Talks
2012
GPUs and Python. (Invited speaker and panelist) PyData NYC —-Conference on big data with Python . New York, NY . October 2012.
Quadrature by expansion. Applied Mathematics Seminar . Carolina Center for Interdisciplinary Applied Mathematics, University of North Carolina . Chapel Hill, NC . October 2012.
Transformational Programming for time- and frequency-domain EM simulation. (Invited plenary talk) SCEE2012 —Scientific Computing in Electrical Engineering . ETH Zurich . Zurich, Switzerland. September 2012.
Easy, Effective, Efficient: GPU Programming in Python with PyOpenCL and PyCUDA. HPC & GPU Supercomputing Group of New York City . New York, NY . May 2012.
POP Quadrature: Painless high-order-accurate layer potentials. Applied & Computational Mathematics Seminar . Dartmouth Co. Hanover, NH . April 2012.
Loo.py: A Loop Generation Tool for CPUs and GPUs. Oil and Gas High Performance Computing Workshop . Rice University. Houston, TX . March 2012.
Tools and Methods for DG on Modern Computer Architectures. Oberwolfach workshop “Theory and Applications of Discontinuous Galerkin Methods” . Mathematisches Forschungsinstitut Oberwolfach . Oberwolfach, Germany. February 2012.
High-order DG Wave Propagation on GPUs: Infrastructure and Implementation. Minisymposium 13, organized by Takahiro Katagiri, Toshiyuki Imamura, and Keita Teranishi . SIAM Conference on Parallel Processing for Scientific Computing . Savannah, GA . February 2012.
Loo.py—a polyhedral code generator for CPUs and GPUs. (lightning talk, invited attendee) Synchronization-reducing and Communication-reducing Algorithms and Programming Models for Large-scale Simulations . Institute for Computational and Experimental Research in Mathematics (ICERM ), Brown University . Providence, RI . January 2012.
2011
Run-time Code Generation for Heterogeneous Computing: Methods and Applications in High-Order PDE Solvers. Red Raider Minisymposium. Texas Tech University. Lubbock, TX . November 2011.
Discontinuous Galerkin, Python, and GPUs: a case study. Workshop `Programming of Heterogeneous Systems in Physics’ . Universität Jena . Jena, Germany. October 2011.
Easy, Effective, Efficient: GPU Programming in Python with PyOpenCL and PyCUDA. HPC & GPU Supercomputing Group of New York City . New York, NY . September 2011.
Run Time Code Generation for Heterogeneous Computing: Methods and Applications in High-Order PDE solvers. Workshop on CBC Key Topics . Center for for Biomedical Computing, Simula Research Laboratory . Lysaker, Norway. August 2011.
Run-time Code Generation for Heterogeneous Computing: Methods and Applications in High-Order PDE Solvers. Workshop `GPU Computing Today and Tomorrow’. GPULab, Department for Informatics and Mathematical Modelling, Technical University of Denmark . Lyngby, Denmark. August 2011.
Generalized Debye Sources: Computational Aspects on Arbitrary Surfaces. Frontiers in Applied and Computational Mathematics . New Jersey Institute of Technology. Newark, NJ . June 2011.
Discontinuous Galerkin, Python, and GPUs: the `hedge’ solver package. Advances and Challenges in Computational General Relativity . Brown University . Providence, RI . May 2011.
Easy, Effective, Efficient: GPU Programming in Python with PyOpenCL and PyCUDA. (guest lecture) CS264 , Massively Parallel Computing . Harvard University. Boston, MA . March 2011.
High-order DG Wave Propagation on GPUs: Infrastructure, Implementation, Method Improvements. Scientific Computing and Numerics (SCAN ) Seminar . Cornell University . Ithaca, NY . March 2011.
Easy, Effective, Efficient: GPU Programming in Python with PyOpenCL and PyCUDA. Research Seminar. D.E. Shaw Research . New York, NY . March 2011.
High-order DG Wave Propagation on GPUs: Infrastructure, Implementation, Method Improvements. Mechanical Engineering Department, City College of New Yew York . New York, NY . March 2011.
Shock Capturing in a Time-Explicit Discontinuous Galerkin Method on the GPU . Minisymposium 116 . SIAM Conference on Computational Science and Engineering 2011 . Reno, NV . March 2011.
Paper to GPU : Optimizing and Executing Discontinuous Galerkin Operators in Python. Minisymposium 62 . SIAM Conference on Computational Science and Engineering 2011 . Reno, NV . March 2011.
High-Order Discontinuous Galerkin Methods by GPU Metaprogramming. Minisymposium 1 . SIAM Conference on Computational Science and Engineering 2011 . Reno, NV . March 2011.
High-order DG Wave Propagation on GPUs: Infrastructure, Implementation, Method Improvements. Math Department Seminar . UMass Dartmouth . Dartmouth, MA . February 2011.
High-order DG Wave Propagation on GPUs: Infrastructure, Implementation, Method Improvements. Workshop “High Performance Computing and Emerging Architectures” . Institute for Mathematics and Its Applications, University of Minnesota. Minneapolis, MN . January 2011.
Easy, Effective, Efficient: GPU programming with PyOpenCL and PyCUDA. Pan-American Advanced Studies Institute (PASI ) “Scientific Computing in the Americas: the challenge of massive parallelism” . Universidad Técnica Federico Santa María. Valparaíso, Chile. January 2011.
2010
Machine-adapted Methods: High-order DG Wave Propagation on GPUs. Imaging and Computing Seminar . Mathematics Department, MIT . Boston, MA . December 2010.
Machine-adapted Methods: High-order DG Wave Propagation on GPUs. Numerical Analysis and Scientific Computing Seminar . Courant Institute, NYU . New York, NY . November 2010.
PyCUDA: Even Simpler GPU Programming with Python. Nvidia GPU Technology Conference. San Jose, CA . October 2010.
High-Order Discontinuous Galerkin Methods by GPU Metaprogramming. 2010 International Workshop of GPU Solutions to Multiscale Problems in Science and Engineering . Harbin, China. July 2010.
Machine-adapted Methods: Shock Detection and Capture in GPU -DG . Minisymposium 1 . SIAM Annual Meeting 2010 . Pittsburgh, PA . July 2010.
Half-day Tutorial on GPU Computing using PyOpenCL. Conference on Scientific Computing in Python (SciPy 2010) . Austin, TX . June 2010.
High-Order Discontinuous Galerkin Methods by GPU Metaprogramming. Aerospace Computational Design Laboratory Seminar . Mechanical Engineering, MIT . Boston, MA . March 2010.
High-Order Discontinuous Galerkin Methods by GPU Metaprogramming. Mathematics and Computer Science Division Seminar. Argonne National Laboratory . Chicago, IL . January 2010.
2009
GPU metaprogramming using PyCUDA: methods and applications. GPU @BU project launch workshop . Boston University Center for Computational Science . Boston, MA . November 2009.
High-Order Discontinuous Galerkin Methods and Loop Generation by GPU Metaprogramming. Seminar Departement Mathematik . Universität Basel. Basel, Switzerland. October 2009.
Scripting GPUs with PyOpenCL. FACETS Code Jam 3 . Bernstein Center for Computational Neuroscience, Universität Freiburg . Freiburg, Germany. October 2009.
GPU Metaprogramming using PyCUDA: Methods & Applications. Nvidia GPU Technology Conference . San Jose, CA . October 2009.
GPU Metaprogramming Applied to High-Order DG and Loop Generation. Frontiers of Geophysical Simulation . Institute for Mathematics Applied to Geosciences . Boulder, CO . August 2009.
GPU Computing: Introduction, Scripting, and Time-domain DG . Advanced Computation Department Seminar . SLAC National Accelerator Laboratory . Menlo Park, CA . July 2009.
Scripting for GPUs (feat. Discontinuous Galerkin Time Domain). Hess Corporation. Houston, TX . May 2009.
Accelerated Computing: GPUs, Cell, Larabee. (day-long lecture) 2009 HPC Summer Institute . Ken Kennedy Institute for Information Technology, Rice University . Houston, TX . May 2009.
High-Productivity Supercomputing: Metaprogramming GPUs. Minisymposium 134 . SIAM Conference on Computational Science and Engineering 2009 . Miami, FL . March 2009.
PyCUDA and PyUblas: Hybrid HPC in Python made easy. Minisymposium 98 . SIAM Conference on Computational Science and Engineering 2009 . Miami, FL . March 2009.
High-Productivity Supercomputing: Metaprogramming GPUs. (guest lecture) CUDA IAP Class . MIT . Boston, MA . January 2009.
2008