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:242
DTSTART;TZID=America/Chicago:20211115T090000
DTEND;TZID=America/Chicago:20211115T170000
UID:submissions.supercomputing.org_SC21_sess340@linklings.com
SUMMARY:ESPM2 2021: Sixth International Workshop on Extreme Scale Programm
 ing Models and Middleware
DESCRIPTION:Workshop\n\nThe sixth edition of the ESPM2 workshop, being pro
 posed to be held as a full-day meeting with the Supercomputing (SC21) conf
 erence in St. Louis, Missouri focuses on programming models and runtimes f
 or extreme-scale systems. Next-generation architectures and systems being 
 deployed are characterized by high concurrency, low memory per-core, and m
 ultiple levels of hierarchy and heterogeneity. These characteristics bring
  out new challenges in energy efficiency, fault-tolerance and, scalability
 . It is commonly believed that software has the biggest share of the respo
 nsibility to tackle these challenges. In other words, this responsibility 
 is delegated to the next generation programming models and their associate
 d middleware/runtimes. This workshop focuses on different aspects of progr
 amming models such as task-based parallelism (Charm++, OCR, Habanero, Legi
 on, X10, HPX, etc), PGAS (OpenSHMEM, UPC, CAF, Chapel, UPC++, etc.), BigDa
 ta (Hadoop, Spark, Dask etc), Machine Learning (NVIDIA RAPIDS, Scikit-lear
 n, etc.), Deep Learning (Caffe, Microsoft CNTK, Google TensorFlow, Faceboo
 k PyTorch), directive-based languages (OpenMP, OpenACC) and Hybrid MPI+X, 
 etc. It also focuses on their associated middleware (unified runtimes, int
 eroperability for hybrid programming, tight integration of MPI+X, and supp
 ort for accelerators/FPGAs) for next-generation systems and architectures.
 \n\nThe ultimate objective of the ESPM2 workshop is to serve as a forum th
 at brings together researchers from academia and industry working in the a
 reas of programming models, runtime systems, compilation and languages, an
 d application developers.\n\nESPM2 2021 will be held as a full-day worksho
 p in conjunction with the SuperComputing (SC 2021) in St. Louis, Missouri,
  USA.\n\nPerformance Evaluation of Python Parallel Programming Models: Cha
 rm4Py and Mpi4py\n\nFink\n\nPython is rapidly becoming the lingua franca o
 f machine learning and scientific computing. With the broad use of framewo
 rks such as Numpy, SciPy, and TensorFlow, scientific computing and machine
  learning are seeing a productivity boost on systems without a requisite l
 oss in performance. While high-p...\n\n---------------------\nParallel SIM
 D - A Policy Based Solution for Free Speed-Up Using C++ Data-Parallel Type
 s\n\nYadav, Gupta, Reverdell, Kaiser\n\nRecent additions to the C++ standa
 rd and ongoing standardization efforts aim to add data-parallel types to t
 he C++ standard library. This enables the use of vectorization techniques 
 in existing C++ codes without having to rely on the C++ compiler's abiliti
 es to auto-vectorize the code's execution. T...\n\n---------------------\n
 ESPM:  Lunch Break (12:30-2)\n\n\n\n---------------------\nAccelerating Me
 ssages by Avoiding Copies in an Asynchronous Task-Based Programming Model\
 n\nBhat, White, Ramos, Kale\n\nTask-based programming models promise impro
 ved communication performance for irregular, fine-grained, and load imbala
 nced applications. They do so by relaxing some of the messaging semantics 
 of stricter models and taking advantage of those at the lower-levels of th
 e software stack. For example, whil...\n\n---------------------\nOpening T
 alk: HPC in the 20’s - Scalable On-Premise Performance in the Cloud\n\nDeR
 ose\n\nThe continuous increase in complexity and scale of high-end systems
 , together with the evolving diversity of processor options, are forcing c
 omputational scientists to face system characteristics that can significan
 tly impact the performance and scalability of applications. HPC users need
  a system i...\n\n---------------------\nScalable Parallel Algorithm for F
 ast Computation of Transitive Closure on Shared Memory Architectures\n\nPa
 tel, Dave, Kumbhani, Desai, Kumar...\n\nWe present a scalable algorithm th
 at computes the transitive closure of a graph on shared memory architectur
 es using the OpenMP API in C++. Two different parallelization strategies h
 ave been presented and the performance of the two algorithms has been comp
 ared for several data-sets of varying sizes....\n\n---------------------\n
 Closing Remarks\n\nPanda, Subramoni, Shafi, Schulz\n\nClosing Remarks\n\n-
 --------------------\nTaskflow-San: Sanitizing Erroneous Control Flow in T
 askflow Programs\n\nMajors, Mower, Huang\n\nTaskflow is a general-purpose 
 parallel and heterogeneous task graph programming system that enables in-g
 raph control flow to express end-to-end parallelism. By integrating contro
 l-flow decisions into condition tasks, developers can efficiently overlap 
 CPU-GPU dependent tasks both inside and outside ...\n\n-------------------
 --\nESPM:  Afternoon Break (3-3:30)\n\n\n\n---------------------\nESPM:  M
 orning Break (10-10:30)\n\n\n\n---------------------\nESPM2 2021: Sixth In
 ternational Workshop on Extreme Scale Programming Models and Middleware\n\
 nSubramoni, Shafi, Schulz, Panda\n\nNext-generation architectures and syst
 ems being deployed are characterized by high concurrency, low memory per-c
 ore, and multiple levels of hierarchy/heterogeneity. These bring out new c
 hallenges in energy efficiency, fault-tolerance and scalability. It is com
 monly believed that next-generation prog...\n\n---------------------\nWhat
  Are the Different Approaches for Developing Tools, Languages, and Program
 ming Models for Quantum Computing?\n\nArora, Paz\n\n---------------------\
 nEvaluation of Distributed Tasks in Stencil-Based Application on GPUs\n\nR
 aut, Anderson, Araya-Polo, Meng\n\nIn the era of exascale computing, the t
 raditional MPI+X paradigm starts losing its strength in taking advantage o
 f heterogeneous systems. Subsequently, research and development on finding
  alternative programming models and runtimes have become increasingly popu
 lar. This encourages comparison, on com...\n\n\nTag: Architectures, Big Da
 ta, Cloud and Distributed Computing, Extreme Scale Computing, Parallel Pro
 gramming Languages and Models, Parallel Programming Systems, Quantum Compu
 ting, Scientific Computing\n\nRegistration Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR