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:20260522T150117Z
LOCATION:C2/3/4 Ballroom
DTSTART;TZID=America/Chicago:20181113T083000
DTEND;TZID=America/Chicago:20181113T170000
UID:submissions.supercomputing.org_SC18_sess325_spost115@linklings.com
SUMMARY:OoO Instruction Benchmarking Framework on the Back of Dragons
DESCRIPTION:Julian Hammer (University of Erlangen-Nuremberg, RRZE)\n\nIn o
 rder to construct an accurate instruction execution model for modern out-o
 f-order micro architectures, an accurate description of instruction latenc
 y, throughput and concurrency is indispensable. Already existing resources
  and vendor provided information is neither complete nor detailed enough a
 nd sometimes incorrect. We therefore proclaim to deduct this information t
 hrough runtime instruction benchmarking and present a framework to support
  such investigations based on LLVM's just-in-time and cross-platform compi
 lation capabilities.\n\npyasmjit abstracts instructions, operands, and dep
 endency chains, to easily construct the necessary benchmarks. The synthesi
 zed code is interactively compiled and executed using the llvmlite library
 , which in turn is based on the stable LLVM C-API.  pyasmjit offers a comm
 and line as well as a programming interface.  Unlike other approaches, we 
 do not rely on model specific performance counters and focus on interopera
 bility and automation to support quick modeling of future microarchitectur
 es.\n\nRegistration Category: Tech Program Reg Pass, Exhibits Reg Pass\n\n
END:VEVENT
END:VCALENDAR