BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260422T143036Z
LOCATION:B304
DTSTART;TZID=America/New_York:20241118T090000
DTEND;TZID=America/New_York:20241118T123000
UID:submissions.supercomputing.org_SC24_sess749@linklings.com
SUMMARY:The 10th International Workshop on Data Analysis and Reduction for
  Big Scientific Data
DESCRIPTION:In this new exascale computing era, applications must increasi
 ngly perform online data analysis and reduction—tasks that introduce algor
 ithmic, implementation, and programming model challenges unfamiliar to man
 y scientists and with major implications for the design and use of various
  elements of exascale systems. There are at least three important topics t
 hat this workshop is striving to address: (1) whether several orders of ma
 gnitude of data reduction is possible for exascale sciences; (2) understan
 ding the performance and accuracy trade-off of data reduction; and (3) sol
 utions to effectively reduce data while preserving the information hidden 
 in large scientific datasets. Tackling these challenges requires expertise
  from computer science, mathematics, and application domains to study the 
 problem holistically and develop solutions and robust software tools.\n\nF
 RSZ2 for In-Register Block Compression Inside GMRES on GPUs\n\nThe perform
 ance of the GMRES iterative solver on GPUs is limited by the GPU main memo
 ry bandwidth. Compressed Basis GMRES outperforms GMRES by storing the Kryl
 ov basis in low precision, thereby reducing the memory access. An open que
 stion is whether compression techniques that are more sophisticated...\n\n
 \nThomas Grützmacher (Karlsruhe Institute of Technology (KIT), Technical U
 niversity of Munich); Robert Underwood, Sheng Di, and Franck Cappello (Arg
 onne National Laboratory (ANL), University of Chicago); and Hartwig Anzt (
 Technical University of Munich; University of Tennessee, Innovative Comput
 ing Laboratory (ICL))\n---------------------\nEnabling Data Reduction for 
 Flash-X Simulations\n\nHigh-fidelity physics simulation codes, such as Fla
 sh-X, generate large amounts of simulation data. Much of the data written 
 to files is sparse and can be compressed without significantly impacting t
 he accuracy of the simulation or the quality of the visualizations. Reduce
 d file sizes can significan...\n\n\nRajeev Jain (Argonne National Laborato
 ry (ANL)), Houjun Tang (Lawrence Berkeley National Laboratory (LBNL)), Aka
 sh Dhruv (Argonne National Laboratory (ANL)), and Suren Byna (The Ohio Sta
 te University)\n---------------------\nAccelerating Viz Pipelines Using Ne
 ar-Data Computing: An Early Experience\n\nTraditional scientific visualiza
 tion pipelines transfer entire data arrays from storage to client nodes fo
 r processing into displayable graphics objects. However, this full data tr
 ansfer is often unnecessary, as many visualization filters operate on only
  small subsets of data in a data array. With t...\n\n\nQing Zheng (Los Ala
 mos National Laboratory (LANL), New Mexico Consortium); Brian Atkinson (Lo
 s Alamos National Laboratory (LANL)); Daoce Wang (Indiana University); and
  Jason Lee, John Patchett, Dominic Manno, and Gary Grider (Los Alamos Nati
 onal Laboratory (LANL))\n---------------------\nShifting Between Compute a
 nd Memory Bounds: A Compression-Enabled Roofline Model\n\nThis work propos
 es a compression-enabled roofline model to facilitate this adaptability wi
 th data compression techniques to balance and transform between computatio
 nal and memory demands. This model enables applications to adjust in respo
 nse to the specific strengths and limitations of the underlyin...\n\n\nRam
 asoumya Naraparaju, Tianyu Zhao, Yanting Hu, and Dongfang Zhao (University
  of Washington) and Luanzheng Guo and Nathan Tallent (Pacific Northwest Na
 tional Laboratory (PNNL))\n---------------------\nSZOps: Scalar Operations
  for Error-bounded Lossy Compressor for Scientific Data\n\nError-bounded l
 ossy compression has been a critical technique to significantly reduce the
  sheer amounts of simulation datasets for high-performance computing (HPC)
  scientific applications while effectively controlling the data distortion
  based on user-specified error bound. In many real-world use ca...\n\n\nTr
 ipti Agarwal (University of Utah); Sheng Di (Argonne National Laboratory (
 ANL)); Jiajun Huang (University of California, Riverside); Yafan Huang (Un
 iversity of Iowa); Ganesh Gopalakrishnan (University of Utah); Robert Unde
 rwood (Argonne National Laboratory (ANL)); Kai Zhao (Florida State Univers
 ity); Xin Liang (University of Kentucky); Guanpeng Li (University of Iowa)
 ; and Franck Cappello (Argonne National Laboratory (ANL))\n---------------
 ------\nDRBSD-10 Closing Remarks\n\nXin Liang (University of Kentucky)\n--
 -------------------\nDRBSD-10 Break\n---------------------\nAn Exploration
  of How Volume Rendering is Impacted by Lossy Data Reduction\n\nData reduc
 tion is now frequently used by simulations to reduce the amount of data th
 at needs to be stored. Consequently, several error-bound lossy data reduct
 ion techniques have been developed to help compress scientific datasets wh
 ile trying to maximize quality. However, their impact on visualizati...\n\
 n\nYanni Etchi (Los Alamos National Laboratory (LANL), University of North
  Carolina at Chapel Hill); Daoce Wang (Indiana University, Los Alamos Nati
 onal Laboratory (LANL)); and Pascal Grosset, Terece Turton, James Ahrens, 
 and David Rogers (Los Alamos National Laboratory (LANL))\n----------------
 -----\nFilling the Void: Data-Driven Machine Learning-based Reconstruction
  of Sampled Spatiotemporal Scientific Simulation Data\n\nAs high-performan
 ce computing systems continue to advance, the gap between computing perfor
 mance and I/O capabilities is widening. This bottleneck limits the storage
  capabilities of increasingly large-scale simulations, which generate data
  at never-before-seen granularities while only being able to ...\n\n\nAyan
  Biswas (Los Alamos National Laboratory (LANL)); Aditi Mishra (Arizona Sta
 te University); Meghanto Majumder (Los Alamos National Laboratory (LANL));
  Subhashis Hazarika (Fujitsu Research of America Inc.); Alexander Most and
  Juan Castorena (Los Alamos National Laboratory (LANL)); Christopher Bryan
  (Arizona State University); and Patrick McCormick, James Ahrens, Earl Law
 rence, and Aric Hagberg (Los Alamos National Laboratory (LANL))\n---------
 ------------\nGPUFastqLZ: An Ultra Fast Compression Methodology for Fastq 
 Sequence Data on GPUs\n\nWe present gpuFastqLZ, an ultra-fast compression 
 methodology for FASTQ sequence data on GPUs. Leveraging the high paralleli
 sm capabilities of GPUs, gpuFastqLZ incorporates several optimizations, in
 cluding a fast algorithm for field separation, a 2-bit encoding scheme for
  base fields, and the impleme...\n\n\nTaolue Yang, Youyuan Liu, Bo Jiang, 
 and Sian Jin (Temple University)\n---------------------\nBCSR on GPU: A Wa
 y Forward Extreme-scale Graph Processing on Accelerator-enabled Frontier S
 upercomputer\n\nHandling large graphs in a distributed environment require
 s effective partitioning across processors and efficient management of loc
 al partitions. In 2D partitioning, local graphs often become too sparse, m
 aking memory-efficient data structures crucial. Using the Compressed Spars
 e Row (CSR) format w...\n\n\nNaw Safrin Sattar, Hao Lu, and Feiyi Wang (Oa
 k Ridge National Laboratory (ORNL))\n---------------------\nDRBSD-10 Openi
 ng Remarks\n\nXin Liang (University of Kentucky)\n---------------------\nI
 nvited Talk: Learning from Automatically Synthesized Compression Algorithm
 s\n\nWe are generating data in larger amounts and at higher speeds than ev
 er before. Data compression is able to mitigate the resulting storage and 
 transmission problems, but only if the compression ratio is high enough to
  obtain a meaningful benefit and the throughput is sufficient to not intro
 duce a ne...\n\n\nMartin Burtscher (Texas State University)\n-------------
 --------\nEnhancing Lossy Compression Through Cross-Field Information for 
 Scientific Applications\n\nLossy compression is one of the most effective 
 methods for reducing the size of scientific data containing multiple data 
 fields. It reduces information density through prediction or transformatio
 n techniques to compress the data. Previous approaches use local informati
 on from a single target field w...\n\n\nYouyuan Liu (Temple University), W
 enqi Jia (University of Texas at Arlington), Taolue Yang (Temple Universit
 y), Miao Yin (University of Texas at Arlington), and Sian Jin (Temple Univ
 ersity)\n\nTag: Data Compression, Data Movement and Memory, Middleware and
  System Software\n\nRegistration Category: Workshop Reg Pass\n\nSession Ch
 airs: Sheng Di (Argonne National Laboratory (ANL), University of Chicago);
  Ana Gainaru (Oak Ridge National Laboratory (ORNL)); Sian Jin (Temple Univ
 ersity); Xin Liang (Oregon State University); Kento Sato (RIKEN Center for
  Computational Science (R-CCS)); and Dingwen Tao (Institute of Computing T
 echnology, Chinese Academy of Sciences; University of Chinese Academy of S
 ciences)
END:VEVENT
END:VCALENDAR