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:20211207T055401Z
LOCATION:224
DTSTART;TZID=America/Chicago:20211115T090000
DTEND;TZID=America/Chicago:20211115T173000
UID:submissions.supercomputing.org_SC21_sess350@linklings.com
SUMMARY:IA^3 2021: 11th Workshops on Irregular Applications: Architectures
  and Algorithms
DESCRIPTION:Workshop\n\nIA^3: Morning Break (10-10:30)\n\n\n\n------------
 ---------\nIA^3: Invited Talk 2 - Implementing Performance Portable Graph 
 Algorithms Using Task-Based Execution\n\nCatalyurek\n\nDesigning flexible 
 graph kernels that can run well on various platforms is a crucial research
  problem due to the frequent usage of graphs for modeling data and recent 
 architectural advances and variety. In this talk, I will present our recen
 t graph processing model and framework, PGAbB, for modern s...\n\n--------
 -------------\nGreatly Accelerated Scaling of Streaming Problems with a Mi
 grating Thread Architecture\n\nPage, Kogge\n\nApplications where continuou
 s streams of data are passed through large data structures are increasing 
 in importance. However, their execution on conventional architectures, is 
 highly inefficient. The primary issue is often the need to stream large nu
 mbers of disparate data items through the equivale...\n\n-----------------
 ----\nToward Scalable Data Processing in Python with CLIPPy\n\nPirkelbauer
 , Bromberger, Iwabuchi, Pearce\n\nThe Python programming language has beco
 me a popular choice for data scientists. While easy to use, the Python lan
 guage is not well suited to drive data science on large scale systems.\n\n
 This paper presents a first prototype of CLIPPy (Command line interface pl
 us Python), a user-side interface in Pyt...\n\n---------------------\nIA^3
 : Lunch Break (12:30-2)\n\n\n\n---------------------\nIA^3: Welcome\n\nTum
 eo, Feo, Minutoli, Castellana\n\n---------------------\nIA^3: Closing Rema
 rks\n\nTumeo, Feo, Minutoli, Castellana\n\n---------------------\nIA^3: In
 vited Talk 1 - Project 38: Innovative Architectures for High-Performance C
 omputing Systems\n\nCheng\n\nThe high-performance computing (HPC) needs of
  the US government require advances in architectures to support a wide var
 iety of critical missions. Project 38 is a cross-agency effort between the
  Department of Defense and the Department of Energy exploring architectura
 l enhancements that will provide ...\n\n---------------------\nNo More Lea
 ky PageRank\n\nSallinen, Ripeanu\n\nWe have surveyed multiple PageRank imp
 lementations available with popular graph processing frameworks, and disco
 vered that they treat sink vertices (i.e., vertices without outgoing edges
 ) incorrectly. This leads to two issues: (i) incorrect PageRank scores, an
 d (ii) flawed performance evaluations (a...\n\n---------------------\nSpar
 se Exact Factorization Update\n\nChen, Davis, Lourenco, Moreno-Centeno\n\n
 To meet the growing need for extended or exact precision solvers, an effic
 ient framework based on Integer-Preserving Gaussian Elimination (IPGE) has
  been recently developed which includes dense/sparse LU/Cholesky factoriza
 tions and dense LU/Cholesky factorization updates for column and/or row re
 plac...\n\n---------------------\nIA^3: Panel\n\nTumeo, Chien, Green, Pedr
 etti, Verbanescu\n\n---------------------\nIA^3 2021: 11th Workshops on Ir
 regular Applications: Architectures and Algorithms\n\nTumeo, Minutoli, Cas
 tellana, Feo\n\nDue to the heterogeneous data sets they process, data-inte
 nsive applications employ a diverse set of methods and data structures, ex
 hibiting irregular memory accesses, control flows and communication patter
 ns. Current supercomputing systems are organized around components optimiz
 ed for data locality...\n\n---------------------\nMapping Irregular Comput
 ations for Molecular Docking to the SX-Aurora TSUBASA Vector Engine\n\nSol
 is Vasquez, Focht, Koch\n\nMolecular docking is a key method in computer-a
 ided drug design, where the rapid identification of drug candidates is cru
 cial for combating diseases. AutoDock is a widely-used molecular docking p
 rogram, having an irregular structure characterized by a divergent control
  flow and compute-intensive cal...\n\n---------------------\nIA^3: Afterno
 on Break (3-3:30)\n\n\n\n---------------------\nAccelerating Unstructured-
 Grid CFD Algorithms on NVIDIA and AMD GPUs\n\nStone, Walden, Zubair, Niels
 on\n\nComputational performance of the FUN3D unstructured-grid computation
 al fluid dynamics application on GPUs is highly dependent on the efficienc
 y of floating-point atomic updates needed to support the irregular cell-, 
 edge-, and node-based data access patterns in massively parallel GPU envir
 onments. W...\n\n\nTag: Algorithms, Architectures, Big Data, Data Analytic
 s, Memory Systems, Numerical Algorithms\n\nRegistration Category: Workshop
  Reg Pass
END:VEVENT
END:VCALENDAR