BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Denver
X-LIC-LOCATION:America/Denver
BEGIN:DAYLIGHT
TZOFFSETFROM:-0700
TZOFFSETTO:-0600
TZNAME:MDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0600
TZOFFSETTO:-0700
TZNAME:MST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260422T000610Z
LOCATION:607
DTSTART;TZID=America/Denver:20231112T140000
DTEND;TZID=America/Denver:20231112T173000
UID:submissions.supercomputing.org_SC23_sess435@linklings.com
SUMMARY:PDSW23: 8th International Parallel Data Systems Workshop
DESCRIPTION:PoliMOR: A Policy Engine "Made-to-Order" for Automated and Sca
 lable Data Management in Lustre\n\nModern supercomputing systems are incre
 asingly reliant on hierarchical, multi-tiered file and storage system arch
 itectures due to cost-performance-capacity trade-offs. Within such multi-t
 iered systems, data management services are required to maintain healthy u
 tilization, performance, and capacity l...\n\n\nAnjus George, Christopher 
 Brumgard, Rick Mohr, Ketan Maheshwari, James Simmons, Sarp Oral, and Jesse
  Hanley (Oak Ridge National Laboratory (ORNL))\n---------------------\nPDS
 W – Afternoon Break\n---------------------\nDAOS as HPC Storage:  Explorin
 g Interfaces\n\nWe present preliminary results of research investigating h
 ow the DAOS object store performs under a range of different object class 
 configurations, data access interfaces, and application usage patterns. We
  demonstrate that good performance can be achieved for a number of differe
 nt approaches using ...\n\n\nAdrian Jackson (University of Edinburgh) and 
 Nicolau Nicolau Manubens (European Centre for Medium-Range Weather Forecas
 ts (ECMWF))\n---------------------\nToward Standardized, Open Object-Based
  Computational Storage For Large-Scale Scientific Data Analytics\n\nQing Z
 heng (Los Alamos National Laboratory (LANL), New Mexico Consortium) and Ja
 son Lee, Dominic Manno, and Gary Grider (Los Alamos National Laboratory (L
 ANL))\n---------------------\nDomain-Aware Performant AI-Based Compression
 \n\nMicroscopes play a critical role in scientific discoveries. A grand ch
 allenge in microscopy-based research is to manage the significantly high d
 ata volume and velocity of data generation while ensuring real-time analys
 is and closed-loop microscope operation. The scanning transmission electro
 n micros...\n\n\nBoyuan Zhang (Indiana University); Luanzheng Guo, Nathan 
 Tallent, and Jan Strube (Pacific Northwest National Laboratory (PNNL)); an
 d Dingwen Tao (Indiana University)\n---------------------\nWelcome and Ope
 ning Remarks\n\norganizers' welcome and opening remarks\n\n---------------
 ------\nCompression of Scientific Simulation Data by Stochastic Basis Expa
 nsion – Example on Multiple Computer Systems\n\nTargeting scientific data 
 storage and processing of large-scale complex problems, we consider the in
 troduction of stochastic basis expansions for compressing and restoring da
 ta with low conversion costs by the effective use of high-performance comp
 uter systems and file systems. Here we target Monte ...\n\n\nKohei Fujita 
 and Tsuyoshi Ichimura (University of Tokyo, RIKEN); Lalith Maddegedara (Un
 iversity of Tokyo); and Muneo Hori (Japan Agency for Marine-Earth Science 
 and Technology)\n---------------------\nAdvancing Automated I/O Analysis w
 ith Multi-Perspective Views\n\nReal-world HPC workloads, including simulat
 ions and machine learning, place significant strain on storage infrastruct
 ure due to their data-dependency, exacerbated by the diverse storage optio
 ns in modern HPC environments, leading to I/O bottlenecks. To mitigate the
 se bottlenecks, past analysis metho...\n\n\nIzzet Yildirim (Illinois Insti
 tute of Technology), Hariharan Devarajan (Lawrence Livermore National Labo
 ratory (LLNL)), Anthony Kougkas and Xian-He Sun (Illinois Institute of Tec
 hnology), and Kathryn Mohror (Lawrence Livermore National Laboratory (LLNL
 ))\n---------------------\nEnhancing Metadata Transfer Efficiency: Unlocki
 ng the Potential of DAOS in the ADIOS Context\n\nIn HPC, data movement bet
 ween applications is typically facilitated by I/O middleware, such as the 
 Adaptable I/O System (ADIOS). This middleware leverages the capabilities o
 f the underlying storage services, to facilitate data movement and distrib
 ution. A recent storage system, Intel DAOS, promises ...\n\n\nRanjan Sarpa
 ngala Venkatesh and Greg Eisenhauer (Georgia Institute of Technology), Sco
 tt Klasky (Oak Ridge National Laboratory (ORNL)), and Ada Gavrilovska (Geo
 rgia Institute of Technology)\n---------------------\nAccelerate Stage-Out
  in Single Shared Files from Node-Local Burst-Buffers\n\nKohei Sugihara an
 d Osamu Tatebe (University of Tsukuba)\n---------------------\nIOMax: Maxi
 mizing Out-of-Core I/O Analysis Performance on HPC Systems\n\nI/O analysis
  is an essential task for improving the performance of scientific applicat
 ions on high-performance computing (HPC) systems. However, current analysi
 s tools, which often use data drilling techniques (iterative exploration f
 or deeper insights), treat every query independently and do not op...\n\n\
 nIzzet Yildirim (Illinois Institute of Technology), Hariharan Devarajan (L
 awrence Livermore National Laboratory (LLNL)), Anthony Kougkas and Xian-He
  Sun (Illinois Institute of Technology), and Kathryn Mohror (Lawrence Live
 rmore National Laboratory (LLNL))\n---------------------\nThe I/O Trace In
 itiative:  Building a Collaborative I/O Archive to Advance HPC\n\nHPC appl
 ication developers and administrators need to understand the complex inter
 play between compute clusters and storage systems to make effective optimi
 zation decisions. Ad hoc investigations of this interplay based on isolate
 d case studies can lead to conclusions that are incorrect or difficult...\
 n\n\nNafiseh Moti, André Brinkmann, and Marc-André Vef (Johannes Gutenberg
  University Mainz); Philippe Deniel (CEA); Jesus Carretero (Universidad Ca
 rlos III de Madrid); Philip Carns (Argonne National Laboratory (ANL)); Jea
 n-Thomas Acquaviva (DataDirect Networks (DDN)); and Reza Salkhordeh (Johan
 nes Gutenberg University Mainz)\n---------------------\nGrIOt: Graph-Based
  Modeling of HPC Application I/O Call Stacks for Predictive Prefetch\n\nMo
 dern HPC storage systems use tiers of heterogeneous storage technologies t
 o compromise between capacity, performance, and cost. Prefetching is a tec
 hnique used in these systems to move the right data at the right time from
  a slower to a high-performance tier in order to improve performance with 
 a ...\n\n\nLouis-Marie Nicolas (National Institute of Advanced Technologie
 s of Brittany (ENSTA Bretagne), Bull Atos Technologies); Salim Mimouni and
  Philippe Couvée (Bull Atos Technologies); and Jalil Boukhobza (National I
 nstitute of Advanced Technologies of Brittany (ENSTA Bretagne))\n---------
 ------------\nDAOS Project Update\n\nThe Distributed Asynchronous Object S
 torage (DAOS) is an open source scale-out storage system that is designed 
 from the ground up to support Storage Class Memory (SCM) and NVMe storage 
 in user space. This PDSW23 WiP session highlights two new technologies tha
 t are available in the recently released ...\n\n\nMichael Hennecke and Moh
 amad Chaarawi (Intel Corporation)\n---------------------\nClosing Remarks\
 n\nOrganizers' Closing Remarks\n\n---------------------\nInvited Talk\n\nG
 okul Soundararajan (Amazon)\n---------------------\nToward a Peer-to-Peer 
 Data Distribution Layer for Efficient and Collaborative Resource Optimizat
 ion of Distributed Dataflow Applications\n\nOptimizing the underlying clus
 ter configurations of distributed data processing frameworks can be comple
 x and often requires performance modeling techniques due to the multitude 
 of performance-affecting factors.  While these approaches may not always b
 e applicable due to the need for substantial tra...\n\n\nDominik Scheinert
 , Soeren Becker, Jonathan Will, and Luis Englaender (Technical University 
 of Berlin) and Lauritz Thamsen (University of Glasgow)\n\nTag: Data Analys
 is, Visualization, and Storage, Data Movement and Memory\n\nRegistration C
 ategory: Workshop Reg Pass\n\nSession Chairs: Suren Byna (The Ohio State U
 niversity, Lawrence Berkeley National Laboratory (LBNL)); Jay Lofstead (Sa
 ndia National Laboratories, University of New Mexico); Bing Xie (Microsoft
  Corporation); and Amelie Chi Zhou (Hong Kong Baptist University)
END:VEVENT
END:VCALENDAR