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:20250618T143000
DTEND;TZID=Europe/Stockholm:20250618T150000
UID:submissions.pasc-conference.org_PASC25_sess142_msa252@linklings.com
SUMMARY:The X Frameworks: FFTX, IRISX, FortranX
DESCRIPTION:Sanil Rao and Franz Franchetti (Carnegie Mellon University)\n\
 nMotif-specific libraries have long been the gold standard for writing lar
 ge scale scientific\napplications. These libraries expose key operators an
 d can be specialized to a given\nhardware architecture without significant
  API modification. However, as algorithms\nincrease in complexity, using t
 he library approach leaves performance on the table due\nto optimizations 
 available across library calls. We present recent efforts to optimize\nlib
 rary-based applications without significant source code modification. FFTX
  is a new\nFFT library that uses code generation and runtime compilation t
 o dynamically generate\nFFT kernels and optimize algorithms using FFT’s li
 ke convolution. IRISX leverages the\ncode generation capabilities of FFTX 
 to dynamically dispatch runtime generated kernels\nvia the IRIS runtime sy
 stem, enabling diverse heterogeneity and performance\nportability. Finally
 , FortranX can optimize legacy Fortran programs without source code\nmodif
 ication by leveraging FFTX/IRISX.\n\nDomain: Engineering, Computational Me
 thods and Applied Mathematics\n\nSession Chair: Het Yagnesh Mankad (Oak Ri
 dge National Laboratory)\n\n
END:VEVENT
END:VCALENDAR