PROGRAM
Days: Monday, August 30th Tuesday, August 31st Wednesday, September 1st Thursday, September 2nd Friday, September 3rd
Monday, August 30th
View this program: with abstractssession overviewtalk overview
09:00-10:30 Session 1A: PhD Symposium 1
Chairs:
Location: PhD Symposium Room
09:00 | Memory Efficient Deep Neural Network Training (abstract) |
09:18 | Parallelization and auto-scheduling of data access queries in ML workloads (abstract) PRESENTER: Pawel Bratek |
09:36 | Communication overlapping Pipelined Conjugate Gradients for Distributed Memory Systems and Heterogeneous Architectures (abstract) PRESENTER: Manasi Tiwari |
09:54 | Scalable hybrid parallel ILU preconditioner to solve sparse linear systems (abstract) PRESENTER: Raju Ram |
10:12 | Low-Overhead Reuse Distance Profiling Tool for Multicore (abstract) PRESENTER: Muhammad Aditya Sasongko |
09:00-10:30 Session 1B: ParaMo 2021 - 3rd International Workshop on Parallel Programming Models in High-Performance Cloud
Chairs:
Location: ParaMo Workshop Room
09:00 | Network SLO for High Performance Clouds (abstract) |
09:50 | Rafiki: Task-level Capacity Planning in Distributed Stream Processing Systems (abstract) PRESENTER: Benjamin J. J. Pfister |
09:00-10:30 Session 1C: AMTE 2021 - Asynchronous Many-Task systems for Exascale 2021
Chairs:
Location: AMTE Workshop Room
09:00 | On using modern C++ and nested recursive task parallelism for HPC applications with AllScale (abstract) |
09:50 | Enabling support for zero copy semantics in an Asynchronous Task-based Programming Model (abstract) PRESENTER: Sam White |
10:30-10:50Coffee Break
10:50-12:30 Session 2A: PhD Symposium 2
Chairs:
Location: PhD Symposium Room
10:50 | Interferences between Communications and Computations in Distributed HPC Systems (abstract) |
11:08 | A Low Overhead Tasking Model for OpenMP (abstract) PRESENTER: Chenle Yu |
11:26 | Application-Based Fault Tolerance for Numerical Linear Algebra at Large Scale (abstract) PRESENTER: Daniel Alberto Torres Gonzalez |
11:44 | Collaborative, distributed, scalable and low-cost plat-form based on microservices, containers, mobile devices and Cloud services to solve compute-intensive tasks (abstract) PRESENTER: David Marcelo Petrocelli |
12:02 | Model-based Loop Perforation (abstract) |
10:50-12:30 Session 2B: ParaMo 2021 - 3rd International Workshop on Parallel Programming Models in High-Performance Cloud
Chairs:
Location: ParaMo Workshop Room
10:50 | Extracting Information from Large Scale Graph Data: Case Study on Automated UI Testing (abstract) PRESENTER: Ramazan Faruk Oguz |
11:15 | Parallelizing Automatic Model Management System for AIOps on Microservice Platforms (abstract) PRESENTER: Ruibo Chen |
10:50-12:30 Session 2C: AMTE 2021 - Asynchronous Many-Task systems for Exascale 2021
Chairs:
Location: AMTE Workshop Room
10:50 | An Experimental Study of SYCL Task Graph Parallelism for Large-Scale Machine Learning Workloads (abstract) PRESENTER: Cheng-Hsiang Chiu |
11:15 | OpenMP target task: tasking and target offloading on heterogeneous systems (abstract) PRESENTER: Pedro Valero-Lara |
11:40 | Understanding the Effect of Task Granularity on Execution Time in Asynchronous Many-Task Runtime Systems (abstract) PRESENTER: Shahrzad Shirzad |
12:30-13:30Lunch Break
13:30-15:00 Session 3A: COLOC - 5th Workshop on Data Locality
Chairs:
Location: COLOC Workshop Room
13:30 | Data-Centric Python - Productivity, portability and all with high performance! |
14:05 | Locality-Aware Scheduling of Independent Tasks for Runtime Systems (abstract) PRESENTER: Maxime Gonthier |
14:30 | High Performance Computing with Java Streams (abstract) PRESENTER: João Sobral |
13:30-15:00 Session 3B: Resilience 2021 - 14th Workshop on Resiliency in High Performance Computing (Resilience) in Clusters, Clouds, and Grids
Chairs:
Location: Resilience Workshop Room
13:30 | Faults, Errors and Failures in Extreme-Scale Supercomputers (abstract) |
14:20 | Energy-Efficient Execution of Streaming Task Graphs with Parallelizable Tasks on Multicore Platforms with Core Failures (abstract) PRESENTER: Sebastian Litzinger |
13:30-15:00 Session 3C: AMTE 2021 - Asynchronous Many-Task systems for Exascale 2021
Chairs:
Location: AMTE Workshop Room
13:30 | The Past, Present, and Future of Asynchrony in C++ (abstract) |
14:20 | FleCSI 2.0: The Flexible Computational Science Infrastructure Project (abstract) PRESENTER: Ben Bergen |
15:00-15:15Coffee Break
15:15-16:40 Session 4A: COLOC - 5th Workshop on Data Locality
Chairs:
Location: COLOC Workshop Room
15:15 | Exploring Strategies to Improve Locality Across Many-core Affinities (abstract) PRESENTER: Neil Butcher |
15:40 | Monitoring Collective Communication Among GPUs (abstract) PRESENTER: Muhammet Abdullah Soyturk |
16:05 | ECP: Data Analytics and Optimization Applications On Accelerator-Based Systems (abstract) |
15:15-16:30 Session 4B: Resilience 2021 - 14th Workshop on Resiliency in High Performance Computing (Resilience) in Clusters, Clouds, and Grids
Chairs:
Location: Resilience Workshop Room
15:15 | Exploring the impact of node failures on the resource allocation for parallel jobs (abstract) PRESENTER: Ioannis Vardas |
15:40 | RDPM: An Extensible Tool for Resilience Design Patterns Modeling (abstract) PRESENTER: Mohit Kumar |
16:05 | Characterizing Memory Failures Using Benford’s Law (abstract) PRESENTER: Kurt Ferreira |
15:15-16:30 Session 4C: AMTE 2021 - Asynchronous Many-Task systems for Exascale 2021
Panel session
Chairs:
Location: AMTE Workshop Room
16:40-17:30 Session 5: COLOC - 5th Workshop on Data Locality
Panel session
Chairs:
Location: COLOC Workshop Room
Tuesday, August 31st
View this program: with abstractssession overviewtalk overview
09:00-10:30 Session 6A: HeteroPar 2021 - 19th International Workshop on Algorithms, Models and Tools for Parallel Computing on Heterogeneous Platforms
Chair:
Location: HeteroPar Workshop Room
09:00 | Towards High Level Synthesis Support in the European Deep Learning Library (abstract) |
09:50 | Elastic Deep Learning using Knowledge Distillation with Heterogeneous Computing Resources (abstract) PRESENTER: Ji Liu |
09:00-10:30 Session 6B: FPDAPP 2021 - 4th International Workshop on Future Perspective of Decentralized Applications
Chairs:
Location: FPDAPP Workshop Room
09:00 | Smart Contract Based Public Procurement to Fight Corruption |
09:50 | Towards A Broadcast Time-Lock Based Token Exchange Protocol (abstract) PRESENTER: Fadi Barbara |
10:30-10:50Coffee Break
10:50-12:30 Session 7A: HeteroPar 2021 - 19th International Workshop on Algorithms, Models and Tools for Parallel Computing on Heterogeneous Platforms
Chairs:
Location: HeteroPar Workshop Room
10:50 | Porting Sparse Linear Algebra to Intel GPUs (abstract) PRESENTER: Yu-Hsiang Tsai |
11:15 | Accelerating FFT using NEC SX-Aurora Vector Engine (abstract) PRESENTER: Pablo Vizcaino |
11:40 | A Novel Bi-Objective Optimization Algorithm on Heterogeneous HPC Platforms for Applications with Continuous Performance and Linear Energy Profiles (abstract) PRESENTER: Hamidreza Khaleghzadeh |
12:05 | Towards an efficient sparse storage format for the SpMM kernel in GPUs (abstract) PRESENTER: Ernesto Dufrechou |
10:50-12:30 Session 7B: FPDAPP 2021 - 4th International Workshop on Future Perspective of Decentralized Applications
Chairs:
Location: FPDAPP Workshop Room
10:50 | Decentralisation Over Privacy: An Analysis Of The Bisq Trade Protocol (abstract) PRESENTER: Liam Hickey |
11:15 | DoS Attacks on Blockchain Ecosystem (abstract) PRESENTER: Mayank Raikwar |
11:40 | Towards a graphical DSL for tracing supply chains on blockchain (abstract) PRESENTER: Francesco Faloci |
12:30-13:30Lunch Break
13:30-14:45 Session 8A: HeteroPar 2021 - 19th International Workshop on Algorithms, Models and Tools for Parallel Computing on Heterogeneous Platforms
Chairs:
Location: HeteroPar Workshop Room
13:30 | Heterogeneous Voltage Frequency Scaling of Data-Parallel Applications for Energy Saving on Homogeneous Multicore Platforms (abstract) PRESENTER: Pawel Bratek |
13:55 | Data management model to program irregular compute kernels on FPGA: application to heterogeneous distributed system (abstract) PRESENTER: Erwan Lenormand |
14:20 | Domain-Specific Runtime to Orchestrate Computation on Heterogeneous Platforms (abstract) PRESENTER: Jared O'Neal |
13:30-14:45 Session 8B: LSDVE 2021 - 8th Workshop on Large Scale Distributed Virtual Environments
Chairs:
Location: LSDVE Workshop Room
13:30 | Integrating Fog Computing and Blockchain Technology for Applications with Enhanced Trust and Privacy (abstract) |
14:20 | SMART: a Tool for Trust and Reputation Management in Social Media (abstract) PRESENTER: Nishant Saurabh |
15:00-15:15Coffee Break
15:15-17:00 Session 9A: HeteroPar 2021 - 19th International Workshop on Algorithms, Models and Tools for Parallel Computing on Heterogeneous Platforms
Chair:
Location: HeteroPar Workshop Room
15:15 | Kernel Fusion in OpenCL (abstract) PRESENTER: John Stratton |
15:40 | Feasibility study of Molecular Dynamics kernels exploitation using EngineCL (abstract) PRESENTER: Raúl Nozal |
16:05 | Continuous Self-Adaptation of Control Policies in Automatic Cloud Management (abstract) PRESENTER: Paweł Koperek |
16:30 | An Automata–based Approach to Profit Optimization of Cloud Brokers in IaaS Environment (abstract) PRESENTER: Jakub Gąsior |
15:15-16:00 Session 9B: LSDVE 2021 - 8th Workshop on Large Scale Distributed Virtual Environments
Chairs:
Location: LSDVE Workshop Room
15:15 | Towards Generating Realistic Trace for Simulating Functions-as-a-Service (abstract) PRESENTER: Dilshad Hassan Sallo |
15:40 | SPIRIT: A microservice-based framework for interactive Cloud infrastructure planning (abstract) PRESENTER: Spiros Koulouzis |
16:10-17:00 Session 10: LSDVE 2021 - 8th Workshop on Large Scale Distributed Virtual Environments
Chair:
Location: LSDVE Workshop Room
16:10 | Data management in EpiGraph COVID-19 epidemic simulator (abstract) PRESENTER: David E. Singh |
16:35 | Merging Real Images with Physics Simulations via Data Assimilation (abstract) PRESENTER: Rossella Arcucci |
Wednesday, September 1st
View this program: with abstractssession overviewtalk overview
11:00-12:30 Session 12: Regular Papers 1: Parallel Methods & Applications
Chair:
Location: Euro-Par Conference Room
11:00 | A GPU Architecture Aware Fine-Grain Pruning Technique for Deep Neural Networks (abstract) PRESENTER: Hoeseok Yang |
11:20 | Mixed Precision Incomplete and Factorized Sparse Approximate Inverse Preconditioning on GPUs (abstract) PRESENTER: Fritz Goebel |
11:40 | Outsmarting the Atmospheric Turbulence for Ground-Based Telescopes Using the Stochastic Levenberg-Marquardt Method (abstract) PRESENTER: Yuxi Hong |
12:00 | GPU Accelerated Mahalanobis-average Hierarchical Clustering Analysis (abstract) PRESENTER: Adam Šmelko |
12:30-14:00Lunch Break
14:00-15:30 Session 13: Regular Papers 2: Architectures & Accelerators
Chairs:
Location: Euro-Par Conference Room
14:00 | PrioRAT: Criticality-Driven Prioritization Inside the On-Chip Memory Hierarchy (abstract) PRESENTER: Vladimir Dimić |
14:20 | Optimized Implementation of the HPCG Benchmark on Reconfigurable Hardware (abstract) PRESENTER: Alberto Zeni |
14:40 | Exploiting co-execution with oneAPI: heterogeneity from a modern perspective (abstract) PRESENTER: Raúl Nozal |
15:30-16:30 Session 14: Keynote I
Chair:
Location: Euro-Par Conference Room
15:30 | Big Data and Extreme-Scales: Computational Science in the 21st Century (abstract) |
16:30-18:00 Session 15: Regular Papers 3: Machine Learning & Applications
Chairs:
Location: Euro-Par Conference Room
16:30 | Designing a 3D Parallel Memory-Aware Lattice Boltzmann Algorithm on Manycore Systems (abstract) PRESENTER: Yuankun Fu |
16:50 | Fault-tolerant LU factorisation is low cost (abstract) PRESENTER: Daniel Alberto Torres Gonzalez |
17:10 | Efficient and Systematic Partitioning of Large and Deep Neural Networks for Parallelization (abstract) PRESENTER: Haoran Wang |
17:30 | Towards Flexible and Compiler-Friendly Layer Fusion for CNNs on Multicore CPUs (abstract) PRESENTER: Zhongyi Lin |
Thursday, September 2nd
View this program: with abstractssession overviewtalk overview
09:30-11:00 Session 16: Regular Papers 4: Scheduling & Load Balancing I
Chairs:
Location: Euro-Par Conference Room
09:30 | Collaborative GPU Preemption via Spatial Multitasking for Efficient GPU Sharing (abstract) PRESENTER: Zhuoran Ji |
09:50 | A Fixed-Parameter Algorithm for Scheduling Unit dependent Tasks with Unit Communication Delays (abstract) PRESENTER: Ning Tang |
10:10 | Plan-based Job Scheduling for Supercomputers with Shared Burst Buffers (abstract) PRESENTER: Jan Kopański |
10:30 | A log-linear (2+5/6)-approximation algorithm for parallel machine scheduling with a single orthogonal resource (abstract) PRESENTER: Adrian Naruszko |
11:00-12:30 Session 17: Regular Papers 5: Scheduling & Load Balancing II
Chairs:
Location: Euro-Par Conference Room
11:00 | An MPI-Parallel Algorithm for Mapping Complex Networks onto Hierarchical Architectures (abstract) PRESENTER: Maria Predari |
11:20 | Taming Tail Latency in Key-Value Stores: a Scheduling Perspective (abstract) PRESENTER: Anthony Dugois |
11:40 | Pipelined Model Parallelism: Complexity Results and Memory Considerations (abstract) PRESENTER: Alena Shilova |
12:00 | Enhancing Load-Balancing of MPI Applications with Workshare (abstract) PRESENTER: Julien Jaeger |
12:30-14:00Lunch Break
14:00-15:30 Session 18: Regular Papers 6: Power & Performance Modeling
Chairs:
Location: Euro-Par Conference Room
14:00 | Trace-driven Workload Generation and Execution (abstract) PRESENTER: Yannis Sfakianakis |
14:20 | Update on the Asymptotic Optimality of LPT (abstract) PRESENTER: Redouane Elghazi |
14:40 | E2EWatch: An End-to-end Anomaly Diagnosis Framework for Production HPC Systems (abstract) PRESENTER: Burak Aksar |
15:00 | Sustaining Performance While Reducing Energy Consumption: A Control Theory Approach (abstract) PRESENTER: Raphaël Bleuse |
15:30-16:30 Session 19: Keynote II
Chair:
Location: Euro-Par Conference Room
15:30 | HPC for Bioinformatics: The Genetic Sequence Comparison Quest for Performance (abstract) |
16:30-18:00 Session 20: Regular Papers 7: Theory & Algorithms
Chairs:
Location: Euro-Par Conference Room
16:30 | Algorithm design for Tensor Units (abstract) PRESENTER: Francesco Silvestri |
16:50 | TSLQueue: An Efficient Lock-free Design for Priority Queues (abstract) PRESENTER: Adones Rukundo |
17:10 | A Scalable Approximation Algorithm for Weighted Longest Common Subsequence (abstract) PRESENTER: Thomas Lavastida |
17:30 | G-Morph: Induced Subgraph Isomorphism Search of Labeled Graphs on a GPU (abstract) PRESENTER: Bryan Rowe |
Friday, September 3rd
View this program: with abstractssession overviewtalk overview
09:30-11:00 Session 21: EU Projects: European Initiative Projects Towards Exascale Computing
Chairs:
Location: EU Projects Room
09:30 | European Processor Initiative and EU Projects Towards Exascale Computing (abstract) |
09:45 | EPEEC: Europe toward High Coding Productivity for Exascale (abstract) |
10:00 | SparCity: Optimizing Sparse Computation and Graphs for Novel Parallel Architectures (abstract) |
11:00-12:30 Session 22: Regular Papers 8: Tools & Environments
Chairs:
Location: Euro-Par Conference Room
11:00 | ALONA: Automatic Loop Nest Approximation with Reconstruction and Space Pruning (abstract) PRESENTER: Daniel Maier |
11:20 | Automatic low-overhead load-imbalance detection in MPI applications (abstract) PRESENTER: Peter Arzt |
11:40 | Smart Distributed DataSets for Stream Processing (abstract) PRESENTER: Miguel Coimbra |
12:30-14:00Lunch Break
14:00-15:30 Session 23: Regular Papers 9: Cloud & Edge Computing
Chairs:
Location: Euro-Par Conference Room
14:00 | Colony: Parallel Functions as a Service on the Cloud-Edge Continuum (abstract) PRESENTER: Francesc-Josep Lordan Gomis |
14:20 | Horizontal Scaling in Cloud using Contextual Bandits (abstract) PRESENTER: David Delande |
14:40 | Geo-Distribute Cloud Applications at the Edge (abstract) PRESENTER: Marie Delavergne |
15:00 | A Fault Tolerant and Deadline Constrained Sequence Alignment Application on Cloud-based Spot GPU Instances (abstract) PRESENTER: Rafaela Brum |
15:30-16:30 Session 24: Keynote III
Chairs:
Location: Euro-Par Conference Room
15:30 | Knowledge Graphs, Graph AI, and the Need for High-performance Graph Computing (abstract) |
16:30-18:00 Session 25: Regular Papers 10: Programming & Languages
Chairs:
Location: Euro-Par Conference Room
16:30 | Particle-In-Cell Simulation using Asynchronous Tasking (abstract) PRESENTER: Nicolas Guidotti |
16:50 | Efficient GPU Computation using Task Graph Parallelism (abstract) PRESENTER: Dian-Lun Lin |
17:10 | Accelerating Graph Applications Using Phased Transactional Memory (abstract) PRESENTER: Catalina Munoz Morales |
17:30 | Towards High Performance Resilience using Performance Portable Abstractions (abstract) PRESENTER: Nicolas Morales |
18:00-18:30 Session 26: Closing Session
Chairs:
Location: Euro-Par Conference Room
18:00 | Closing of the Euro-Par 2021 |
18:15 | Presenting the Euro-Par 2022 |