Curriculum Vitae: E. Jason Riedy

Table of Contents

PDF version, Plain text version, BibTeX

Contact Information

Employment

Institution
Advanced Micro Devices, Inc. (AMD)
Title
Principal Member of Technical Staff
Since
Mar 2024
Previous Institution
Lucata Corporation (née Emu Technology)
Until
Jan 2024
Title
Member of Technical Staff
Since
2020
Previous Institution
School of Computational Science and Engineering, College of Computing, Georgia Institute of Technology
Until
2020
Title
Director of the CRNCH Rogues Gallery with Jeffrey Young
Since
2017
Title
Senior Research Scientist
Since
2016
Title
Research Scientist
Since
2009

Education

Technical Experience

2021 – present
IEEE P3109 — Arithmetic Formats for Machine Learning
2020 – Jan 2024
Optimizing for the Lucata migratory thread PGAS platform. Tasks / accomplishments include:
  • Porting the required compiler pieces from LLVM 6 to LLVM 14.
  • Supporting and exposing many novel hardware features to programmers.
  • Evaluating concurrent graph analysis on the Lucata architecture, achieving a 19× speed-up over RedisGraph running 128 breadth-first searches concurrently.
  • Moving the assembler from an Early grammar to LALR(1), drastically improving compile times.
  • Developing and implementing GraphBLAS components, including support for RedisGraph.
  • General C++ library infrastructure development supporting novel aspects of the architecture.
  • And others…
2017 – 2020
Director of the Rogues Gallery of novel, post-Moore systems in the Center for Research into Novel Computing Hierarchies.
2016 – present
Developing a "next generation BLAS" specification to ease tuning, support extended and novel precisions, and include composable reproducible linear algebra primitives.
2015 – 2019, 2023 – present
IEEE 754 revision (floating-point arithmetic): Operations to support extended precision and reproducible linear algebra.
2011 – 2019
Development and support for a high-performance shared memory community detection package for massive graphs.
2010 – 2014
Defining the Graph500 benchmark and providing the reference implementations for sequential and shared memory platforms (OpenMP, Cray XMT).
2009 – 2020
Development of STINGER, a framework for analyzing massive graphs with streaming input on both OpenMP platforms and the Cray XMT.
2009 – 2013
Support and porting for GraphCT, a massive graph characterization toolkit.
2009 – 2013
CASS-MT and follow-on projects: Development of STINGER, a framework for analyzing massive graphs with streaming input on both OpenMP platforms and the Cray XMT. Support and porting of GraphCT, a massive graph characterization toolkit, and STINGER, a streaming graph analysis framework.
2001 – 2006
IEEE-754 revision (floating-point arithmetic): Programming language interactions, exceptional behavior, decimal formats and arithmetic.
2002 – 2009
Sca/LAPACK project: Development of coding standards, integration of C routines, multiplatform testing and debugging, code and design review.
1994 – 1999
Systems administration: Maintenance of servers and file systems for CISE Department, Univ. of Florida, including performance tuning, troubleshooting, file system backups, and end-user support.
1995
Visualization: Animations of molecular dynamics simulations.

Research Project Experience

2017 – 2020
SuperSTARLU: Developing logical primitives for advanced memory systems (3D stacked, hybrid memory cube) in support of unsymmetric sparse matrix factorization. (co-PI)
2017 – 2019
DHS Center for Accelerating Operational Efficiency: Predictive analysis of massive streaming graphs. (co-PI)
2017 – 2018
Evaluating memory-centric architectures for high performance data analysis: Combining architecture and algorithms to achieve high performance on architectures like the Emu Technology platform, where memory operations are moved to be local. Focuses on streaming graph analysis and sparse tensor decomposition. (PI)
2016 – 2018
High Performance Data Analytics (HPDA): High-performance data analysis for streaming graphs. (PI and co-PI, different years)
2015 – 2017
NSF Embrace: Evolvable Methods for Benchmarking Realism through Application and Community
2014 – 2016
Idaho Bailiff: High-performance data analysis for streaming graphs. (co-PI)
2013 – 2018
NSF XScala: High-performance kernel development, curation, and modeling for accelerators. (co-PI)
2012 – 2018
DARPA GRATEFUL: Graph analysis optimizing power and efficiency. Under the DARPA Power Efficiency Revolution for Embedded Computing Technologies (PERFECT) program. Accelerating, porting, and maintaining RISC-V-based streaming graph analysis. (co-PI)
2010 – 2014
STING: Spatio-Temporal Interaction Networks and Graphs An open-source dynamic graph package for Intel platforms. (co-PI)
2010 – 2013
Evaluation of the IBM PERCS and Cray Cascade HPCS architectures. (co-PI)
2009 – 2013
CASS-MT: Massively parallel graph analysis (537M node, 8.6B edge), threaded architectures, streaming data analysis and error modeling.
2009
NSF I/UCRC: Center for hybrid multi-core productivity research
2002 – 2009
LAPACK, ScaLAPACK, and XBLAS (dense linear algebra): Extra-precise linear system refinement algorithms, eigenvalue routines, and optimization.
1999 – 2009
SuperLU (sparse linear algebra): Parallel combinatorial preprocessing, numerical stability analysis, iterative solver preconditioning.
1996 – 1999
Image Algebra (image analysis): SIMD parallel optimization, edge detection, geometric hashing.

Students Supervised

Teaching Experience

Spring 2021
Teaching/advising Living Building Science. This Vertically Integrated Project is a continuation of Bee-Snap in the wider perspective of the Kendeda Living Building at Georgia Tech. We are continuing the honeybee related projects while also lending data analysis expertise to other groups within the larger project.
Fall 2015 – Fall 2020
Teaching/advising Bee-Snap, a Vertically Integrated Project collecting and analyzing big data about bee-flower interactions on the Georgia Tech campus and beyond to inform property owners and policy makers about how land use can support pollinator health. With Jennifer Leavey in Biology. Students have won Serve-Learn-Sustain poster sessions, both 1st and 2nd place. "Thank a Teacher" award in fall 2017. Number of undergraduates varies per semester. Internal funding for class projects. Internal link: https://vip.gatech.edu/wiki/index.php/Bee-Snap (Previously also with Bistra Dilkina and Polo Chau in CSE.)
Spring 2019 – Spring 2020
Teaching/advising a Vertically Integrated Project introducing undergraduates to novel architectures via the Rogues Gallery. With Jeffrey Young.
Fall 2014 – May 2016
Advising of a Masters thesis into trade-offs between community quality and change size when adapting to streaming data. Student: Pushkar Godbolé. Title: Agglomerative Clustering for Community Detection in Dynamic Graphs. (joined Yelp)
Summer 2014
Advising of two undergraduate CRUISE students in graph analysis projects in projects on sparse matrix - sparse vector products for graph analysis and identifying key members in graph communities.
Spring 2013, Fall 2013
Advising of Masters level research project in social network data acquisition and analysis.
Fall 2012
Guest lectures in CSE8803-MGA, Georgia Tech's special topics class in massive graph analysis. Topics include streaming graph analysis, parallel community detection, and experiment design.
Spring, Fall 2010
Guest lectures in CSE6140, Georgia Tech's parallel algorithms and applications class. Topics include floating-point arithmetic, parallel linear algebra, and parallel programming environments.
Spring 2010
Shared advising of Masters level research project in seeded community detection.
Fall 2008
Adjunct faculty in mathematics at Virginia Intermont College. Teaching Concepts of Modern Mathematics I (focused on elementary education majors) and Discrete Mathematics I (required mathematics class for most majors). Constructed the programs from only the required textbook.
Fall 2006, Spring 2007
Mentor for Intel Undergraduate Research program. Introduced undergraduates into our research group on both mathematical and technical levels.
Spring 2000, 2004
Assistant for Applications of Parallel Computing. Multidisciplinary, graduate level class focused on introducing scientists to practical aspects of high-performance computers, tools, and programming.

Awards, Recognition, and Honors

  • Georgia Tech College of Computing Outstanding Research Scientist, 2017
  • Georgia Tech "Thank a Teacher" award, fall 2017
  • Georgia Tech Research Teaching Fellow, 2016-2017
  • Best paper award, IEEE High Performance Extreme Computing Conference, 2012
  • The 10th DIMACS Implementation Challenge's Mix and Mix Pareto challenges winner, 2012
  • Institute for Data and High Performance Computing Fellow, 2010-2011

Software

(By its nature, this section always will be a bit out of date. And many of the links currently are busted for various reasons. I’ll fix them over time but can provide tarballs.)

Refereed Journals

Book Chapters

Invited Presentations

Conference Proceedings

Conference Tutorials

Technical Reports

Presentations

Other Publications

Projects

  • Martin Deneroff (PI) and Jason Riedy. Non-Blocking Updates to Graph Databases. NSF 2105977, August 2021. $255,916. (bib).
  • Jeffrey Young (PI), Jennifer Hasler, Ada Gavrilovska, Thomas Conte, and Jason Riedy. CCRI: Medium: Rogues Gallery: A Community Research Infrastructure for Post-Moore Computing. NSF 2016701, September 2020, (grant). $1,351,699. (bib).
  • Jason Riedy (PI), Will Powell, and D. B. POWER Systems for Data Analysis and HPC classes. Georgia Institute of Technology, Technology Fee Proposal, July 2019, (equipment grant). $96,272. (bib).
  • David A. Bader (PI), Jason Riedy, and Haesun Park. High-Performance Data Analytics (HPDA) Research Topics, January 2018, (grant). $100,000. (bib).
  • E. Jason Riedy (PI), David A. Bader, and Thomas M. Conte. Evaluating Memory-centric Architectures for High Performance Data Analysis, August 2017, (grant). $662,525. (bib).
  • Jeffrey S. Young (PI), Jason Riedy (coPI), and Richard Vuduc (coPI). CDS&E: SuperSTARLU - STacked, AcceleRated Algorithms for Sparse Linear Systems, August 2017, (grant). $500,000. (bib).
  • E. Jason Riedy and David Bader. Support for Data Analytics for CSE Programs and Courses. Georgia Institute of Technology, Technology Fee Proposal, July 2016, (equipment grant). $194,150. (bib).
  • David A. Bader (PI GT), Jack Dongarra (PI UTK), Jason Riedy (coPI GT), Richard Vuduc (coPI GT), and Piotr Luszczek (coPI UTK). Collaborative Research: EMBRACE: Evolvable Methods for Benchmarking Realism through Application and Community Engagement, September 2015, (grant). $125,000. (bib).
  • David A. Bader (PI GT), E. Jason Riedy (coPI GT), Rich Vudic (coPI GT), and Viktor Prasanna (PI USC). SI2-SSI: Collaborative: The XScala Project: A Community Repository for Model-Driven Design and Tuning of Data-Intensive Applications for Extreme-Scale Accelerator-Based Systems (NSF ACI-1339745), October 2013, (grant). $1,937,624, ($1,188,710 GA Tech portion). (bib).
  • David A. Bader (PI) and E. Jason Riedy (coPI). GRATEFUL: GRaph Analysis Tackling power EFficiency, Uncertainty, and Locality. coPI for DARPA award under the Power Efficiency Revolution for Embedded Computing Technologies (PERFECT) program, August 2012, (grant). $2,929,819. (bib).
  • David A. Bader (PI) and E. Jason Riedy (coPI). Benchmarking the IBM PERCS and Cray CASCADE architectures. coPI for DARPA award, June 2011, (grant). $287,994. (bib).
  • Viktor Prasanna (PI USC), David A. Bader (PI GT), Manish Parashar (PI Rutgers), Jason Riedy (coPI GT), Rich Vuduc (coPI GT), Yogesh Simmhan (coPI USC), and Shantenu Jha (coPI Rutgers). Collaborative Research: Software Infrastructure for Accelerating Grand Challenge Science with Future Computing Platforms. coPI for NSF award under the Software Institutes program, October 2012, (grant). $104,386. (bib).
  • E. Jason Riedy and David A. Bader. Oracle: Multithreaded Algorithms. Grant for two Oracle X4470 servers with two processors, 0.5TiB and four processors 1.0TiB, April 2012, (equipment grant). $118,000. (bib).
  • E. Jason Riedy and Logan Moon. Teaching Massive Data Analysis and Manycore Computing. Georgia Institute of Technology, Technology Fee Proposal, July 2011, (equipment grant). $223,800. (bib).
  • E. Jason Riedy. Evaluating PGAS scientific graph analysis codes on the Gemini interconnect. Department of Energy NERSC Initiative for Scientific Exploration, June 2011, (computing time grant). 250,000 hours of DoE processing time. (bib).
  • E. Jason Riedy and David A. Bader. STING: Spatio-Temporal Interaction Networks and Graphs; An open-source dynamic graph package for Intel platforms. Intel RFP on Parallel Algorithms in Non-Numeric Computing, April 2010, (grant). $375,000. (bib).
  • David A. Bader (PI) and E. Jason Riedy. Dynamic Graph Data Structures in X10. IBM X10 Innovation Award, December 2009, (grant). $20,000. (bib).

Nontechnical Writing

Interesting Mentions

External Publication Lists

Lists at various external bibliography services:

Professional Societies

Association for Computing Machinery
Member since 1992. Univ. of Florida secretary 1995-1997.
Society for Industrial and Applied Mathematics
Member since 2000.
Society of Physics Students
Member 1993-1996. Univ. of Florida local officer 1994-1996.
IEEE
Member since 2009. Standards Association member as necessary.

Professional Service

  • Standardization committees:
    • IEEE 754-2xxx study group
    • IEEE P3109 working group
    • IEEE 754-2019 revision committee member, ballot resolution sub-committee member
    • IEEE 754-2008 revision committee member, website and email archive maintenance
  • Program committee member for:
    • IEEE International Symposium on Computer Arithmetic (ARITH) 2021–2024
    • IEEE International Parallel & Distributed Processing Symposium (IPDPS) 2013, 2016-2018. 2023, 2024
    • Euro-PAR 2024
    • International Conference on Parallel Processing (ICPP) 2015, 2019, 2020
    • Workshop on Irregular Applications: Architectures and Algorithms 2019
    • PAW-ATM 2019: Parallel Applications Workshop – Alternatives to MPI
    • GrAPL 2019: Workshop on Graphs, Architectures, Programming, and Learning
    • Technical program of the International Conference for High Performance Computing, Networking, Storage, and Analysis (SC) 2019
    • IEEE International Conference on High Performance Computing (HiPC) 2013, 2017, 2018
    • First Workshop on High Performance Graph Data Mining and Machine Learning (HPGDML) 2017
    • First Workshop on the Intersection of Graph Algorithms and Machine Learning (GRAML) 2017
    • Workshop on Irregular Applications: Architectures and Algorithms (IA3) 2016, 2017
    • Architecture, Languages, Compilation and Hardware support for Emerging ManYcore systems (ALCHEMY) 2015, 2017
    • Workshop on High Performance Graph Data Management and Processing (HPGDMP) 2016
    • High Performance Graph Processing 2016
    • Graph Data Management Experiences and Systems (GRADES) 2015
    • Second SDM Workshop on Mining Networks and Graphs: A Big Data Analytic Challenge 2015
    • Graph Data Management Experiences and Systems (GRADES) 2014
    • 8th Workshop on Multithreaded Architectures and Applications (MTAAP) 2014
  • Referee/technical reviewer for (partial list):
    • ACM Journal of Experimental Algorithmics (JEA)
    • ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming (PPoPP)
    • ACM Transactions on Architecture and Code Optimization (TACO)
    • ACM Transactions on Knowledge Discovery from Data (TKDD)
    • ACM Transactions on Mathematical Software (TOMS)
    • ACM/IEEE International Conference on Grid Computing (GRID)
    • Algorithms and Data Structures Symposium (WADS)
    • Circlet Press
    • Computer Journal
    • European Symposium on Algorithms (ESA)
    • IBM Journal of Research and Development
    • IEEE Cluster
    • IEEE International Parallel and Distributed Processing Symposium (IPDPS)
    • IEEE International Symposium on Computer Arithmetic (Arith)
    • IEEE Transactions on Computers
    • IEEE Transactions on Emerging Topics in Computing
    • IEEE Transactions on Intelligent Systems and Technology
    • IEEE Transactions on Knowledge and Data Engineering
    • IEEE Transactions on Parallel and Distributed Systems (TPDS)
    • Innovating Parallel Computing (INPAR)
    • International Conference for High Performance Computing, Networking, Storage and Analysis (SC)
    • International Journal of High Performance Computing (IJHPC)
    • International Symposium on Code Generation and Optimization (CGO)
    • International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD)
    • International Symposium on Distributed Computing (DISC)
    • International Symposium on Experimental Algorithms (SEA)
    • International Workshop on Accelerators and Hybrid Exascale Systems (AsHES)
    • Journal of Combinatorial Optimization
    • Journal of Parallel and Distributed Computing (JPDC)
    • Journal of Systems and Software
    • O'Reilly
    • Parallel Computing
    • SIAM Journal on Matrix Analysis and Applications (SIMAX)
    • SIAM/ACM Algorithm Engineering and Experiments (ALENEX)
    • 10th DIMACS Implementation Challenge