BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:DAYLIGHT
TZOFFSETFROM:-0500
TZOFFSETTO:-0400
TZNAME:EDT
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=2SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=11;BYDAY=1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20210402T160553Z
LOCATION:
DTSTART;TZID=America/New_York:20201109T090000
DTEND;TZID=America/New_York:20201109T200000
UID:submissions.supercomputing.org_SC20_sess280_job137@linklings.com
SUMMARY:Postdoctoral Appointee – Heterogeneity in High Performance Computi
 ng
DESCRIPTION:Job Posting\n\nPostdoctoral Appointee – Heterogeneity in High 
 Performance Computing\n\n\n\nPosition Description:	\nThe Argonne Leadershi
 p Computing Facility’s (ALCF) mission is to accelerate major scientific di
 scoveries and engineering breakthroughs for humanity by designing and prov
 iding world-leading computing facilities in partnership with the computati
 onal science community. We help researchers solve some of the world’s larg
 est and most complex problems with our unique combination of supercomputin
 g resources and computational science expertise\n\nHeterogeneity in High P
 erformance Computing (HPC) has never been greater, and most exascale syste
 ms deployed in the US will be accelerator-based systems. Understanding the
  performance of applications running on sizeable fractions of those machin
 es will be a challenge, as the scale and complexity of those applications 
 will be unprecedented. Nonetheless, the hybrid nature of these platforms o
 ffers a common opportunity to better understand how the applications inter
 act with the accelerator (which is where most of the computing power will 
 reside). Indeed, the Application Programming Interfaces (APIs) of those ac
 celerators are well defined entry points that can be traced. CUDA or OpenC
 L are such APIs. By applying techniques derived from Model Centric Debuggi
 ng on those APIs, it is possible to capture most of the accelerator-relate
 d context and events. Those techniques have already been leveraged in an H
 PC context for debugging purposes or for porting an HPC application from C
 UDA to OpenCL.\n\nAt Argonne, in order to meet those challenges, we’ve bee
 n developing a collection of Model Centric Tracing tools that cover the AP
 Is that will be encountered on exascale platforms. In order to meet the sc
 alability and performance requirements, those tracers are based on LTTng, 
 and work on a similar manner to LTTng CLUST but with Model Centric Tracing
  in mind. The fine level of control in the granularity of the captured tra
 ces allows those tracers to be used for a variety of purposes:\n\nProfilin
 g accelerator usage of HPC applications,\nDebugging accelerator usage,\nCa
 pturing traces that can be reinjected in simulation frameworks,\nExtractin
 g kernels for replay, allowing study and tuning in a sand-box,\nLightweigh
 t and transparent monitoring of platform usage.\nMost of those remain to b
 e invented or perfected and offer a lot of opportunities to develop new re
 search. In this context, Argonne’s ALCF is looking for a post-doctoral app
 ointee to perform research and development on the collection of tracers an
 d their uses. Especially, with the exascale Aurora platform expected next 
 year, integration of the tracing framework and its scalability will be an 
 important topic. Another important objective will be to collaborate with a
 pplication developers to help them leverage the possibilities offered by t
 he tracers. The work will take place in a multi-disciplinary environment a
 nd will offer opportunities to interact with a wide range of talents from 
 the whole spectrum of HPC research.  The successful candidate will be expe
 cted to present and publish their work at major symposia and journals.\n\
 nPosition Requirements:	\nIdeal candidates are expected to have:\nRecent P
 hD in related field\nComprehensive knowledge in C/C++ programming under Un
 ix/Linux.\nComprehensive knowledge of one or more libraries and tools such
  as OpenCL, CUDA/HIP, ROCm, Level0\nComprehensive knowledge in System Prog
 ramming\nConsiderable knowledge of parallel algorithms, I/O architectures,
  performance evaluation and tuning.\nConsiderable expertise in parallel pr
 ogramming, multicore systems, threading, and scientific application codes.
 \nConsiderable software development skills, written, and communication ski
 lls.\nGood collaborative skills, including the ability to work well with o
 ther divisions, laboratories, and universities.\nGood self-motivation to g
 et involved and participate in the project team`s research, and balance th
 at against intense code development.\nCandidate should have the ability to
  create, maintain, and support high-quality software.\nAbility to model Ar
 gonne’s Core Values: Impact, Safety, Respect, Integrity, and Teamwork.\n\
 nApplication Documents:\nCover letter (optional); uploaded as a PDF docume
 nt.\nResume.\n\nRegistration Category: Tech Program Reg Pass, Workshop Re
 g Pass, Tutorial Reg Pass, Exhibits Reg Pass
END:VEVENT
END:VCALENDAR