## Edgar Solomonik

Postdoctoral Researcher at ETH Zürich

E-mail: edgar DOT solomonik AT gmail DOT com

Office: CAB E63, Universitätstrasse 6, 8092 Zürich

### Information:

ETH Zürich Postdoctoral Fellow (since Oct 2014), working at SPCL with Prof. Torsten Hoefler
PhD in Computer Science from University of California Berkeley, August 2014, advised by Prof. James Demmel
BS in Computer Science from University of Illinois, Urbana-Champaign, May 2010, advised by Prof. Laxmikant Kale
Leads development of Cyclops Tensor Framework
(Doxygen,
GitHub) and NuLAB
(GitHub)
Supported by a
DOE Computational Science Graduate Fellowship 2010-2014
Received the
2013 NERSC Award for Innovative Use of High Performance Computing,
the 2013 ACM-IEEE George Michael HPC Fellowship,
and the 2014 David J. Sakrison Memorial Prize
Interested in numerical and graph algorithms, especially in the context of
massively-parallel electronic structure and molecular dynamics calculations
### Publications:

Edgar Solomonik;
__Provably Efficient Algorithms for Numerical Tensor Algebra__;
Dissertation, University of California, Berkeley, August 2014.
(pdf)
(bibtex)

Edgar Solomonik, Devin Matthews, Jeff R. Hammond, John F. Stanton, and James Demmel;
__A massively parallel tensor contraction framework for coupled-cluster computations__;
Journal of Parallel and Distributed Computing, June 2014.
(report)
(paper)
(bibtex)

Edgar Solomonik, Erin Carson, Nicholas Knight, and James Demmel;
__Tradeoffs between synchronization, communication, and work in parallel linear algebra computations__;
26th ACM Symposium on Parallelism in Algorithms and Architectures, Prague, Czech Republic, June 2014.
(report)
(paper)
(bibtex)

Grey Ballard, James Demmel, Laura Grigori, Mathias Jacquelin, Hong Diep Nguyen, and Edgar Solomonik;
__Reconstructing Householder Vectors from Tall-Skinny QR__;
IEEE International Parallel and Distributed Processing Symposium (IPDPS),
Phoenix, AZ, May 2014.
(report)
(paper)
(bibtex)

Edgar Solomonik, Devin Matthews, Jeff Hammond, and James Demmel;
__Cyclops Tensor Framework: reducing communication and eliminating load imbalance in massively parallel contractions__;
IEEE International Parallel and Distributed Processing Symposium (IPDPS),
Boston, MA, May 2013.
(report)
(paper)
(bibtex)

Edgar Solomonik, Aydin Buluc, and James Demmel; __Minimizing communication in all-pairs shortest-paths__;
IEEE International Parallel and Distributed Processing Symposium (IPDPS),
Boston, MA, May 2013.
(report)
(paper)
(bibtex)

Michael Driscoll, Evangelos Georganas, Penporn Koanantakool, Edgar Solomonik, and Katherine Yelick;
__A Communication-Optimal N-Body Algorithm for Direct Interactions__;
IEEE International Parallel and Distributed Processing Symposium (IPDPS),
Boston, MA, May 2013.
(paper)
(bibtex)

Evangelos Georganas, Jorge Gonzalez-Dominguez, Edgar Solomonik, Yili Zheng, Juan Tourino and Katherine Yelick;
__Communication Avoiding and Overlapping for Numerical Linear Algebra__;
ACM/IEEE Supercomputing Conference, Salt Lake City, Utah, November 2012.
(report)
(paper)
(bibtex)

Edgar Solomonik and James Demmel; __Matrix multiplication on multidimensional torus networks__,
Springer Lecture Notes in Computer Science (LNCS), Proceedings of VECPAR, Kobe, Japan, July 2012.
(report)
(paper)
(bibtex)

Edgar Solomonik, Jeff Hammond, and James Demmel; __A preliminary analysis of Cyclops Tensor Framework__;
EECS Department, University of California, Berkeley, March 2012.
(report)
(bibtex)

Edgar Solomonik, Abhinav Bhatele, and James Demmel; __Improving
communication performance in dense linear algebra via topology
aware collectives__;
ACM/IEEE Supercomputing Conference 2011, Seattle, WA, November 2011.
(report)
(paper)
(bibtex)

Edgar Solomonik and James Demmel; __Communication-optimal parallel 2.5D matrix
multiplication and LU factorization algorithms__; Lecture Notes in Computer Science,
Euro-Par, Bordeaux, France, August 2011. "Distinguished Paper"
(report)
(paper)
(bibtex)

Laxmikant Kale and Edgar Solomonik; __Parallel Sorting;__
Encyclopedia of Parallel Computing, Springer Verlag, David Padua, Ed., 2011.

Edgar Solomonik and Laxmikant V. Kale; __Highly Scalable Parallel Sorting__;
IEEE International Parallel and Distributed Processing Symposium (IPDPS),
Atlanta, GA, April 2010.
(paper)
(bibtex)

Vivek Kale and Edgar Solomonik; __Parallel Sorting Pattern__; Workshop on Parallel Programming Patterns
(ParaPLOP), March 2010. (paper)
(bibtex)

Abhinav Bhatele, Lukasz Wesolowski, Eric Bohm, Edgar Solomonik, and Laxmikant V. Kale;
__Understanding Application Performance via Micro-benchmarks on Three Large Supercomputers:
Intrepid, Ranger and Jaguar__; International Journal of High Performance
Computing Applications (IJHPCA), November 2010.
(paper)
(bibtex)

### Talks:

(pdf) August 2014; Dissertation talk; Berkeley CA, USA;
Provably efficient algorithms for numerical tensor algebra

(pdf) July 2014; DOE CSGF Program Review; Washington DC, USA;
Minimizing communication in numerical linear algebra

(pdf) June 2014; SPAA; Prague, Czech Republic;
Tradeoffs between synchronization, communication, and computation in parallel linear algebra computations

(pdf) June 2014; ETH Zurich;
Algorithms for contraction of tensors over a commutative ring

(pdf) June 2014; Householder Symposium XIX; Spa, Belgium;
Contracting symmetric tensors via fully-symmetric intermediates

(pdf) Feb 2014; LBNL, Berkeley, CA;
Cyclops Tensor Framework

(pdf) Feb 2014; SIAM PP; Portland, OR;
Tradeoffs between synchronization, communication, and work in parallel linear algebra computations

(pdf) Feb 2014; Berkeley, CA;
Tradeoffs between synchronization, communication, and work in parallel schedules

(pdf) Feb 2014; Berkeley, CA;
Fast tensor contraction algorithms for Coupled Cluster

(pdf) Dec 2013; Laguna Beach, CA;
A distributed-memory framework for tensor contractions

(pdf) Dec 2013; Berkeley, USA;
A framework for mapping and redistribution of multidimensional distributed arrays

(pdf) Oct 2013; Berkeley, USA;
Communication-avoiding algorithms for dense matrix factorizations

(pdf) Oct 2013; Berkeley, CA;
Efficient algorithms for symmetric tensor contractions

(pdf) June 2013; ETH Zurich; Switzerland;
Communication-avoiding parallel algorithms for dense linear algebra

(pdf) June 2013; Swiss National Supercomputing Centre; Lugano, Switzerland;
Communication-avoiding parallel numerical algorithms for dense matrices and tensors

(pdf) May 2013; IPDPS; Boston, USA;
Cyclops Tensor Framework: reducing communication and eliminating load imbalance in massively parallel contractions

(pdf) May 2013; IPDPS; Boston, USA;
Minimizing communication in all-pairs shortest paths

(pdf) March 2013; SIAM CSE; Boston, USA;
Scalable numerical algorithms for electronic structure calculations

(pdf) February 2013; Berkeley, USA;
Communication-avoiding parallel algorithms for dense linear algebra and tensor Computations

(pdf) January 2013; University of Southern California; LA, USA;
A parallel tensor framework for Coupled Cluster

(pdf) Sep. 2012; seminar; Lawrence Livermore National Laboratory; Livermore, CA;
Scalable numerical algorithms for electronic structure calculations

(pdf) July 2012; University of Tokyo; Tokyo, Japan;
2.5D algorithms for distributed-memory computing

(pdf) July 2012; VECPAR; Kobe, Japan;
Matrix multiplication on multidimensional torus networks

(pdf) June 2012; SIAM ALA; Valencia, Spain;
2.5D Algorithms for dense linear algebra

(pdf) Feb. 2012; SIAM PP; Savannah, GA;
Topology-aware parallel algorithms for symmetric tensor contractions

(pdf) Nov. 2011; ACM/IEEE Supercomputing; Seattle, WA;
Improving communication performance in dense linear algebra via topology-aware collectives

(pdf) Sep. 2011; CS 294 lecture; Berkeley, CA;
2.5D algorithms: from hardware to theory and back

(pdf) Sep. 2011; Bordeaux, France;
Communication-optimal parallel 2.5D matrix multiplication and LU factorization algorithms

(pdf) Aug. 2011; seminar; Argonne National Laboratory; Argonne, IL;
Reducing communication in dense matrix/tensor computations

(pdf) Apr. 2010; IPDPS; Atlanta, GA;
Highly Scalable Parallel Sorting

### Posters:

(pdf) Jul. 2013; CSGF conference; Arlington, VA;
Cyclops Tensor Framework.

(pdf) Jul. 2011; CSGF conference; Arlington, VA;
2.5D algorithms for dense linear algebra

(pdf) Nov. 2009; ACM/IEEE Supercomputing; Portland, OR
Performance Comparison of Intrepid, Jaguar and Ranger Using Scientific Applications