BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:Unlocking HPC Performance with AMD Tools & GPUs
DTSTART:20261104T120000Z
DTEND:20261106T160000Z
DTSTAMP:20261030T093600Z
UID:indico-event-597@events.hpc-portal.eu
DESCRIPTION: HPC Training – November 4 to 6\, 2026\n \nThis three-half-
 day program is aimed at HPC scientists\, researchers\, and practitioners w
 ho want to port\, optimize\, and profile their codes on AMD systems.\nProg
 ram highlights:\n\nDay 1 (Beginner): HIP and ROCm introduction\, OpenMP of
 floading\, profiling basics.\nDays 2–3 (Advanced): advanced HIP/OpenMP\,
  GPU-aware MPI\, performance portability frameworks\, AMD profiling tools\
 , latest utilities (trace decoder\, advanced profilers).\nEach module incl
 udes hands-on exercises.\n\n \nAudience: researchers and engineers from a
 cademia or industry with prior HPC experience.\nPrerequisites: Linux comma
 nd-line\, HPC software stack familiarity\, compiling/running codes on HPC 
 systems.\nWhat you will learn:\n\nPort applications from CPU or other vend
 or GPUs to run on AMD GPUs.\nUnderstanding the ROCm SDK and what it provid
 es\n\n\nWhat programming languages can be used for AMD GPUs (HIP\, OpenMP\
 , etc.)\nOptimizing and scaling GPU applications\nCommunication packages i
 ncluding MPI\, RCCL and rocSHMEM\nProfiling and debugging tools for AMD GP
 Us\n\n \nThis training will equip participants with the skills to efficie
 ntly exploit AMD GPUs and CPUs for high-performance workloads.\n \n\nForm
 at: Online: remote participants will access AMD infrastructures via the AM
 D Accelerator Cloud.\n \nCertificate of ParticipationParticipants who com
 plete the training will receive an official Certificate of Participation\,
  recognizing their participation in this AMD training program.\n\nhttps://
 events.hpc-portal.eu/event/597/
URL:https://events.hpc-portal.eu/event/597/
END:VEVENT
END:VCALENDAR