<html><body><div style="font-family: arial, helvetica, sans-serif; font-size: 12pt; color: #000000"><div>CALL FOR PARTICIPATION - PDSW 2021 <br>===============================================================<br>The 6th International Parallel Data Systems Workshop <br><a data-mce-href="http://www.pdsw.org/%20" href="http://www.pdsw.org/%20">http://www.pdsw.org/</a> <br><br>Monday, 15 November 2021 9:00am - 4:55pm CST<br><br>Held in conjunction with SC21: The International Conference for <br>High Performance Computing, Networking, Storage and Analysis, <br>In cooperation with IEEE TCHPC. <br>=============================================================== <br>### WORKSHOP ABSTRACT ###<br><br>The 6th International Parallel Data Systems Workshop (PDSW’21). PDSW'21 will be hosted in conjunction with SC21: The International Conference for High Performance Computing, Networking, Storage and Analysis.<br><br>Efficient data storage and data management are crucial to scientific productivity in both traditional simulation-oriented HPC environments and Big Data analysis environments. This issue is further exacerbated by the growing volume of experimental and observational data, the widening gap between the performance of computational hardware and storage hardware and the emergence of new data-driven algorithms in machine learning. The goal of this workshop is to facilitate research that addresses the most critical challenges in scientific data storage and data processing.<br><br>### PROGRAM ###<br><br>9:00am – 9:10am Welcome & Introduction<br><br>== Session 1 ==<br>9:10am – 10:00am Invited Speaker - Marcos K. Aguilera, VMware<br> Why Memory Is Your Next Bottleneck And How To Overcome It<br><br>(10:00am - 10:30am Morning Coffee Break)<br><br>== Session 2 ==<br>10:30am - 10:55am New Challenges of Benchmarking All-Flash Storage for HPC<br> Glenn K. Lockwood (Lawrence Berkeley National Laboratory)<br> Alberto Chiusole (Lawrence Berkeley National Laboratory)<br> Nicholas J. Wright (Lawrence Berkeley National Laboratory)<br><br>10:55am - 11:20am Understanding the I/O Impact on the Performance of High-Throughput Molecular Docking <br> Stefano Markidis (KTH Royal Institute of Technology) <br> Davide Gadioli (Polytechnic University of Milan)<br> Emanuele Gadioli (Polytechnic University of Milan) <br> Gianluca Palermo (Polytechnic University of Milan) <br><br>11:20am - 11:45am I/O Bottleneck Detection and Tuning: Connecting the Dots using Interactive Log Analysis<br> Jean Luca Bez (Lawrence Berkeley National Laboratory) <br> Houjun Tang (Lawrence Berkeley National Laboratory) <br> Bing Xie (Oak Ridge National Laboratory)<br> David Williams-Young (Lawrence Berkeley National Laboratory) <br> Rob Latham (Argonne National Laboratory) <br> Rob Ross (Argonne National Laboratory) <br> Sarp Oral (Oak Ridge National Laboratory)<br> Suren Byna (Lawrence Berkeley National Laboratory) <br><br>== Session 3 ==<br>11:45am - 12:10pm Data-Aware Storage Tiering for Deep Learning <br> Cong Xu (Hewlett Packard Enterprise) <br> Suparna Bhattacharya (Hewlett Packard Enterprise) <br> Martin Foltin (Hewlett Packard Enterprise) <br> Suren Byna (Lawrence Berkeley National Laboratory) <br> Paolo Faraboschi (Hewlett Packard Enterprise)<br><br>12:10pm - 12:20pm (WiP) pMEMCPY: A Simple, Lightweight, and Portable I/O Library for Storing Data in Persistent Memory <br> Luke Logan (Illinois Institute of Technology)<br><br>12:20pm - 12:30pm (WiP) Optimising I/O using Non-Volatile Memory <br> Adrian Jackson (University of Edinburgh)<br><br>(12:30pm - 2:00pm Lunch Break)<br><br>== Session 4 ==<br>2:00pm - 2:30pm Invited Industry Talk: Jump's Archive for the Next Decade <br> Alex Davies (Jump Trading LLC)<br><br>== Session 5 ==<br>2:30pm - 2:40pm (WiP) Network-accelerated Distributed File Systems <br> Salvatore Di Girolamo (ETH Zürich)<br><br>2:40pm - 2:50pm (WiP) High-throughput Small File Access for Large-scale Machine Learning Applications <br> Hiroki Ohtsuji (Fujitsu Ltd)<br><br>2:50pm - 3:00pm (WiP) Hyperconverged Storage for High Performance Data Analysis in High Energy Physics: A Case of Intel DAOS Deployment <br> Alexander Moskovsky (RSC Group) <br><br>(3:00pm - 3:30pm Afternoon Coffee Break)<br><br>== Session 6 ==<br>3:30pm - 3:55pm SCTuner: An Auto-tuner Addressing Dynamic I/O Needs on Supercomputer I/O Sub-systems <br> Houjun Tang (Lawrence Berkeley National Laboratory)<br> Bing Xie (Oak Ridge National Laboratory) <br> Suren Byna (Lawrence Berkeley National Laboratory) <br> Philip Carns (Argonne National Laboratory) <br> Quincey Koziol (Lawrence Berkeley National Laboratory) <br> Sudarsun Kannan (Rutgers University) <br> Jay Lofstead (Sandia National Laboratories) <br> Sarp Oral (Oak Ridge National Laboratory, Open Scalable File Systems Inc)<br><br>3:55pm - 4:20pm User-Centric System Fault Identification Using IO500 Benchmark <br> Radita Liem (RWTH Aachen University)<br> Gerald Loftstead (Sandia National Laboratories)<br><br>4:20pm - 4:45pm Verifying IO Synchronization from MPI Traces <br> Sushma Yellapragada (University of Illinois) <br> Chen Wang (University of Illinois) <br> Marc Snir (University of Illinois)<br><br>4:45pm - 4:55pm Closing Remarks<br><br>#############<br></div><div><br data-mce-bogus="1"></div></div></body></html>