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:20181221T160908Z
LOCATION:D166
DTSTART;TZID=America/Chicago:20181112T090000
DTEND;TZID=America/Chicago:20181112T173000
UID:submissions.supercomputing.org_SC18_sess173@linklings.com
SUMMARY:ESPM2 2018: Fourth International Workshop on Extreme Scale Program
 ming Models and Middleware
DESCRIPTION:Workshop\nAccelerators, Exascale, Parallel Programming Languag
 es, Libraries, and Models, Workshop Reg Pass\n\nDesign of Data Management 
 for Multi-SPMD Workflow Programming Model\n\nDufaud, Tsuji, Sato\n\nAs bot
 h the complexity of algorithms and architecture increase, development of s
 cientific software becomes a challenge. In order to exploit future archite
 cture, we consider a Multi-SPMD workflow programing model. Then, data tran
 sfer between tasks during computation highly depends on the architecture..
 .\n\n---------------------\nIntegration of CUDA Processing within the C++ 
 Library for Parallelism and Concurrency (HPX)\n\nDiehl, Kaiser, Heller, Se
 shadri\n\nExperience shows that on today's high performance systems, the u
 tilization of different acceleration cards in conjunction with a high util
 ization of all other parts of the system is difficult. Future architecture
 s, like exascale clusters, are expected to aggravate this issue as the num
 ber of cores a...\n\n---------------------\nAnalysis of Explicit vs. Impli
 cit Tasking in OpenMP Using Kripke\n\nJin, Baskaran\n\nDynamic task-based 
 parallelism has become a widely-accepted paradigm in the quest for exascal
 e computing. In this work, we deliver a non-trivial demonstration of the a
 dvantages of explicit over implicit tasking in OpenMP 4.5 in terms of both
  expressiveness and performance. We target the Kripke bench...\n\n--------
 -------------\nESPM2 2018: Closing Remarks\n\nPanda, Subramoni, Schulz\n\n
 ---------------------\nAsynchronous Execution of Python Code on Task Based
  Runtime Systems\n\nTohid, Wagle, Shirzad, Diehl, Serio...\n\nDespite adva
 ncements in the areas of parallel and distributed computing, the complexit
 y of programming on High Performance Computing (HPC) resources has deterre
 d many domain experts, especially in the areas of machine learning and art
 ificial intelligence (AI), from utilizing performance benefits of ...\n\n-
 --------------------\nAutomatic Generation of High-Order Finite-Difference
  Code with Temporal Blocking for Extreme-Scale Many-Core Systems\n\nTanaka
 , Ishihara, Sakamoto, Nakamura, Kimura...\n\nIn this paper we describe the
  basic idea, implementation and achieved performance of our DSL for stenci
 l computation, Formura, on systems based on PEZY-SC2 many-core processor. 
 Formura generates, from high-level description of the differential equatio
 n and simple description of finite-difference ste...\n\n------------------
 ---\nPortable and Reusable Deep Learning Infrastructure with Containers to
  Accelerate Cancer Studies\n\nZaki\n\nAdvanced programming models, domain 
 specific languages, and scripting toolkits have the potential to greatly a
 ccelerate the adoption of high performance computing.  These complex softw
 are systems, however, are often difficult to install and maintain, especia
 lly on exotic high-end systems.  We consid...\n\n---------------------\nIn
 troduction - ESPM2 2018: Fourth International Workshop on Extreme Scale Pr
 ogramming Models and Middleware\n\nSubramoni, Schulz, Panda\n\nNext genera
 tion architectures and systems being deployed are characterized by high co
 ncurrency, low memory per-core, and multiple levels of hierarchy and heter
 ogeneity. These characteristics bring out new challenges in energy efficie
 ncy, fault-tolerance, and scalability. It is commonly believed that...\n\n
 ---------------------\nDistributed Memory Futures for Compile-Time, Determ
 inistic-by-Default Concurrency in Distributed C++ Applications\n\nWilke, H
 ollman, Lewis, Markosyan, Morales\n\nFutures are a widely-used abstraction
  for enabling deferred execution in imperative programs. Deferred executio
 n enqueues tasks rather than explicitly blocking and waiting for them to e
 xecute. Many task-based programming models with some form of deferred exec
 ution rely on explicit parallelism that i...\n\n---------------------\nExa
 scale Challenges in Across-Node Parallelism for Languages and Runtimes\n\n
 Kale\n\nMachines with peak performance exceeding one exaflop/s are just ar
 ound the corner, and promises of sustained exaflop/s machines abound. Are 
 there significant challenges in runtime frameworks and languages that need
  to be met to harness the power of these machines?  We will examine this q
 uestion and ...\n\n---------------------\nWorkshop Morning Break\n\n\n\n--
 -------------------\nHeterogeneous Systems and the Road to Exascale for HP
 C and AI\n\nHolmes\n\n---------------------\nA Unified Runtime for PGAS an
 d Event-Driven Programming\n\nPaul, Chen, Hayashi, Grossman, Sarkar\n\nA w
 ell-recognized characteristic of extreme scale systems is that their compu
 tation bandwidths far exceed their communication bandwidths.  PGAS runtime
 s have proven to be effective in enabling efficient use of communication b
 andwidth, due to their efficient support for short nonblocking one-sided m
 e...\n\n---------------------\nWorkshop Afternoon Break\n\n\n\n-----------
 ----------\nWorkshop Lunch (on your own)\n\n\n
END:VEVENT
END:VCALENDAR