HIGHLIGHTS (TL; DR)
-
(5 min watch, SIGCSE Video Link ) Jove software. The contents of Jove's Github allow you to ``Sculpt Automata'' using Jupyter notebooks. See accompanying textbook info bottom of this page.
- NSF 2403379, Collaborative Research: SHF: Medium: SciOPT : Toward Certifiable Compression-Aware SciML Systems. Expected to begin Fall 2024 for three years.
- NSF 2346394, Collaborative Research: CIRC: Medium: New: Workbench for Reliable and Efficient Numerics. Expected to begin Fall 2024 for three years.
- NSF2426055, FMiTF: Track-2: Rigorous and Scalable Formal Floating-Point Error Analysis from LLVM. FMiTF, Track-2. Awarded 7/19/2023 for one year.
- NSF 2244492, REU Site, REU Site: Trust and Reproducibility Education for Undergraduates. Intelligent Computation for Science and Engineering. Awarded 2/27/2023 for three years.
- NSF 2217154, Senior Personnel, PPoSS. Collaborative Research: PPoSS: Large: A comprehensive framework for efficient, scalable, and performance-portable tensor applications. Awarded 6/2022 for five years.
- NSF 2124100, Collaborative Research: FMitF: Track-1: Correctness at Both Ends (CBE): Rigorous ML Meets Correct and Efficient Sparse Implementations. Awarded 6/2021 for three years.
- NSF 1956106, Collaborative Research: SHF: Medium: Practical and Rigorous Correctness Checking and Correctness Preservation for Irregular Parallel Programs. Awarded 7/2020 for three years. Now operating under a one-year no-cost extension.
- Recent Papers and Software Releases:
- HiRace: Accurate and Fast Source-Level Race Checking of GPU Programs, John Jacobson, Martin Burtscher, Ganesh Gopalakrishnan, Accepted in Supercomputing 2024. Arxiv link for HiRace
- FPBOXer: Efficient Input-Generation for Targeting Floating-Point Exceptions in GPU Programs, Authors: Anh Tran, Ignacio Laguna and Ganesh Gopalakrishnan, HPDC 2024.
- Rigorous Error Analysis for Logarithmic Number Systems, Thanh Son Nguyen, Alexey Solovyev, Ganesh Gopalakrishnan. 2024. Arxiv link for LNS
- Report of the DOE/NSF Workshop on Correctness in Scientific Computing, June 2023, Orlando, FL. Maya Gokhale, Ganesh Gopalakrishnan, Jackson Mayo, Santosh Nagarakatte, Cindy Rubio-González, Stephen F. Siegel. Arxiv link for the CSC report
- (Best Workshop Paper Award) What Operations can be Performed Directly on Compressed Arrays, and with What Error? Tripti Agarwal, Harvey Dam, Ponnuswamy Sadayappan, Ganesh Gopalakrishnan, Dorra Ben Khalifa, Matthieu Martel. SC Workshops 2023: 252-262 Arxiv link for PyBlaz paper PyBlaz Software
- Design and Evaluation of GPU-FPX: A Low-Overhead tool for Floating-Point Exception Detection in NVIDIA GPUs. Xinyi Li, Ignacio Laguna, Bo Fang, Katarzyna Swirydowicz, Ang Li, and Ganesh Gopalakrishnan. HPDC 2023. GPU-FPX paper link. GPU-FPX Software
- FTTN: Feature-Targeted Testing for Numerical Properties of NVIDIA & AMD Matrix Accelerators Xinyi Li, Ang Li, Bo Fang, Katarzyna Swirydowicz, Ignacio Laguna and Ganesh Gopalakrishnan. CCGrid 2024. FTTN Software Zenodo link to FTTN Software
- FPBOXer: Efficient Input-Generation for Targeting Floating-Point Exceptions in GPU Programs, Authors: Anh Tran, Ignacio Laguna and Ganesh Gopalakrishnan, HPDC 2024.
- Finding Inputs that Trigger Floating-Point Exceptions in GPUs via Bayesian Optimization Authors: Ignacio Laguna and Ganesh Gopalakrishnan, Supercomputing 2022
- BinFPE: Accurate Floating-Point Exception Detection for GPU Applications Authors: Ignacio Laguna, Xinyi Li and Ganesh Gopalakrishnan, 11th ACM SIGPLAN International Workshop on the State Of the Art in Program Analysis (SOAP 2022)
- Ignacio Laguna, Tanmay Tirpankar, Xinyi Li and Ganesh Gopalakrishnan, ``FPChecker: Floating-Point Exception Detection Tool and Benchmark for Parallel and Distributed HPC,'' IEEE International Symposium on Workload Characterization (IISWC) 2022
- Guarding Numerics Amidst Rising Heterogeneity Authors: G. Gopalakrishnan, I. Laguna, A. Li, P. Panchekha, C. Rubio-González and Z. Tatlock, 2021 IEEE/ACM 5th International Workshop on Software Correctness for HPC Applications
- Keeping Science On Keel When Software Moves Authors: Dong Ahn, Allison H. Baker, Michael Bentley, Ian Briggs, Ganesh Gopalakrishnan, Dorit M. Hammerling, Ignacio Laguna, Gregory L. Lee, Daniel J. Milroy, Mariana Vertenstein, February 2021
- A Programmable Approach to Model Compression, Authors: Vinu Joseph, Saurav Muralidharan, Animesh Garg, Michael Garland, and Ganesh Gopalakrishnan, IEEE Micro, Special Issue on ML for Systems (Track 2), Volume: 40 , Issue: 5 , Sept.-Oct. 1 2020, (IEEE Xplore)
- FPDetect: Efficient Reasoning About Stencil Programs Using Selective Direct Evaluation Arnab Das, Sriram Krishnamoorthy, Ian Briggs, Ganesh C Gopalakrishnan, and Ramakrishna Tipireddy, ACM Transactions on Architecture and Code Optimization, August 2020, Article No.: 19.
- FailAmp: Relativization Transformation for Soft Error Detection in Structured Address Generation Authors: Ian Briggs, Arnab Das, Marek S Baranowski, Vishal Chandra Sharma, Sriram Krishnamoorthy, Zvonimir Rakamaric, and Ganesh C Gopalakrishnan. ACM Transactions on Architecture and Code Optimization (TACO), 2019.
- (Best Student Paper in Supercomputing 2020) An Abstraction-guided Approach to Scalable and Rigorous Floating-Point Error Analysis Arnab Das, Ian Briggs, Ganesh Gopalakrishnan, Pavel Panchekha, Sriram Krishnamoorthy, Supercomputing 2020.
- Rigorous Estimation of Floating-Point Round-off Errors with Symbolic Taylor Expansions. Marek S. Baranowski, Ian Briggs, Charles Jacobsen, Zvonimir Rakamari\'c, and Ganesh Gopalakrishnan. ACM Trans. Program. Lang. Syst. 41, no. 1 (December 2018): 2:1-2:39. doi:10.1145/3230733.
- DiffTrace: Efficient Whole-Program Trace Analysis and Diffing for Debugging. Authors: Taheri, Saeed, Ian Briggs, Martin Burtscher, and Ganesh Gopalakrishnan. IEEE Cluster, 2019.
- STUDENT RECOGNITION:
-
TEST OF TIME HONORABLE MENTION (Awarded in 2020, for paper authored in 2010):
Foundations of Software Engineering.
Ph.D. Student: Guodong Li.
Paper citation: Guodong Li and Ganesh Gopalakrishnan, Scalable SMT-based verification of GPU kernel functions. -
BEST STUDENT PAPER AWARDS: DRBSD Workshop and Supercomputing
(SC) 2020 (see in paper list)
- NVIDIA GRADUTE FELLOWSHIP 2020 , Ph.D. Student: Vinu Joseph. School of Computing News Item.
- Lawrence Livermore National Laboratory DIRECTOR'S 2020 EXCELLENCE IN PUBLICATION (Student Category Winner) Ph.D. Student: Michael Bentley. Paper citation: Michael Bentley, Ian Briggs, Ganesh Gopalakrishnan, Dong H. Ahn, Ignacio Laguna, Gregory L. Lee, Holger E. Jones, Multi-Level Analysis of Compiler-Induced Variability and Performance Tradeoffs.
-
TEST OF TIME HONORABLE MENTION (Awarded in 2020, for paper authored in 2010):
Foundations of Software Engineering.
Ph.D. Student: Guodong Li.
Funding Acknowledgements
Prof. Ganesh Gopalakrishnan's research is funded by the Department of Energy, Office of Science, Office of Advanced Scientific Computing Research under award number DE-SC0024042 under the XStack Project (DOE Office of Science). Their project 'ComPort : Rigorous Testing Methods to Safeguard Software Porting' investigates methods to port software reliably across upcoming hardware. Prof. Ganesh Gopalakrishnan's research is also funded by several NSF projects. Most of his papers and software involve multiple of these projects (given the small amounts of money per project). Each paper and software item is therefore collectively attributed to all these NSF projects.
Cover Design
