Events and Presentations

See a map of recent events.

The Trilinos Project User Group Meeting

June 10, 2019

Tutorial, Platform for Advanced Scientific Computing (PASC), Zurich, Switzerland

This event is co-located with the PASC Conference and represents the next installment of the European Trilinos User Group (EuroTUG) meetings.

Accelerated Sparse Linear Algebra: Emerging Challenges and Capabilities for Numerical Algorithms and Software

April 11, 2019

Invited Talk, Royal Society Meeting on Numerical Linear Algebra, London, UK

For the foreseeable future, the performance potential for most high-performance scientific software will require effective use of hosted accelerator processors, characterized by massive concurrency, high bandwidth memory and stagnant latency. These accelerators will also typically have a backbone of traditional networked multicore processors that serve as the starting point for porting applications and the default execution environment for non-accelerated computations.

Making Reproducibility Indispensable: Changing the Incentives that Drive Computaitonal Science

March 21, 2019

Invited Talk, SPPEXA Conference, Paris, France

Reproducibility is essential for scientific progress and engineering advances. Even so, many published computational results lack sufficient capture and description of companion information that would enable subsequent confirmation and extension of the results. Certainly, most scientists intend to publish correct results, but without sufficient rigor in computational processes and practices, risk is unnecessarily high that results will occasionally be wrong and will always be costly to confirm and extend.

Recent Trends and Challenges for High Performance Sparse Linear Algebra

February 25, 2019

Talk, SIAM Computational Science and Engineering Conference 2019, Spokane, WA, USA

The path to scalable performance on next generation platforms must include design and implementation for accelerated computations, including addressing all phases of computation and data movement.

SC18-SC19 Turnover Meeting

January 22, 2019

Talk, SC18-SC19 Turnover Meeting, San Antonio TX, USA

This meeting is for transferring ownership and planning from SC18 leadership to SC19 leadership.I was reproducibility chair for SC18 and will be special advisor to the conference chair on reproducibility for SC19.

Building the Exascale Software Stack: Challenges and Strategies

July 18, 2018

Invited Talk, DOE CSGF Annual Meeting, Washington DC, USA

The US DOE Exascale Computing Project (ECP) is preparing to deliver science and engineering computing capabilities for machines that can perform up to a billion-billion operations per second. Realizing this performance potential requires fundamental changes in algorithms, software design and development. In addition, ECP is integrating software activities across all major DOE labs and numerous universities and corporations at a larger scale than ever before.

TOP 500 HPCG Results

June 27, 2018

BOF, The International Supercomputing Conference 2019, Frankfurt, Germany

ISC is the European-focused community event for high-performance computing. We announce the TOP 500 results at this meeting and at the US Supercomputing Conference.

TOP 500 HPCG Results

June 24, 2018

BOF, The International Supercomputing Conference 2018, Frankfurt, Germany

ISC is the European-focused community event for high-performance computing. We announce the TOP 500 results at this meeting and at the US Supercomputing Conference.

SC17-SC18 Turnover Meeting

January 16, 2018

Talk, SC17-SC18 Turnover Meeting, Tucson AZ, USA

This meeting is for transferring ownership and planning from SC17 leadership to SC18 leadership.I was tech papers co-chair for SC17 and will be reproducibility chair for SC18.

Better Science Through Better Software

July 27, 2017

Talk, DOE CSGF Annual Meeting, Washington DC, USA

Computational Science and Engineering (CSE) is effective to the extent it contributes to overall scientific and engineering pursuits. Its contributions are most tangible when delivering concrete scientific and engineering results via modeling, simulation and analysis. At the same time, delivery of CSE results is impacted by how we develop and support the ecosystem that produced these results, including, in particular, software and people. While delivering results is the ultimate goal of our CSE efforts, the shortest path to results is often not the most productive and sustainable.

Linear Algebra Software for High Performance Computing

June 18, 2017

Tutorial, International Supercomputing Conference 2017, Frankfurt, Germany

Tutorial Information Today, a desktop computer with a multicore processor and a GPU accelerator can already provide a teraFLOPS of performance. This tremendous computational power can only be fully utilized with the appropriate software infrastructure. Most often a major part of the computational effort in scientific and engineering computing goes towards solving linear algebra sub-problems. This tutorial surveys the state-of-the-art numerical libraries for solving problems in dense and sparse linear algebra. The tutorial consists of three parts. The first part provides a brief historical look at the development of dense linear algebra libraries, from LINPACK, to LAPACK, to ScaLAPACK. The second part discusses dense linear algebra software for multicore processors (PLASMA) and hardware accelerators (MAGMA). The fourth part will presents software for sparse liner algebra, including the Trilinos package.

ECP Software Technology Review

January 09, 2017

Event, ECP Independent Project Review, Oak Ridge TN, USA

The Independent Project Review for the DOE Exascale Computing Project.