BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/Chicago
X-LIC-LOCATION:America/Chicago
BEGIN:DAYLIGHT
TZOFFSETFROM:-0600
TZOFFSETTO:-0500
TZNAME:CDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0500
TZOFFSETTO:-0600
TZNAME:CST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20211207T055412Z
LOCATION:Online
DTSTART;TZID=America/Chicago:20211114T090000
DTEND;TZID=America/Chicago:20211114T173000
UID:submissions.supercomputing.org_SC21_sess327@linklings.com
SUMMARY:HiPar21: 2nd Workshop on Hierarchical Parallelism for Exascale Com
 puting
DESCRIPTION:Workshop\n\nPPIR: Parallel Pattern Intermediate Representation
 \n\nSchmitz, Miller, Trümper, Müller\n\nHPC systems are becoming rapidly l
 arger, heterogeneous, and generally more complex to fulfill the growing de
 mand for computational resources in science and engineering. HPC system an
 d architecture-specific optimizations are necessary to leverage the full p
 otential of such systems. One approach is to...\n\n---------------------\n
 Did the GPU Obfuscate the Load Imbalance in My MPI Simulation?\n\nEberius,
  Boehme, Pearce\n\nThe current proliferation of GPU-based HPC systems nece
 ssitates a method for assessing the performance of simulations on heteroge
 neous machines.  The addition of GPUs to a system adds multiple hierarchic
 al levels of parallelism to the node architecture.  In this paper, we demo
 nstrate that the tradit...\n\n---------------------\nHiPar21: Panel Sessio
 n\n\nHowes, Slaughter, McIntosh-Smith, Kelly, Taufer\n\n------------------
 ---\nDistributing Higher-Dimensional Simulations across Compute Systems: A
  Widely Distributed Combination Technique\n\nPollinger, Hurler, Obersteine
 r, Pflüger\n\nThe numerical solution of high-dimensional PDE problems is e
 ssential for many research questions, such as understanding relativistic a
 strophysics, quantum physics, or hot fusion plasmas. At the same time, it 
 is haunted by the curse of dimensionality, rendering finely resolved simul
 ations infeasible ...\n\n---------------------\nHiPar21 Morning Break (10-
 10:30 am)\n\n\n\n---------------------\nUintah+Hedgehog: Combining Paralle
 lism Models for End-to-End Large-Scale Simulation Performance\n\nHolmen, S
 ahasrabudhe, Berzins, Bardakoff, Blattner...\n\nThe complexity of heteroge
 neous nodes near and at exascale has increased the need for “heroic” progr
 amming efforts. To accommodate this complexity, significant investment is 
 required for codes not yet optimizing for low-level architecture features 
 (e.g., wide vector units) and/or running at large-sc...\n\n---------------
 ------\nHiPar21: Closing Remarks\n\nRizzi, Howes, Li, Trott, Spiga...\n\n-
 --------------------\nHiPar21 Afternoon Break (3-3:30)\n\n\n\n------------
 ---------\nHiPar21 Lunch Break (12:30-2)\n\n\n\n---------------------\nHiP
 ar21: Welcome and Overview\n\nRizzi, Howes, Li, Trott, Spiga...\n\n-------
 --------------\nAccelerate MMEwald on a New Generation of Sunway Supercomp
 uter\n\nWu, Wu, Shang, Liu, Cui...\n\nThe Poisson solver for the calculati
 on of the electrostatic potential is an essential primitive in quantum mec
 hanics calculations. In this paper, we adopt the Ewald method and propose 
 a highly-optimized and scalable framework for Poisson solver, MMEwald, on 
 the new generation Sunway supercomputer, c...\n\n---------------------\nHi
 Par21: Invited Talk: "Reasoning About Software Correctness"\n\nParent\n\n-
 --------------------\nBenchmarking and Extending SYCL Hierarchical Paralle
 lism\n\nDeakin, Alpay, McIntosh-Smith, Heuveline\n\nSYCL is an open-standa
 rd, parallel programming model for programming heterogeneous devices from 
 Khronos. It allows single-source programming of diverse attached devices i
 n a cross-platform manner in modern C++. SYCL provides different layers of
  parallel abstractions, including Same Instruction Multi...\n\n-----------
 ----------\nHiPar21: 2nd Workshop on Hierarchical Parallelism for Exascale
  Computing\n\nRizzi, Li, Hollman, Howes\n\nHigh-performance computing (HPC
 ) platforms are evolving towards having fewer but more powerful nodes, dri
 ven by the increasing number of physical cores in multiple sockets and acc
 elerators. The boundary between nodes and networks is starting to blur, wi
 th some nodes now containing tens of compute el...\n\n\nTag: Online Only, 
 Algorithms, Architectures, Extreme Scale Computing, Heterogeneous Systems,
  Memory Systems, Parallel Programming Languages and Models, Resource Manag
 ement and Scheduling\n\nRegistration Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR