BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:[Online] Fundamentals of Accelerated Computing with Modern CUDA C+
 +
DTSTART:20261027T080000Z
DTEND:20261029T120000Z
DTSTAMP:20261010T223600Z
UID:indico-event-211@indico.ecap.work
DESCRIPTION:Fundamentals of Accelerated Computing with Modern CUDA C++\n\n
 Schedule & Format\n\nDate: 2026\, October 27-29\nTimes:\n\nOct 27: 9:00 - 
 13:00 CE(S)T\nOct 28: 9:00 - 13:00 CE(S)T\nOct 29: 9:00 - 13:00 CE(S)T\n\n
 \nFormat: Three half-days\nLocation: Online via Zoom\nLanguage: English\n\
 nRegistered participants will receive the video conferencing link via emai
 l on the day before the course.\nInstructor\n\nDr. Sebastian Kuckuk\, NHR@
 FAU\, certified NVIDIA DLI Ambassador\n\nThis course is organized by Erlan
 gen National High Performance Computing Center (NHR@FAU) in collaboration 
 with NVIDIA Deep Learning Institute (DLI).\nCourse Description\nThis cours
 e teaches GPU acceleration of C++ applications using CUDA\, with an emphas
 is on modern C++ idioms rather than low-level GPU APIs. Starting from libr
 ary-provided parallel algorithms that execute transparently on the GPU\, i
 t progresses through custom CUDA kernels\, thread hierarchies\, shared mem
 ory\, and concurrent streams - covering the full range from high-level abs
 tractions to fine-grained GPU control. No prior CUDA or GPU programming ex
 perience is required.\nFurther information about this tutorial can be foun
 d on the NVIDIA DLI course page.\nPrerequisites\nKnowledge\n\nC++ programm
 ing experience\, including lambda expressions and standard library algorit
 hms\n\nTechnical\n\nA free NVIDIA developer account\nA local installation 
 of NVIDIA Nsight Systems is recommended\n\nCourse Structure\n\nGPU program
 ming fundamentals: writing and launching CUDA-accelerated C++ code\; apply
 ing parallel algorithms on the GPU\nConcurrency and profiling: CUDA stream
 s\, asynchronous data transfers\, and code analysis with NVIDIA Nsight Sys
 tems\nCustom kernel development: thread hierarchies\, shared memory\, and 
 cooperative parallel algorithms\n\nLearning Outcomes\nAfter completing thi
 s course\, you will be able to:\n\nAccelerate C++ applications by writing\
 , compiling\, and running GPU code with CUDA\nApply parallel algorithms to
  GPU workloads without writing custom kernels\nManage CPU-GPU data movemen
 t and optimize memory access patterns\nWrite custom CUDA kernels and manag
 e thread hierarchies and shared memory\nOverlap computation with data tran
 sfers using concurrent CUDA streams\nProfile GPU code and identify perform
 ance bottlenecks with NVIDIA Nsight Systems\n\nRegistration\, Wait List an
 d Withdrawal Policy\nRegistration\nPlease register at the bottom of this p
 age. Registration is open until a few days before the course starts\, or u
 ntil the course is fully booked.\nPrices and Eligibility\nFree for partici
 pants affiliated with academic institutions in EU member states and Horizo
 n 2020-associated countries\nWait List\nEmail nhr-training@fau.de with nam
 e and university affiliation\nWithdrawal Policy\nWithdraw through the regi
 stration system or email nhr-training@fau.de. No-shows will be excluded fr
 om future events.\nIf you need to withdraw your registration\, please eith
 er cancel it directly through the registration system or send an email to 
 nhr-training@fau.de.\nAdditional Courses\nYou can find an up-to-date list 
 of all courses offered by NHR@FAU at https://hpc.fau.de/teaching/tutorials
 -and-courses/.\n\nhttps://indico.ecap.work/event/211/
LOCATION:Online
URL:https://indico.ecap.work/event/211/
END:VEVENT
END:VCALENDAR