Professional Service
Associate Editor: Journal of Parallel and Distributed Computing (JPDC), since 2022.
Chair: ACM Undergraduate Student Research Competition (SRC) in Supercomputing (SC’22), 2022.
Guest Editor: Sustainable Computing: Informatics and Systems (SUSCOM Special Issue on RE-HPC), 2017.
Chair: First International Workshop on Resilience and/or Energy-aware techniques for High-Performance Computing (RE-HPC), 2016.
Program Committee: HiPC'24, APDCM'24, CCGrid'24, HiPC'23, ICPP'23, APDCM'23, IPDPS'23, HPCI'23, HiPC'22, APDCM'22, ALLDATA'22, IPDPS’22, ICPP’21, ISC’21, CCGrid’21, APDCM’21, E2DC’21, SC’21 (SRC), SBAC-PAD’20, ICPP’20, CCIW’20, E2DC’20, HiPC’19, CCIW’19, ICPP’19, ISORC’19, INFOCOMP’19, SC’18 (Poster), ICPP’18, E2DC’18, INFOCOMP’18, HiPC’17, ICA3PP’17, E2DC’17, HPC4BD’17, ICS’17, INFOCOMP’17, IPDPS’16, HPC4BD’16, SBAC-PAD’15.
Selected Talks
Dynamic Selective Protection of Sparse Iterative Solvers via ML Prediction of Soft Error Impacts. Fault Tolerance for HPC at eXtreme Scales (FTXS) Workshop, held in conjunction with SC'23, Denver, CO, USA, Nov. 2023. [slides]
Online Scheduling of Moldable Task Graphs under Common Speedup Models. 52nd International Conference on Parallel Processing (ICPP), Salt Lake City, UT, USA, Aug. 2023. [slides]
Resilient Scheduling of Moldable Parallel Jobs to Cope with Silent Errors. 13th Joint Laboratory for Extreme Scale Computing Workshop, Virtual, Dec. 2021. [slides]
Resilient Scheduling of Moldable Jobs on Failure-Prone Platforms. The 22nd IEEE International Conference on Cluster Computing, Virtual, Sept. 2020. [slides]
Selective Protection for Sparse Iterative Solvers to Reduce the Resilience Overhead. The 32nd IEEE International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD), Virtual, Sept. 2020. [slides]
Scheduling Stochastic Jobs on HPC Systems (and Beyond). The 9th Joint Laboratory for Extreme Scale Computing (JLESC) Workshop, Knoxville, TN, USA, Apr. 2019. [slides]
Multi-Resource Scheduling of Parallel Jobs. The 13th Scheduling for Large Scale Systems Workshop, Berkeley, CA, USA, June 2018. [slides]
Scheduling Parallel Tasks under Multiple Resources: List vs. Pack. The 32nd International Parallel and Distributed Processing Symposium (IPDPS), Vancouver, Canada, May 2018. [slides]
Identifying the Right Replication Level to Detect and Correct Silent Errors at Scale. The 7th Workshop on Fault Tolerance for HPC at eXtreme Scale (FTXS), Washington D.C., USA, June 2017. [slides]
When Amdahl Meets Young/Daly. The 18th IEEE International Conference on Cluster Computing, Taipei, Taiwan, September 2016. [slides]
Towards Optimal Multi-Level Checkpointing. The 5th Joint Laboratory for Extreme Scale Computing (JLESC) Workshop, Lyon, France, June 2016. [slides]
Mathematical Exercises on Daly and Extensions (with Aurélien Cavelan). The 3rd JLESC Summer School, Lyon, France, June 2016. [slides]
Resilience Algorithms to Cope with Fail-stop and Silent Errors. HPC Days in Lyon, Lyon, France, April 2016. [slides]
Resilient Algorithms for Coping with Silent Errors. Guest lecture for the Master 2 course “Resilient and energy-aware scheduling algorithms” at ENS Lyon, Lyon, France, October 2015. [slides]
Assessing the Impact of Partial Verifications Against Silent Data Corruptions. The 44th International Conference on Parallel Processing (ICPP’15), Beijing, China, September 2015. [slides]
Which Verification for Soft Error Detection? The 3rd Joint Laboratory for Extreme Scale Computing (JLESC) Workshop, Barcelona, Spain, July 2015. [slides]
Energy-Efficient and Thermal-Aware Resource Management for Heterogeneous Datacenters. The 9th Scheduling for Large Scale Systems Workshop, Lyon, France, July 2014. [slides]
Competitive Online Adaptive Scheduling for Sets of Parallel Jobs with Fairness and Efficiency. Talk given at ENS de Lyon, France, February 2014. [slides]
Improved Semi-Online Makespan Scheduling with a Reordering Buffer. The 11th Workshop on Models and Algorithms for Planning and Scheduling Problems (MAPSP'13), Pont à Mousson, France, June 2013. [slides]
Speed Scaling for Energy and Performance with Instantaneous Parallelism. The 1st International ICST Conference on Theory and Practice of Algorithms in (Computer) System (TAPAS'11), Rome, Italy, April 2011. [slides]