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:20210402T160544Z
LOCATION:Track 6
DTSTART;TZID=America/New_York:20201112T155000
DTEND;TZID=America/New_York:20201112T163000
UID:submissions.supercomputing.org_SC20_sess212_ws_llvmf105@linklings.com
SUMMARY:Robust Practical Binary Optimization at Run-Time Using LLVM
DESCRIPTION:Workshop\n\nRobust Practical Binary Optimization at Run-Time U
 sing LLVM\n\nEngelke, Schulz\n\nIn High Performance Computing (HPC), perfo
 rmance of applications are important factors, which is has led to a wide b
 ody of work on optimizing compilers. However, compilers alone are naturall
 y limited in their potential, as they cannot exploit run-time information 
 to specialize generated code. For this reason, run-time components to perf
 orm such specializations are gaining traction. In particular, application 
 or use driven specializations have a high potential for optimizations, as 
 they can benefit from explicit guidance from the application or the user, 
 which allows for targeted changes incorporating specific knowledge. Becaus
 e full compilers and sources are usually unavailable during computation, s
 pecializations have to be done at machine code level. However, existing li
 braries for binary specialization face structural limitations of separatin
 g optimization and code generation, in addition to numerous implementation
  gaps.\n\nIn this paper, we describe BinOpt, a novel and robust library fo
 r performing application-driven binary optimization and specialization usi
 ng LLVM. A machine code function is lifted directly to LLVM-IR, optimized 
 in LLVM while making use of application-specified information, used to gen
 erate a new specialization for a function, and integrated back to the orig
 inal code. We apply this technique to existing optimized code and show tha
 t significant performance improvements can be observed with only a small o
 ptimization time overhead.\n\nRegistration Category: Workshop Reg Pass
END:VEVENT
END:VCALENDAR