Invited Talks and Seminars
General HPC Runtime Systems
-
Challenges and Opportunities in Co-Design for High-Performance Computing Software Systems.
Invited talk at UMN Cloud Data Center and Edge (CDCE) workshop, February 2021.
-
Co-Design for High-Performance Computing Software Systems.
Invited talk at the REBASE track of the SPLASH 2020 virtual conference, November 2020.
[SLIDES]
-
AI@Edge: Software System Implications.
Invited talk of Microelectronics Workshop at Argonne National Laboratory, October 2019.
OpenSHMEM
-
OpenSHMEM over MPI: A Performance Contender.
Invited talk at OpenSHMEM Unofficial Birds of a Feather at SC20, November 2020.
[SLIDES]
-
OpenSHMEM over MPI: Capabilities and Challenges.
Invited talk at State of the Union Birds of a Feather at SC19, November 2019.
[SLIDES]
-
Performance Analysis of MPI RMA in Supporting OpenSHMEM Runtime.
Invited talk at OpenSHMEM in the Era of Exascale Birds of a Feather at SC18, November 2018.
-
OpenSHMEM over Portable MPI RMA with Asynchronous Progress Support.
Invited talk at OpenSHMEM in the Era of Exascale Birds of a Feather at SC17, November 2017.
Beehive and MPI
-
Beehive: A Dynamic Execution Environment for Performance, Power, and Resilience on Extreme-Scale Computing Systems.
Invited talk of Argonne Named Fellows Mid-Year MiniSymposium at Argonne National Laboratory, June 2020.
-
Towards Dynamic Communication Runtime for Scalable Irregular Parallel Computing.
Invited talk at Florida State University, December 2018.
-
Designing Dynamic Communication Infrastructure for Scalable Irregular Parallel Computing.
LDRD seminar at Argonne National Laboratory, May 2018.
-
Casper: Portable and Adaptable Asynchronous Progress Model for MPI Communication.
Invited talk at PCCluster Booth at SC17, November 2017.
-
Towards Portable and Adaptable Asynchronous Communication for One-Sided Applications.
Invited talk at Tenth International Workshop on Parallel Programming Models and Systems Software for High-End Computing (P2S2 2017), August 2017.
-
Data Locality Challenges in Irregular Applications for Exascale Programing.
Invited talk at Fourth Workshop on Programming Abstractions for Data Locality (PADAL 2017), August 2017.
-
Scaling NWChem with Efficient and Portable Asynchronous Communication on NERSC Edison Supercomputer.
Invited talk at National Energy Research Scientific Computing Center, 2016-03.
[SLIDES]
-
Techniques for Enabling Highly Efficient Message Passing on Many-Core Architectures.
Seminar at Argonne National Laboratory, 2015-10.
[SLIDES]
-
Casper: An Asynchronous Progress Model for MPI RMA on Many-core Architectures.
Seminar at Argonne National Laboratory, 2015-04.
-
MT-MPI: Multi-threaded MPI for Many-core Environments.
Seminar at Argonne National Laboratory, 2013-09.