
Lionel Eyraud-Dubois
87
Documents
Publications
Publications
|
A 1.25(1+ε)-Approximation Algorithm for Scheduling with Rejection Costs Proportional to Processing TimesInternational European Conference on Parallel and Distributed Computing (Euro-Par), Aug 2024, Madrid, Spain. pp.225-238, ⟨10.1007/978-3-031-69577-3_16⟩
Communication dans un congrès
hal-04670834
v1
|
|
Tightening I/O Lower Bounds through the Hourglass Dependency PatternSPAA 2024 - 36th ACM Symposium on Parallelism in Algorithms and Architectures, Jun 2024, Nantes, France. pp.1-34
Communication dans un congrès
hal-04555744
v1
|
|
Exploiting Processor Heterogeneity to Improve Throughput and Reduce Latency for Deep Neural Network InferenceSBAC-PAD 2024 - IEEE 36th International Symposium on Computer Architecture and High Performance Computing, Nov 2024, Hilo, Hawaii, United States
Communication dans un congrès
hal-04690154
v1
|
StarONNX : Un ordonanceur dynamique pour une inférence rapide et à haut débit sur des ressources hétérogènesCompas 2024 - Conférence francophone d'informatique en Parallélisme, Architecture et Système, Jul 2024, Nantes, France
Communication dans un congrès
hal-04668550
v1
|
|
|
StarONNX: a Dynamic Scheduler for Low Latency and High Throughput Inference on Heterogeneous ResourcesHeteroPar 2024 - 22ND INTERNATIONAL WORKSHOP Algorithms, Models and Tools for Parallel Computing on Heterogeneous Platforms, EuroPar'24, Aug 2024, Madrid, Spain
Communication dans un congrès
hal-04646530
v1
|
|
Rockmate: an Efficient, Fast, Automatic and Generic Tool for Re-materialization in PyTorchICML 2023 - 40 th International Conference on Machine Learning, Jul 2023, Honolulu (HI), United States
Communication dans un congrès
hal-04095305
v5
|
|
Data Distribution Schemes for Dense Linear Algebra Factorizations on Any Number of NodesIPDPS 2023 - 37th IEEE International Parallel & Distributed Processing Symposium, IEEE, May 2023, St. Petersburg, Florida, United States
Communication dans un congrès
hal-04013708
v1
|
|
On the Arithmetic Intensity of Distributed-Memory Dense Matrix Multiplication Involving a Symmetric Input Matrix (SYMM)IPDPS 2023 - 37th International Parallel and Distributed Processing Symposium, IEEE, May 2023, St. Petersburg, FL, United States. pp.357-367
Communication dans un congrès
hal-04093162
v1
|
|
Survey on Large Scale Neural Network TrainingIJCAI-ECAI 2022 - 31st International Joint Conference on Artificial Intelligence, Jul 2022, Vienna, Austria. pp.5494-5501, ⟨10.24963/ijcai.2022/769⟩
Communication dans un congrès
hal-03952171
v1
|
|
MadPipe: Memory Aware Dynamic Programming Algorithm for Pipelined Model ParallelismScaDL 2022 - Scalable Deep Learning over Parallel and Distributed Infrastructure - An IPDPS 2022 Workshop, Jun 2022, Lyon / Virtual, France
Communication dans un congrès
hal-03025305
v1
|
|
Symmetric Block-Cyclic Distribution: Fewer Communications Leads to Faster Dense Cholesky FactorizationSC 2022 - Supercomputing, Nov 2022, Dallas, Texas, United States
Communication dans un congrès
hal-03768910
v1
|
|
I/O-Optimal Algorithms for Symmetric Linear Algebra KernelsACM Symposium on Parallelism in Algorithms and Architectures, Association for Computing Machinery : SIGACT, SIGARCH, Jul 2022, Philadelphie, United States
Communication dans un congrès
hal-03580531
v1
|
|
Pipelined Model Parallelism: Complexity Results and Memory ConsiderationsEuropar 2021, Aug 2021, Lisbon, Portugal
Communication dans un congrès
hal-02968802
v3
|
|
Efficient Combination of Rematerialization and Offloading for Training DNNsNeurIPS 2021 - Thirty-fifth Conference on Neural Information Processing Systems, Dec 2021, Virtual-only Conference, France
Communication dans un congrès
hal-03359793
v1
|
|
TEXTAROSSA: Towards EXtreme scale Technologies and Accelerators for euROhpc hw/Sw Supercomputing Applications for exascaleDSD 2021 - 24th Euromicro Conference on Digital System Design, Sep 2021, Palermo / Virtual, Italy
Communication dans un congrès
hal-03329640
v1
|
|
Analysis of a List Scheduling Algorithm for Task Graphs on Two Types of ResourcesIPDPS 2020 - 34th IEEE International Parallel and Distributed Procesing Symposium, May 2020, New Orleans / Virtual, United States
Communication dans un congrès
hal-02431810
v1
|
|
Algorithms for Preemptive Co-scheduling of Kernels on GPUsHiPC 2020 : 27th IEEE International Conference on High Performance Computing, Data, and Analytics, Dec 2020, Pune / Virtual, India
Communication dans un congrès
hal-03148711
v1
|
|
2D Static Resource Allocation for Compressed Linear Algebra and Communication ConstraintsHIPC 2020: 27th IEEE International Conference on High Performance Computing, Data, and Analytics, Dec 2020, (virtual), India
Communication dans un congrès
hal-02900244
v2
|
|
Optimal GPU-CPU Offloading Strategies for Deep Neural Network TrainingEuro-Par 2020 - 26th International Conference on Parallel and Distributed Computing, Aug 2020, Warsaw / Virtual, Poland. pp.151-166, ⟨10.1007/978-3-030-57675-2_10⟩
Communication dans un congrès
hal-02316266
v3
|
|
Performance Models for Data Transfers: A Case Study with Molecular Chemistry KernelsICPP 2019 - 48th International Conference on Parallel Processing, Aug 2019, Kyoto, Japan. ⟨10.1145/3337821.3337921⟩
Communication dans un congrès
hal-02431877
v1
|
|
Sizing and Partitioning Strategies for Burst-Buffers to Reduce IO ContentionIPDPS 2019 - 33rd IEEE International Parallel and Distributed Processing Symposium, May 2019, Rio de Janeiro, Brazil
Communication dans un congrès
hal-02141616
v2
|
|
What Size Should your Buffers to Disks be?International Parallel and Distributed Processing Symposium (IPDPS), May 2018, Vancouver, Canada. ⟨10.1109/IPDPS.2018.00075⟩
Communication dans un congrès
hal-01623846
v2
|
|
Using Static Allocation Algorithms for Matrix Matrix Multiplication on Multicores and GPUsICPP 2018 - 47th International Conference on Parallel Processing, Aug 2018, Eugene, OR, United States. ⟨10.1145/3225058.3225066⟩
Communication dans un congrès
hal-01670678
v2
|
|
Approximation Proofs of a Fast and Efficient List Scheduling Algorithm for Task-Based Runtime Systems on Multicores and GPUsIEEE International Parallel & Distributed Processing Symposium (IPDPS), May 2017, Orlando, United States. ⟨10.1109/IPDPS.2017.71⟩
Communication dans un congrès
hal-01386174
v2
|
|
A New Approximation Algorithm for Matrix Partitioning in Presence of Strongly Heterogeneous Processors30th IEEE International Parallel & Distributed Processing Symposium , May 2016, Chicago, France
Communication dans un congrès
hal-01216245
v1
|
|
Are Static Schedules so Bad ? A Case Study on Cholesky FactorizationIEEE International Parallel & Distributed Processing Symposium (IPDPS 2016), May 2016, Chicago, IL, United States
Communication dans un congrès
hal-01223573
v2
|
|
Scheduling of Linear Algebra Kernels on Multiple Heterogeneous ResourcesInternational Conference on High Performance Computing, Data, and Analytics (HiPC 2016), Dec 2016, Hyderabad, India. ⟨10.1109/HiPC.2016.045⟩
Communication dans un congrès
hal-01361992
v2
|
|
Cuboid Partitioning for Parallel Matrix Multiplication on Heterogeneous Platforms22nd International Conference on Parallel and Distributed Computing, Aug 2016, Grenoble, France. ⟨10.1007/978-3-319-43659-3_13⟩
Communication dans un congrès
hal-01269881
v2
|
|
Column generation integer programming for allocating jobs with periodic demand variationsInternational Workshop on Algorithmic Aspects of Cloud Computing, Sep 2015, Patras, Greece
Communication dans un congrès
hal-01252770
v1
|
|
Bridging the Gap between Performance and Bounds of Cholesky Factorization on Heterogeneous PlatformsHeterogeneity in Computing Workshop 2015, May 2015, Hyderabad, India. ⟨10.1109/IPDPSW.2015.35⟩
Communication dans un congrès
hal-01120507
v1
|
|
Allocating jobs with periodic demand variationsEuro-Par 2015, Träff, Jesper Larsson, Hunold, Sascha, Versaci, Francesco, 2015, Vienna, Austria. ⟨10.1007/978-3-662-48096-0_12⟩
Communication dans un congrès
hal-01118176
v1
|
|
Comparison of Static and Dynamic Resource Allocation Strategies for Matrix Multiplication26th IEEE International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD), 2015, Oct 2015, Florianopolis, Brazil
Communication dans un congrès
hal-01163936
v2
|
|
Efficient and Robust Allocation Algorithms in Clouds under Memory ConstraintsIEEE International Conference on High Performance Computing (HiPC 2014), Dec 2014, Goa, India. pp.12
Communication dans un congrès
hal-00874936
v2
|
|
Analyzing Real Cluster Data for Formulating Allocation Algorithms in Cloud PlatformsProceedings of the IEEE 26th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD), Oct 2014, Paris, France. pp.302 - 309, ⟨10.1109/SBAC-PAD.2014.44⟩
Communication dans un congrès
hal-01094388
v1
|
|
Optimizing Resource allocation while handling SLA violations in Cloud Computing platformsIPDPS - 27th IEEE International Parallel & Distributed Processing Symposium, May 2013, Boston, United States. ⟨10.1109/IPDPS.2013.67⟩
Communication dans un congrès
hal-00772846
v1
|
|
Reliable Service Allocation in CloudsIPDPS - 27th IEEE International Parallel & Distributed Processing Symposium, May 2013, Boston, United States. ⟨10.1109/IPDPS.2013.64⟩
Communication dans un congrès
hal-00743524
v2
|
A Server Consolidation Problem: Definition and ModelProceedings of the 14th conference ROADEF, 2013, Troyes, France
Communication dans un congrès
hal-00921363
v1
|
|
|
Reliable Service Allocation in Clouds with Memory and Capacity ConstraintsResilience 2013, in conjunction with EuroPar 2013, Sep 2013, Aachen, Germany
Communication dans un congrès
hal-00850125
v1
|
|
Minimizing Weighted Mean Completion Time for Malleable Tasks SchedulingIPDPS 2012, 26th IEEE International Parallel & Distributed Processing Symposium, May 2012, Shangai, China
Communication dans un congrès
inria-00564056
v2
|
|
Bedibe: Datasets and Software Tools for Distributed Bandwidth PredictionAlgoTel'2012 - Rencontres Francophones sur les Aspects Algorithmiques des Télécommunications, May 2012, La Grande Motte, France
Communication dans un congrès
hal-00690861
v1
|
|
Broadcasting on Large Scale Heterogeneous Platforms with connectivity artifacts under the Bounded Multi-Port ModelICPADS 2011 - 17th Internation Conference on Parallel and Distributed Systems, IEEE, Dec 2011, Taïnan, Taiwan. pp.173-180
Communication dans un congrès
inria-00618784
v1
|
|
Using the Last-mile Model as a Distributed Scheme for Available Bandwidth PredictionEuroPar 2011, Sep 2011, Bordeaux, France
Communication dans un congrès
inria-00588651
v1
|
|
Broadcasting on Large Scale Heterogeneous Platforms under the Bounded Multi-Port Model24th IEEE International Parallel and Distributed Processing Symposium (IPDPS 2010), Apr 2010, Atlanta, United States
Communication dans un congrès
inria-00444586
v1
|
On-line Allocation of Clients to Multiple Servers on Large Scale Heterogeneous SystemsPDP 2010 - The 18th Euromicro International Conference on Parallel, Distributed and Network-Based Computing, Feb 2010, Pisa, Italy
Communication dans un congrès
inria-00444584
v1
|
|
Online and offline Independent Tasks Allocation Schemes on Large Scale Master-Worker Heterogeneous Platforms.1st Workshop on New Challenges in Distributed Systems, Apr 2009, Valparaiso, Chile
Communication dans un congrès
inria-00413434
v1
|
|
Allocation of Clients to Multiple Servers on Large Scale Heterogeneous PlatformsThe Fifteenth International Conference on Parallel and Distributed Systems (ICPADS'09), Dec 2009, Shenzhen, China
Communication dans un congrès
inria-00413437
v1
|
|
|
Online Allocation of Splitable Clients to Multiple Servers on Large Scale Heterogeneous PlatformsAlgoTel, 2009, Carry-Le-Rouet, France
Communication dans un congrès
inria-00384569
v1
|
Scheduling divisibleworkloads on heterogeneous platforms under bounded multi-port modelHeterogeneity in Computing Workshop, in IEEE International Symposium on Parallel and Distributed Processing, 2008. IPDPS 2008., Apr 2008, Miami, FL, United States
Communication dans un congrès
inria-00336189
v1
|
|
Distributed Approximation Algorithm for Resource ClusteringOpodis 2008, 2008, Luxor, Egypt. pp.564--567, ⟨10.1007/978-3-540-92221-6_41⟩
Communication dans un congrès
istex
hal-00396449
v1
|
|
|
Assessing the Quality of Automatically Built Network RepresentationsWorkshop on Programming Models for Grid Computing - organized at IEEE/ACM International Symposium on Cluster Computing and the Grid - CCGrid 2007, May 2007, Rio de Janeiro, Brazil. pp.795 - 800, ⟨10.1109/CCGRID.2007.25⟩
Communication dans un congrès
inria-00188408
v1
|
A First Step Towards Automatically Building Network Representations13th International Euro-Par Conference - Euro-Par 2007, Aug 2008, Rennes, France. pp.160-169, ⟨10.1007/978-3-540-74466-5_18⟩
Communication dans un congrès
istex
inria-00407692
v1
|
|
|
Analysis of Scheduling Algorithms with ReservationsIPDPS 2007, Mar 2007, Long Beach, California, United States. pp.1-8
Communication dans un congrès
hal-00186786
v1
|
|
Models for scheduling on large scale platforms: which policy for which application?18th International Parallel and Distributed Processing Symposium (IPDPS'04), 2004, Santa Fe, New Mexico, United States
Communication dans un congrès
hal-00003125
v1
|
|
Bi-criteria Algorithm for Scheduling Jobs on Cluster PlatformsACM Symposium on Parallel Algorithms and Architectures (SPAA), 2004, France. pp.125-132
Communication dans un congrès
hal-00001520
v3
|
The impact of platform models on scheduling techniquesYves Robert and Frédéric Vivien. Introduction to Scheduling, Taylor and Francis, 2009
Chapitre d'ouvrage
inria-00344035
v1
|
|
Influence of Platform Models on Scheduling TechniquesRobert, Yves and Vivien, Frédéric. Introduction to Scheduling, Taylor and Francis publisher, 2009
Chapitre d'ouvrage
hal-00789465
v1
|
Chargement...
Chargement...