BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Shamrock: SPH and more\, from a laptop to Exascale. - Timothée Cl
 éris
DTSTART:20250528T124000Z
DTEND:20250528T130500Z
UID:TALK232744@talks.cam.ac.uk
CONTACT:Cristiano Longarini
DESCRIPTION:We introduce Shamrock\, a performance-portable framework writt
 en in C++17\, targeting CPU and GPUs from any vendors using the SYCL progr
 amming standard\, designed for numerical astrophysics across a wide range 
 of hardware\, from laptops to Exascale systems.\nAstrophysical schemes oft
 en share a common structure: a combination of neighbor searching and the n
 umerical scheme itself. Shamrock embraces such abstractions to provide a c
 ommon framework for multiple hydrodynamical schemes\, namely finite elemen
 ts\, finite volume (with adaptive mesh refinement)\, and Smoothed Particle
  Hydrodynamics. To achieve this\, at its core\, Shamrock features a highly
  optimized\, parallel tree algorithm with negligible construction overhead
 . This tree structure is coupled with a domain decomposition strategy that
  enables near-linear weak scalability across multiple GPUs.\nShamrock achi
 eves 92% weak scaling efficiency on 1024 AMD MI250x GPUs in large-scale Sm
 oothed Particle Hydrodynamics (SPH) simulations. This corresponds to proce
 ssing billions of particles per second\, with tens of millions of particle
 s handled per GPU\, allowing us to perform the first SPH simulations above
  the billion-particle mark for protoplanetary discs.
LOCATION:The Hoyle Lecture Theatre + Zoom 
END:VEVENT
END:VCALENDAR