
    • Overview of Parallel Programming at CCR, a guest lecture by Dr.Matt Jones, Center for Computational Research

    • Intermediate MPI, guest lecture by Dr.Matt Jones, Center for Computational Research
    • Advanced MPI, guest lecture by Dr.Matt Jones, Center for Computational Research
    • Shared Memory Programming with OpenMP, guest lecture by Dr.Matt Jones, Center for Computational Research
    • Practical Issues in OpenMP, guest lecture by Dr.Matt Jones, Center for Computational Research
    • Application Performance Tuning, guest lecture by Dr.Matt Jones, Center for Computational Research
    • MPI Quick Reference: Compiling/Running, guest lecture by Dr.Matt Jones, Center for Computational Research
    • Fingerprints via EM, Chang Su

    • Identification of Functional Modules in Protein Interaction Networks, Lei Shi

    • Parallel AutoClass, Kevin Keane

    • A Parallel Algorithms for Maximal Clique Detection, Steven Kapturowski

    • Stationary Temperature Distribution in a Square Plate, Jesper Dybdahl Hede

    • Parallel implementation of FRAME - Filters, Random Fields and Maximum Entropy, Rocardo Nagel Rogrigues

• CSE 701: Cyberinfrastructure (Spring 2008)

  • Cluster Installs, John Bannen

  • Condor Installation, Madhavi Nadig

  • Construction of the MCIL Cyberinfrastructure Lab, Michael Rokitka

  • Clusters Topology, by Zoran Obradovic

  • Virtual Memory Machines, by Zoran Obradovic

• CSE 704: Programming Massively Parallel GPGPU Systems (Spring, 2013)

  • This seminar focuses on student projects involvinig high-performance computing systems. Students are expected to have previous experience programming HPC systems using, for example, OpenMP, MPI, CUDA, or similar. Students will work on projects of their own choosing.
  • We will meet weekly, at a time convenient to all of those who register, and discuss goals and progress. Students will share experiences and information in an effort to expedite the progress of all participants.
  • Please see information on related seminars below.
  • Available for 1, 2, or 3 credits.
  • Tutorials and fundamental information (e.g., MPI, PBS, CUDA, etc.) can be found through the material listed under CSE633 and the related CSE7XX seminars below.

• CSE 704: Programming Massively Parallel GPGPU Systems (Spring, 2012)

  • Tutorials and fundamental information (e.g., MPI, PBS, etc.) can be found through the material listed under CSE633.
  • Common Mistakes in OpenMP and How To Avoid Them: A Collection of Best Practices, Michael SuB and Claudia Leopold, University of Kassel, Germany.
  • 32 OpenMP Traps for C++ Developers, PVS-Studio.

• CSE 704: Programming Massively Parallel GPGPU Systems (Spring, 2011)

  • Using MPI to Break Data Encryption, James Townsend, 4/2011.
  • Condor and the Hadoop File System with a Packing Problem, Phil Matuskiewicz, 4/2011.
  • Mersenne Twister Implementation on a GPU, Rohit Bal & Sagar Keer, 4/2011.
  • Parallel Computing with Browsers, John Longanecker, 4/2011.
  • Network Car Race Game, Pankaj Kumar Yadav, 4/2011.
  • OpenGL Visualization of the N-Body Problem, Suraj A. Balchand & Andrew Leach, 4/2011.
  • Evolving Creatures, Thomas J. Hartnett, 4/2011.

• CSE 710: Programming Massively Parallel GPGPU Systems (Fall, 2009)

  • Overview of Magic, Kevin Clearly, 9/2009.
  • CUDA, OpenMPI, OpenMP Basics, Matt Heavner, 9/2009.
  • Massively Parallel Traveling Salesman Genetic Algorithm, Matt Heavner, 12/2009.
  • Factorization of a Large Number, Morgan Cooper, 12/2009.
  • N Body Gravitational Problem, Srinivasan Manoharan, 12/2009.
  • MergeSort over CUDA, MPI, and openMP, Brady Tello, 12/2009.
  • Computation of Pi using CUDA, Dan Padgett, 12/2009.

• CSE 710: Cyberinfrastructure (Fall 2007)

• Concepts and Challenges of Grid Programming, Michel Rokitka
• Grid Cookbook: Grid Case Studies, John Bannen
• Grid Cookbook: What Grids Can Do For You, John Bannen
• Open Science Grid, Zoran Obradovic
• Grid Monitoring, Zoran Obradovic
• The Cyberinfrastructure Laboratory, the New York State Grid, and the New York State Grass-Roots Cyberinfrastructure Initiative, Russ Miller
• Globus - GTK and Grid Services, Michael Rokitka

• Honors Seminar (Freshman): Computing at the High End (Fall, 2010)

  • Course Description and Instructor Bio.
  • Schedule.

• Seminar on Grid Computing

This seminar series (2004-present) focuses on fundamental aspects of Grid computing and Cyberinfrastructure. Some of the student presentations are available below.

• Grid Scheduling Ontology, Shreyansh Vakil, Fall 2006

• Data Grids, Hanumant Singh, Fall 2006

• Semantic Grids, Arun Mirpuri, Fall 2006

• Grid Resource Broker, Abhishek Singh, Fall 2006

• Grid Security Infrastructure, Sergey Chernokozinskiy, Fall 2006

• Approaches to Resource Discovery in Computational Grids, Anurag Bhardwaj, Fall 2006

• SnBDCV: Distributed Collaborative Visualization, Amin Ghadersohi, Fall 2006

• Open Grid Services Architecture and Data Grids, Karthik Ram Venkataramani, Spring 2004

• Autonomic Computing and Grid, Catherine L. Ruby, Spring 2004

• Narada Brokering, Martins Innus, Spring 2004

• Data Grid Scenario Builder, Catherine L. Ruby, Spring 2004

• Grid Resource Allocation, Teena Vyas, Spring 2004

• Condor and the Grid, Karthikram Venkatarmani, Spring 2004

• Peer-to-Peer Grids, Michael Fritz, Spring 2004

• Data Grid Generating Tool, Catherine L. Ruby, Spring 2004

• Seminar on WWW

This "seminar" is open to graduate students and undergraduates, by permission of instructor. Topics to be covered include HTML, CGI, perl, Java, and issues of security, to name a few.

• Spring, 1998

• Spring, 1997