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:20260421T090513Z
LOCATION:Plenary Room (Bldg. 6 - 001)
DTSTART;TZID=Europe/Stockholm:20260629T192400
DTEND;TZID=Europe/Stockholm:20260629T192500
UID:submissions.pasc-conference.org_PASC26_sess124_pos140@linklings.com
SUMMARY:Bridging Python Flexibility and GPU Performance with Aithon:"Kerne
 l-Level Optimization, Scaling, and Extreme-Resolution MHD Turbulence Simul
 ations"
DESCRIPTION:Manthan Verma (Indian Institute of Technology kanpur), Gina Si
 taraman (AMD), and Mahendra Verma (Indian Institute of Technology kanpur)\
 n\nWe present Aithon, a GPU-accelerated incompressible flow solver for hyd
 rodynamics and magnetohydrodynamics, designed for extreme-scale supercompu
 ting. Optimized for AMD MI250X GPUs and deployed on the Frontier system, A
 ithon combines kernel-level GPU optimizations, CUDA/HIP-aware MPI, and Pyt
 hon integration via pybind11 to achieve near-ideal scaling up to 32,768 GP
 Us. These capabilities enable some of the highest-resolution MHD turbulenc
 e simulations (in 2D) to date, reaching $8192^2$ and $1536^3$ grids. Using
  multiple independent diagnostics, we resolve a decades-old debate on iner
 tial-range spectral scaling, providing compelling numerical evidence in fa
 vor of Kolmogorov scaling. This work demonstrates how extreme-scale GPU co
 mputing can directly enable definitive scientific breakthroughs.\n\n
END:VEVENT
END:VCALENDAR