Live Webcast 15th Annual Charm++ Workshop

-->

PPL/Charm++ at SC17

Harshitha Menon
PhD Students
gplkrsh2 at illinois.edu
Profile
Please visit my research website for more information.

Harshitha is a doctoral candidate in the Department of Computer Science at the University of Illinois, Urbana-Champaign, advised by Prof. Laxmikant V. Kale. Her research focuses on developing scalable load balancing algorithms and adaptive run time techniques to improve the performance of large scale dynamic applications. The proposed algorithms and run time techniques have been evaluated on scales of more than 100K cores on HPC systems such as BG/Q, Cray XE6, BG/P.
Harshitha's research also includes conducting scaling studies and performance optimizations for cosmology simulation application called ChaNGa, which is a collaborative research project with astrophysicists at University of Washington. ChaNGa is used by many astrophysicists to study the impact of dwarf galaxies on the milky way, modeling gas properties in merging clusters of galaxy and studying the role of dark matter in dwarf galaxy formation. Recently, they have achieved scaling results up to 512K cores on Blue Waters which is a Cray XE6 machine at NCSA.

Harshitha was awarded George Michael High Performance Computing award for research excellence and academic progress in 2014. She is also a recipient of Google Anita Borg scholarship, Siebel Scholarship, Feng Chen Award and Google fellowship for employees.

Resume PDF
Research Areas
Papers
17-08
2017
[Paper]
Integrating OpenMP into the Charm++ Programming Model [ESPM2 2017]
16-19
2016
[Paper]
Handling Transient and Persistent Imbalance Together in Distributed and Shared Memory [PPL Technical Report 2016]
16-18
2016
[PhD Thesis]
Adaptive Load Balancing for HPC Applications [Thesis 2016]
16-12
2016
[Paper]
Power, Reliability, Performance: One System to Rule Them All [Computer 2016]
14-41
2014
[Paper]
Applying Graph Partitioning Methods in Measurement-based Dynamic Load Balancing [CS Res. & Tech. Report 2014]
| Harshitha Menon | Abhinav Bhatele | Sébastien Fourestier | Laxmikant Kale | François Pellegrini
14-30
2015
[Paper]
Adaptive Techniques for Clustered N-Body Cosmological Simulations [Computational Astrophysics and Cosmology 2015]
| Harshitha Menon | Lukasz Wesolowski | Gengbin Zheng | Pritish Jetley | Laxmikant Kale | Thomas Quinn | Fabio Governato
14-21
2014
[Paper]
Scalable Replay with Partial-Order Dependencies for Message-Logging Fault Tolerance [Cluster 2014]
14-07
2014
[Paper]
Parallel Programming with Migratable Objects: Charm++ in Practice [SC 2014]
13-33
2013
[Paper]
Thermal Aware Automated Load Balancing for HPC Applications [Cluster 2013]
| Harshitha Menon | Bilge Acun | Simon Garcia De Gonzalo | Osman Sarood | Laxmikant Kale
13-26
2013
[Paper]
A Distributed Dynamic Load Balancer for Iterative Applications [SC 2013]
12-47
2012
[Paper]
Migratable Objects + Active Messages + Adaptive Runtime = Productivity + Performance: A Submission to the 2012 HPC Class II Challenge [SC 2012]
12-41
2012
[MS Thesis]
Meta-Balancer: Automated Load Balancing Based On Application Behavior [Thesis 2012]
12-29
2012
[Paper]
Automated Load Balancing Invocation based on Application Characteristics [Cluster 2012]
Talks/Posters
17-01
2017
[Poster]
Poster: Automated Load Balancer Selection Based on Application Characteristics [PPoPP 2017]
14-31
2014
[Talk]
Scalable Replay with Partial-Order Dependencies for Message-Logging Fault Tolerance [Cluster 2014]
13-47
2013
[Talk]
A Distributed Dynamic Load Balancer for Iterative Applications [SC 2013]
13-27
2013
[Poster]
Chizu: A Framework to Enable Topology Aware Task Mapping [LLNL Poster Symposium 2013]
13-03
2013
[Poster]
Charm++: Migratable Objects + Active Messages + Adaptive Runtime = Productivity + Performance [PSAAP Site-visit 2013]
13-02
2013
[Poster]
Scalable Algorithms for Distributed-Memory Adaptive Mesh Refinement [PSAAP Site-visit 2013]
12-53
2012
[Talk]
Automated Load Balancing Invocation based on Application Characteristics [Cluster 2012]