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:20211207T055400Z
LOCATION:220-221
DTSTART;TZID=America/Chicago:20211119T083000
DTEND;TZID=America/Chicago:20211119T120000
UID:submissions.supercomputing.org_SC21_sess339@linklings.com
SUMMARY:PEHC: Programming Environments for Heterogeneous Computing
DESCRIPTION:Workshop\n\nUbiquitous heterogeneous computing is increasingly
  becoming the norm in computing systems. In addition to hardware innovatio
 n, the community needs to shift the software environment to enable heterog
 eneity in an equitable, secure and sustainable manner. With increasing inn
 ovation in the accelerator space, there is a growing diversity in the syst
 ems built around them, and their software and management stacks. As a resu
 lt, end users are encountering increasing difficulty in reusing applicatio
 ns across different, and potentially multiple, accelerators.\n\nTo address
  these problems, the inaugural “Programming Environments for Heterogeneous
  Computing” workshop aimed to gather users, researchers, hardware and soft
 ware developers to address the opportunities and challenges of heterogenei
 ty. Of particular interest were practical solutions that address reuse, fu
 nctional and performance portability, DevOps, low-code and no-code develop
 ment, and functional and non-functional characteristics of run times, prog
 ramming languages, compilers and tools. Of interest were traditional HPC, 
 cloud and edge, and convergence of HPC and AI.\n\nFor the first workshop, 
 we have primarily focused on paper and discussion sessions. We have organi
 zed two sessions, one on tools and the other on systems. Both sessions wil
 l end with a discussion slot to encourage cross-fertilization of ideas.\n\
 nThe tools session, features ML-driven auto-tuner for heterogeneous platfo
 rms; automatically parallelizing compiler and API for heterogeneous multic
 ores; and a Python-based high-level programming flow for CPU-FPGA heteroge
 neous systems.  \n\nThe systems session features a holistic systems approa
 ch to leveraging heterogeneity; survival of the fittest amidst the Cambria
 n explosion of processor architectures for artificial intelligence; and de
 signing heterogeneous systems: large scale architectural exploration via s
 imulation.\n\nTools Session Q&A\n\nGokhale\n\nAll three presenters from th
 e tools session will join for a common Q&A session.\n\n-------------------
 --\nOSCAR Parallelizing and Power Reducing Compiler and API for Heterogene
 ous Multicores\n\nKasahara\n\nThis presentation introduces the OSCAR Paral
 lelizing and Power Reducing Compiler and API for shared memory heterogeneo
 us multicore processors having general-purpose and accelerator cores.  The
 y parallelize and vectorize a sequential C or Fortran program automaticall
 y using Multigrain Parallelization...\n\n---------------------\nSystems Se
 ssion Q&A\n\nBadia\n\nAll three presenters from the Systems session will j
 oin for a common Q&A session.\n\n---------------------\nPEHC:   Morning Br
 eak (10-10:30)\n\n\n\n---------------------\nSurvival of the Fittest Amids
 t the Cambrian Explosion of Processor Architectures for Artificial Intelli
 gence\n\nSukumar\n\nThe need for high performance computing in data-driven
  artificial intelligence (AI) workloads has led to the Cambrian explosion 
 of processor architectures. As these novel processor architectures aim to 
 evolve and thrive inside datacenters and cloud-services, we need to unders
 tand different figures-o...\n\n---------------------\nA Holistic Systems A
 pproach to Leveraging Heterogeneity\n\nSury, Pennycook, Thierry, Tian, Wis
 niewski\n\nIncreasingly, HPC developers are turning to heterogeneity to co
 ntinue to achieve the performance they desire.  Leveraging heterogeneity h
 owever is challenging.  While an increasing number of applications are sta
 rting to gain advantage from heterogeneity, there remains much work before
  it sees widesp...\n\n---------------------\nPEHC: Programming Environment
 s for Heterogeneous Computing\n\nBadia, Gokhale, Milojicic, Hwu, Kasahara.
 ..\n\nUbiquitous heterogeneous computing is increasingly becoming the norm
  in computing systems. In addition to hardware innovation, the community n
 eeds to shift the software environment to enable heterogeneity in an equit
 able, secure and sustainable manner. With increasing innovation in the acc
 elerator s...\n\n---------------------\nDesigning Heterogeneous Systems:  
 Large-Scale Architectural Exploration via Simulation\n\nEmmot\n\nThe end o
 f Dennard’s scaling in 2005 and the emerging end of Moore’s La
 w has resulted in a number of heterogeneous design wins, applied to comput
 e (vector processing (GPUs), vector-matrix multiplication, FPGAs, etc.), m
 emory (High Bandwidth Memory (HBM), Fabric Attached Memory (FAM), mem...\n
 \n---------------------\nGenMAT:  A General-Purpose Machine Learning-Drive
 n Auto-Tuner for Heterogeneous Platforms\n\nZhang, Srivastava, Kannan, Pra
 sanna\n\nTo assist the end-users in optimally deploying workloads on the h
 eterogeneous environment with high productivity, a fundamental problem is 
 to automatically find the best “variant” of an application—the implementat
 ion with the optimal configurations on the most suitable hardware resource
  resulting in...\n\n---------------------\nA Python-Based High-Level Progr
 amming Flow for CPU-FPGA Heterogeneous Systems\n\nHuang\n\nThe fast-growin
 g complexity of new applications and new use scenarios poses serious chall
 enges for computing systems. Heterogeneous systems consist of different ty
 pes of processors and accelerators, and provide unique combined benefits o
 f hardware acceleration from each individual component. CPU-FPG...\n\n\nTa
 g: Heterogeneous Systems, Parallel Programming Languages and Models, Paral
 lel Programming Systems, Productivity Tools, System Software and Runtime S
 ystems\n\nRegistration Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR
