Orçun Yildiz

PhD student at INRIA Rennes

PhD subject: Efficient Big Data processing on large-scale shared platforms

Supervised by: Shadi Ibrahim and Gabriel Antoniu

Contact details

Inria Rennes Bretagne – Atlantique Campus Universitaire de Beaulieu, 35042, Rennes

Office: D166 Phone: + 33 2 99 84 22 78   E-mail: orcun.yildiz@inria.fr

Short bio

Orcun YILDIZ received his BSc degree in computer science from Bogazici University, Turkey. He graduated with a double master degree in Distributed Computing (EMDC) from Royal Institute of Technology (KTH), Sweden and Instituto Superior Técnico (IST), Portugal. He is currently a PhD student in INRIA, Rennes-Bretagne Atlantique Research Centre. His research interests include distributed systems, high performance computing and big data management.

Software

Ifer: MicroBenchmark for Studying the Cross-Application I/O Interference

Publications

Publications HAL de Orcun,Yildiz

Journal articles

titre
Improving the Effectiveness of Burst Buffers for Big Data Processing in HPC Systems with Eley
auteur
Orcun Yildiz, Amelie Chi Zhou, Shadi Ibrahim
article
Future Generation Computer Systems, 2018, 86, pp.308-318. ⟨10.1016/j.future.2018.03.029⟩
DOI
DOI : 10.1016/j.future.2018.03.029
Accès au bibtex
BibTex
titre
Damaris: Addressing Performance Variability in Data Management for Post-Petascale Simulations
auteur
Matthieu Dorier, Gabriel Antoniu, Franck Cappello, Marc Snir, Robert Sisneros, Orcun Yildiz, Shadi Ibrahim, Tom Peterka, Leigh Orf
article
ACM Transactions on Parallel Computing, 2016, 3 (3), pp.15. ⟨10.1145/2987371⟩
DOI
DOI : 10.1145/2987371
Accès au texte intégral et bibtex
https://inria.hal.science/hal-01353890/file/Damaris%20-%20ACM%20Transactions%20on%20Parallel%20Computing.pdf BibTex
titre
Enabling Fast Failure Recovery in Shared Hadoop Clusters: Towards Failure-Aware Scheduling
auteur
Orcun Yildiz, Shadi Ibrahim, Gabriel Antoniu
article
Future Generation Computer Systems, 2016, ⟨10.1016/j.future.2016.02.015⟩
DOI
DOI : 10.1016/j.future.2016.02.015
Accès au texte intégral et bibtex
https://inria.hal.science/hal-01338336/file/FGCS-Chronos.pdf BibTex
titre
On the energy footprint of I/O management in Exascale HPC systems
auteur
Matthieu Dorier, Orcun Yildiz, Shadi Ibrahim, Anne-Cécile Orgerie, Gabriel Antoniu
article
Future Generation Computer Systems, 2016, 62, pp.17-28. ⟨10.1016/j.future.2016.03.002⟩
DOI
DOI : 10.1016/j.future.2016.03.002
Accès au texte intégral et bibtex
https://inria.hal.science/hal-01330735/file/Energy-Damaris.pdf BibTex

Conference papers

titre
LowFive: In Situ Data Transport for High-Performance Workflows
auteur
Tom Peterka, Dmitriy Morozov, Arnur Nigmetov, Orcun Yildiz, Bogdan Nicolae, Philip E. Davis
article
IPDPS’23: The 37th IEEE International Parallel and Distributed Processing Symposium, ACM; IEEE, May 2023, St.Petersburg, United States
Accès au texte intégral et bibtex
https://hal.science/hal-04119925/file/lowfive-ipdps23.pdf BibTex
titre
Towards Low-Overhead Resilience for Data Parallel Deep Learning
auteur
Bogdan Nicolae, Tanner Hobson, Orcun Yildiz, Tom Peterka, Dmitry Morozov
article
CCGrid’22: The 22nd IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing, May 2022, Messina, Italy
Accès au texte intégral et bibtex
https://hal.science/hal-03631882/file/Towards%20Low-Overhead%20Resilience%20for%20Data%20Parallel%20Deep%20Learning.pdf BibTex
titre
Shared-Memory Communication for Containerized Workflows
auteur
Tanner Hobson, Orcun Yildiz, Bogdan Nicolae, Jian Huang, Tom Peterka
article
CCGrid’21: The 21th IEEE/ACM International Symposium on Cluster, Cloud and Internet Computing, May 2021, Melbourne, Australia
Accès au texte intégral et bibtex
https://hal.science/hal-03200931/file/Shared-Memory_Communication_for_Containerized_Workflows.pdf BibTex
titre
On the Performance of Spark on HPC Systems: Towards a Complete Picture
auteur
Orcun Yildiz, Shadi Ibrahim
article
SCA 2018 – SupercomputingAsia, Mar 2018, Singapore, Singapore. pp.70-89, ⟨10.1007/978-3-319-69953-0_5⟩
DOI
DOI : 10.1007/978-3-319-69953-0_5
Accès au texte intégral et bibtex
https://hal.science/hal-01742016/file/Yildiz-Ibrahim2018_Chapter_OnThePerformanceOfSparkOnHPCSy.pdf BibTex
titre
Eley: On the Effectiveness of Burst Buffers for Big Data Processing in HPC systems
auteur
Orcun Yildiz, Amelie Chi Zhou, Shadi Ibrahim
article
Cluster’17-2017 IEEE International Conference on Cluster Computing, Sep 2017, Honolulu, United States. ⟨10.1109/CLUSTER.2017.73⟩
DOI
DOI : 10.1109/CLUSTER.2017.73
Accès au texte intégral et bibtex
https://inria.hal.science/hal-01570737/file/Cluster2017-CR.pdf BibTex
titre
On the Root Causes of Cross-Application I/O Interference in HPC Storage Systems
auteur
Orcun Yildiz, Matthieu Dorier, Shadi Ibrahim, Robert Ross, Gabriel Antoniu
article
IPDPS 2016 – The 30th IEEE International Parallel and Distributed Processing Symposium, May 2016, Chicago, United States. ⟨10.1109/ipdps.2016.50⟩
DOI
DOI : 10.1109/ipdps.2016.50
Accès au texte intégral et bibtex
https://inria.hal.science/hal-01270630/file/IPDPS%2716-CR.pdf BibTex
titre
Chronos: Failure-Aware Scheduling in Shared Hadoop Clusters
auteur
Orcun Yildiz, Shadi Ibrahim, Tran Anh Phuong, Gabriel Antoniu
article
BigData’15-The 2015 IEEE International Conference on Big Data, Oct 2015, Santa Clara, CA, United States
Accès au texte intégral et bibtex
https://inria.hal.science/hal-01203001/file/IEEEBigData2015.pdf BibTex
titre
A Performance and Energy Analysis of I/O Management Approaches for Exascale Systems
auteur
Orcun Yildiz, Matthieu Dorier, Shadi Ibrahim, Gabriel Antoniu
article
DIDC ’14 Proceedings of the sixth international workshop on Data Intensive Distributed Computing, Jun 2014, Vancouver, Canada. pp.35-40, ⟨10.1145/2608020.2608026⟩
DOI
DOI : 10.1145/2608020.2608026
Accès au texte intégral et bibtex
https://inria.hal.science/hal-01076522/file/paper.pdf BibTex

Reports

titre
Preserving Fairness in Shared Hadoop Cluster: A Study on the Impact of (Non-) Preemptive Approaches
auteur
Orcun Yildiz, Shadi Ibrahim
article
[Research Report] RR-9384, Inria Rennes – Bretagne Atlantique. 2020
Accès au texte intégral et bibtex
https://inria.hal.science/hal-03091371/file/RR-9384.pdf BibTex

Theses

titre
Efficient Big Data Processing on Large-Scale Shared Platforms: managing I/Os and Failure
auteur
Orcun Yildiz
article
Performance [cs.PF]. École normale supérieure de Rennes, 2017. English. ⟨NNT : 2017ENSR0009⟩
Accès au texte intégral et bibtex
https://theses.hal.science/tel-01723850/file/THESE_YILDIZ_Orcun.pdf BibTex

Comments are closed.