Since May 2020, I try to post some of my talks to the PASSION Lab YouTube channel. Some other videos can also be found from the links here.

Selected Talks

[1] Parallelism in Modern Sparse Linear Solvers,. Managing Parallelism Workshop at the Simons Institute for the Theory of Computing, October 2025, Berkeley, CA [Video]
[2] The Past, Present, and Future of Sparse Computations. Keynote at the Sparse and Graph Computing Session at JuliaCon, July 2025, Pittsburgh, PA [Slides]
[3] Supercomputing-Scale Graph Neural Network Training. Georgia Tech, CSE Department , October 2024, Atlanta, GA [Slides]
[4] Computational Journeys in a Sparse Universe (2024 European Edition). EPFL, Applied Math Department, June 2024, Lausanne, Switzerland [Slides]
[5] Full-batch and Mini-batch Distributed Graph Neural Network Training. The Platform for Advanced Scientific Computing (PASC) Conference, June 2024, Zurich, Switzerland [Slides]
[6] Fast Multiplication of Random Dense Sketch Matrix with Sparse Data Matrices. SIAM Conference on Applied Linear Algebra, May 2024, Paris, France [Slides]
[7] ExaGraph: Graph & Combinatorial Methods for Enabling Exascale Applications. SIAM Conference on Parallel Processing for Scientific Computing, March 2024, Baltimore, MD [Slides]
[8] Sparsitute: A mathematical Institute for Sparse Computations in Science and Engineering. Plenary at the DOE ASCR Applied Math and MMICCs PI meeting, Jan 2024, Albuquerque, NM [Slides]
[9] Computational Journeys in a Sparse Universe. Oak Ridge National Laboratory (also at University of Utah), Nov 2023 [Slides]
[10] Sparse BLAS is not just for Numerical Linear Algebra. Keynote at the Sparse BLAS Workshop, UTK, Nov 2023, Knoxville, TN [Slides]
[11] 3S in Distributed Graph Neural Networks: Sparse communication, Sampling, Scalability GraphEx Symposium, August 2023, Boston, MA [Slides]
[12] The Ubiquitous Sparse Matrix Products JRG70 Workshop, June 2023, Santa Barbara, CA [Slides]
[13] Distributed sparse matrices in graph algorithms and graph learning. Keynote at GTA3 Workshop, IEEE BigData, December 2022 [Slides]
[14] Sparse matrices powering three pillars of science: simulation, data, and learning. ACM ISSAC, Invited Tutorial, July 2022, Lille, France [All slides] [Video Part 1] [Video Part 2]
[15] Parallel Sparse Matrix Algorithms for Data Analysis and Machine Learning. ETH Zurich (SPCL_BCast seminar series), March 2022 [Slides] [Video]
[16] Large-scale graph representation learning and computational biology through sparse matrices. NJIT Institute for Data Science, April 2021 [Slides] [Video]
[17] Sparse Matrices Beyond Solvers - Graphs, Biology, and Machine Learning. MIT (Fast Code Seminar series), June 2020 [Slides] [Video]
[18] GraphBLAST: A High-Performance Linear Algebra-based Graph Framework on the GPU. ACS HPC and Data Analytics Workshop, Baltimore, MD, 2019 [Slides]
[19] GraphBLAS in Data Analytics and Machine Learning. ACS Reverse Site Visit, Berkeley, CA, 2019 [Slides]
[20] Communication-Avoiding Sparse Matrix Algorithms for Large Graph and Machine Learning Problems. SIAM CSE, Spokane, WA, 2019 [Slides]
[21] Large-scale parallel computing for computational genomics. H.Bioinfo-11, Thessaloniki, Greece, 2018 [Slides]
[22] Communication-Avoiding Sparse Matrix Primitives for Parallel Machine Learning. Sparse Days, Toulouse, France, 2018 [Slides]
[23] Scaling Parallel Graph Analysis & Machine Learning using Sparse Matrix Operations. Seminar at Michigan State University and NERSC, 2018 [Slides]
[24] Graph algorithms, computational motifs, and GraphBLAS. Exascale Computing Project 2nd Annual Meeting, Exagraph Tutorial Session, Knoxville, TN, 2018 [Slides]
[25] Parallel Algorithms across the GraphBLAS Stack. ACS HPC and Data Analytics Workshop, Baltimore, MD, 2017 [Slides]
[26] Faster parallel Graph BLAS kernels and new graph algorithms in matrix algebra. EECS, UC Berkeley, 2016 [2016 Slides] and HP Labs, Palo Alto, CA, 2015 [2015 Slides]
[27] Parallel de novo Assembly of Complex (Meta) Genomes via HipMer. Invited Talk at HiCOMB, IPDPS, Chicago, IL, 2016 [Slides]
[28] Scalable algorithms for genome assembly, alignment, and genetic mapping. Georgia Institute of Technology, School of Computational Science and Engineering, Atlanta, GA, 2015 [Slides]
[29] Distributed-Memory Parallel Algorithms for Graph Traversal and Genome Assembly. SUNY Stony Brook, SUNY Albany, SUNY Buffalo , NY, 2014 [Slides]
[30] The Graph BLAS effort and its implications for Exascale. SIAM Workshop on Exascale Applied Mathematics Challenges and Opportunities (EX14) , Chicago, IL, 2014 [Slides]
[31] Reducing Communication in Parallel Graph Computations. Workshop on Algorithms for Modern Massive Data Sets (MMDS) , Berkeley, CA, 2014 [Slides | Video]
[32] High-Productivity and High- Performance Analysis of Filtered Semantic Graphs. SIAM Conference on Parallel Computing , Portland, OR, 2014 [Slides]
[33] Three Goals in Parallel Graph Computations: High Performance, High Productivity, and Reduced Communication. Seminar at the Simons Institute , Berkeley, CA, 2013. [Video and Slides]
[34] A sustainable software stack for parallel graph analysis. Discovery 2015: HPC and Cloud Computing Workshop, Berkeley, CA, 2012 [slides]
[35] Parallel algorithms for sparse matrix product, indexing, and assignment. In Scientific Computing and Matrix Computations Seminar, UC Berkeley 2012. [slides]
[36] Parallel Breadth-First Search on Distributed Memory Systems. In Supercomputing, Seattle 2011. [slides]
[37] An Overview of the Combinatorial BLAS and Knowledge Discovery Toolbox. IBM Exascale Analytics Discussion, 2011. [slides]
[38] Scalable Parallel Primitives for Massive Graph Computation. Invited talk at Sandia National Labs, Lawrence Berkeley National Lab, and Argonne National Lab, 2010. [slides]
[39] Parallel Sparse Matrix-Vector and Matrix-Transpose-Vector Multiplication Using Compressed Sparse Blocks. In ACM Symposium on Parallelism in Algorithms and Architectures (SPAA) , Calgary, Canada, 2009. [slides]
[40] Challenges and advances in parallel sparse matrix-matrix multiplication. In International Conference on Parallel Processing (ICPP), Portland, 2008. [slides]
[41] Gaussian Elimination Based Algorithms on the GPU. In International Workshop on Parallel Matrix Algorithms and Applications (PMAA), Neuchâtel, Switzerland, 2008. [slides]