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:20250822T115807Z
LOCATION:Room 5.2D02
DTSTART;TZID=Europe/Stockholm:20250618T153000
DTEND;TZID=Europe/Stockholm:20250618T160000
UID:submissions.pasc-conference.org_PASC25_sess103_msa188@linklings.com
SUMMARY:Shamrock: Scaling SPH to Exascale for Astrophysics Using SYCL
DESCRIPTION:Timothée David--Cléris (Université Grenoble Alpes)\n\nShamrock
  is a native SYCL-based framework designed for numerical astrophysics on e
 xascale architectures. Developed in C++17, Shamrock addresses the growing 
 need for efficient and scalable solutions in hydrodynamical simulations fo
 r astrophysics. The core of the framework utilizes a ray-tracing-inspired 
 parallel tree structure nested within an abstracted domain decomposition. 
 This design enables the efficient implementation of the Smoothed Particle 
 Hydrodynamics (SPH) algorithm, providing significant speedups for large-sc
 ale simulations and scalability across thousands of GPUs. We chose SYCL fo
 r its portability across CPU and GPU vendors, as well as its performance p
 ortability, allowing us to maintain the same code paths throughout the cod
 ebase. This presentation will introduce Shamrock, its use of SYCL, its per
 formance across multiple vendors and backends, and the reasons behind our 
 initial decision to develop the framework with the buffer/accessor model. 
 We will also discuss our migration to the Unified Shared Memory (USM) mode
 l to achieve finer memory control and reduced latencies.\n\nDomain: Engine
 ering, Computational Methods and Applied Mathematics\n\nSession Chair: And
 rey Alekseenko (KTH Royal Institute of Technology, PDC Center for High Per
 formance Computing)\n\n
END:VEVENT
END:VCALENDAR
