Nikhil Jain
PhD Students
nikhil.jain at acm.org
Profile
Research Homepage
Curriculum Vitae- PDF
Google Scholar
Nikhil Jain was a doctoral candidate with Prof. Laxmikant Kale in the Department of Computer Science at UIUC. While at PPL, Nikhil worked on understanding HPC network behavior for scalable application execution, interoperability of Charm and other paradigms such as MPI and OpenMP, topology aware mapping, load balancing, further development of Charm++ RTS and optimization of Adaptive MPI . He also worked on developing collective algorithms for different network topologies and is interested in exploring machine learning algorithms. After graduating in Spring 2016, Nikhil joined Lawrence Livermore National Laboratory as a Fernbach Postdoctoral Fellow.
Curriculum Vitae- PDF
Google Scholar
Nikhil Jain was a doctoral candidate with Prof. Laxmikant Kale in the Department of Computer Science at UIUC. While at PPL, Nikhil worked on understanding HPC network behavior for scalable application execution, interoperability of Charm and other paradigms such as MPI and OpenMP, topology aware mapping, load balancing, further development of Charm++ RTS and optimization of Adaptive MPI . He also worked on developing collective algorithms for different network topologies and is interested in exploring machine learning algorithms. After graduating in Spring 2016, Nikhil joined Lawrence Livermore National Laboratory as a Fernbach Postdoctoral Fellow.
Research Areas
- AMPI - Adaptive Message Passing Interface
- Topology Aware Mapping
- BlueWaters - Sustained Petascale Computing
- Dynamic Load Balancing
- Runtime Systems and Interoperability
- Interoperability
- OpenAtom - Ab Initio Molecular Dynamics
- BigNetSim - Parallel InterConnection Network Simulation
- BigSim - Simulating PetaFLOPS Supercomputers
- Parallel Discrete Event Simulation
- EpiSimdemics
Papers
17-03
2017
[Paper]
[Paper]
Massively Parallel Simulations of Spread of Infectious Diseases over Realistic Social Networks [CCGrid 2017]
17-02
2017
[Paper]
[Paper]
Automatic topology mapping of diverse large-scale parallel applications [ICS 2017]
16-11
2016
[Paper]
[Paper]
Evaluating HPC Networks via Simulation of Parallel Workloads [SC 2016]
16-05
2016
[Paper]
[Paper]
OpenAtom: Scalable Ab-Initio Molecular Dynamics with Diverse Capability [ISC 2016]
16-04
2016
[Paper]
[Paper]
Analyzing network health and congestion in dragonfly-based systems [IPDPS 2016]
16-02
2016
[PhD Thesis]
[PhD Thesis]
Optimization of Communication Intensive Applications on HPC Networks [Thesis 2016]
16-01
2016
[Paper]
[Paper]
Towards PDES in a Message-Driven Paradigm: A Preliminary Case Study Using Charm++ [ACM SIGSIM PADS 2016]
15-15
2015
[Paper]
[Paper]
Evaluating System Parameters on a Dragonfly using Simulation and Visualization [CS Res. & Tech. Report 2015]
15-14
2015
[Paper]
[Paper]
Preliminary Evaluation of a Parallel Trace Replay Tool for HPC Network Simulations [PADABS, EURO-PAR 2015]
15-03
2015
[Paper]
[Paper]
Identifying the Culprits behind Network Congestion [IPDPS 2015]
15-02
2015
[Paper]
[Paper]
Charm++ & MPI: Combining the Best of Both Worlds [IPDPS 2015]
14-28
2014
[Paper]
[Paper]
On Interoperation among User-driven and System-driven Parallel Languages [CS Res. & Tech. Report 2014]
14-27
2014
[Paper]
[Paper]
Power Management of Extreme-scale Networks with On/Off Links in Runtime Systems [TOPC 2014]
14-17
2014
[Paper]
[Paper]
Mapping to Irregular Torus Topologies and Other Techniques for Petascale Biomolecular Simulation [SC 2014]
14-14
2014
[Paper]
[Paper]
Optimizing the performance of parallel applications on a 5D torus via task mapping [HiPC 2014]
14-07
2014
[Paper]
[Paper]
Parallel Programming with Migratable Objects: Charm++ in Practice [SC 2014]
14-04
2014
[Paper]
[Paper]
Maximizing Throughput on a Dragonfly Network [SC 2014]
13-60
2013
[Paper]
[Paper]
Position Paper: Actionable Performance Modeling for Future Supercomputers [MODSIM 2013]
13-24
2013
[Paper]
[Paper]
ACR: Automatic Checkpoint/Restart for Soft and Hard Error Protection [SC 2013]
13-22
2013
[Paper]
[Paper]
Position Paper: A Multi-resolution Emulation + Simulation Methodology [MODSIM 2013]
13-18
2013
[Paper]
[Paper]
Predicting Application Performance using Supervised Learning on Communication Features [SC 2013]
13-09
2013
[Paper]
[Paper]
Toward Runtime Power Management of Exascale Networks by On/Off Control of Links [HPPAC 2013]
12-47
2012
[Paper]
[Paper]
Migratable Objects + Active Messages + Adaptive Runtime = Productivity + Performance: A Submission to the 2012 HPC Class II Challenge [SC 2012]
12-29
2012
[Paper]
[Paper]
Automated Load Balancing Invocation based on Application Characteristics [Cluster 2012]
12-21
2012
[Paper]
[Paper]
Collectives on Two-tier Direct Networks [EuroMPI 2012]
12-08
2012
[Paper]
[Paper]
Collective Algorithms for Sub-communicators [ICS 2012]
11-49
2011
[Paper]
[Paper]
Charm++ for Productivity and Performance: A Submission to the 2011 HPC Class II Challenge [SC 2011]
11-40
2011
[Paper]
[Paper]
Real Time Contingency Analysis for Power Grids [Euro-Par 2011]
11-37
2011
[Paper]
[Paper]
Simulation-based Performance Analysis and Tuning for a Two-level Directly Connected System [ICPADS 2011]
11-21
2011
[Paper]
[Paper]
Avoiding Hot-Spots on Two-Level Direct Networks [SC 2011]
10-43
2010
[Paper]
[Paper]
Optimizing Matrix Transpose on Torus Interconnects [Euro-Par 2010]
10-42
2010
[Paper]
[Paper]
Optimal Bucket Algorithms for Large MPI Collectives on Torus Interconnects [ICS 2010]
09-31
2009
[Paper]
[Paper]
SMP Based Solver for Large Binary Systems [PDAA 2009]
Talks/Posters
16-21
2016
[Poster]
[Poster]
ACM SRC: Mapping Applications on Irregular Allocations [SC 2016]
15-17
2015
[Talk]
[Talk]
Charm++ & MPI: Combining the Best of Both Worlds [IPDPS 2015]
14-40
2014
[Talk]
[Talk]
Maximizing Throughput on a Dragonfly Network [SC 2014]
13-54
2013
[Talk]
[Talk]
ERS: Techniques for Improving Observed Network Performance [SC 2013]
13-53
2013
[Poster]
[Poster]
Fast Prediction of Network Performance: k-packet Simulation [SC 2013]
13-48
2013
[Talk]
[Talk]
Predicting Application Performance using Supervised Learning on Communication Features [SC 2013]
13-28
2012
[Poster]
[Poster]
Understanding Network Contention on Blue Gene Supercomputers [LLNL Poster Symposium 2012]
13-23
2013
[Talk]
[Talk]
Tutorial: Programming with Parallel Migratable Objects [ATPESC 2013]
13-15
2012
[Talk]
[Talk]
Collectives on Two-tier Direct Networks [EuroMPI 2012]
13-14
2013
[Talk]
[Talk]
Charm++ Interoperability [Charm++ Workshop 2013]
13-13
2013
[Talk]
[Talk]
Predicting Application Performance using Supervised Learning on Communication Features [Lawrence Livermore Talk 2013]
13-03
2013
[Poster]
[Poster]
Charm++: Migratable Objects + Active Messages + Adaptive Runtime = Productivity + Performance [PSAAP Site-visit 2013]
12-53
2012
[Talk]
[Talk]
Automated Load Balancing Invocation based on Application Characteristics [Cluster 2012]
11-52
2012
[Poster]
[Poster]
Collective Algorithms for Sub-communicators [PPoPP 2012]
