BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20250822T115805Z
LOCATION:Room 6.0D13
DTSTART;TZID=Europe/Stockholm:20250618T140000
DTEND;TZID=Europe/Stockholm:20250618T143000
UID:submissions.pasc-conference.org_PASC25_sess142_msa175@linklings.com
SUMMARY:ProtoX: A Code Generation System for Stencil Operations
DESCRIPTION:Het Yagnesh Mankad (Oak Ridge National Laboratory); Sanil Rao 
 (Carnegie Mellon University); Phillip Colella (Lawrence Berkeley National 
 Laboratory); Brian Van Straalen (Lawrence Berkeley National Laboratory, Ca
 rnegie Mellon University); and Franz Franchetti (Carnegie Mellon Universit
 y)\n\nProtoX is a code generation framework for stencil and pointwise oper
 ations-the key  components in numerically approximating the solution to va
 rious partial differential equations (PDEs). The frontend for ProtoX uses 
 Proto-a C++ based domain specific library that provides a high level of ab
 straction and an intuitive interface that optimizes the designing and sche
 duling of an algorithm aimed at solving various PDEs numerically on struct
 ured grids. The high level of abstractions used in Proto can be fused toge
 ther to improve its current performance. However, abstraction fusion canno
 t be performed easily by a compiler. To overcome this issue ProtoX uses SP
 IRAL as its backend. SPIRAL is a code generation system that focuses on ge
 nerating highly optimized target code in C/C++. The performance gain that 
 is thus obtained in ProtoX is demonstrated for examples like the 2D Poisso
 n problem as well as the 2Dand3D Euler equations that are used in the stud
 y of gas dynamics. The results obtained from CPU and GPU implementations w
 ill be discussed. An LLM-based based approach to reduce the numerical erro
 r in structured grid examples from Proto will also be introduced.\n\nDomai
 n: Engineering, Computational Methods and Applied Mathematics\n\nSession C
 hair: Het Yagnesh Mankad (Oak Ridge National Laboratory)\n\n
END:VEVENT
END:VCALENDAR