BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//CERN//INDICO//EN
BEGIN:VEVENT
SUMMARY:HPC Training Series - Course 12 "Introduction to Accelerators: GPU
 s / CUDA"
DTSTART;VALUE=DATE-TIME:20250404T070000Z
DTEND;VALUE=DATE-TIME:20250404T120000Z
DTSTAMP;VALUE=DATE-TIME:20260818T114636Z
UID:indico-event-171@events.grnet.gr
DESCRIPTION:\n\nEuroCC@Greece announces the 12th Course of HPC Training Se
 ries  with the subject "Introduction to Accelerators: GPUs / CUDA"\, that 
 will take place online on April 4th\, 2025.  \n\nDate: April 4th\, 2025\
 , at 10:00 EET   \n\nLocation: Online via Zoom \n\nPresentation Languag
 es: Greek\n\nAudience: This course is ideal for individuals interested in 
 learning GPU programming with CUDA. It is suitable for students\, research
 ers\, engineers and programmers.\n\nCourse Description: This course will c
 over topics on GPU architecture\, programming and their advantages for par
 allel computing\, exploring how GPUs accelerate complex computations. It w
 ill provide an overview of major GPU software suites\, with a particular f
 ocus on CUDA. \n\nParticipants will learn the basics of CUDA programming\
 , including memory allocation\, data transfer\, and kernel execution. The 
 course will also explore various optimization techniques to enhance comput
 ational performance on GPUs\, such as the use of shared memory\, memory co
 alescing\, and managing warp divergence. Additionally\, task-based paralle
 lism will be covered\, utilizing streams and events for efficient parallel
  execution. Profiling tools will be introduced to help identify and addres
 s computational bottlenecks. Furthermore\, the course will delve into perf
 ormance optimizations in CUDA\, emphasizing efficient memory usage and exe
 cution patterns. \n\nParticipants will also be introduced to high-perform
 ance libraries for GPUs\, including cuBLAS for dense linear algebra\, cuSP
 ARSE for sparse matrices\, CUDA Graphs for efficient execution management\
 , cuSOLVER for numerical solvers\, cuFFT for fast Fourier transforms\, cuR
 AND for random number generation\, and AmgX for algebraic multigrid method
 s.\n\nLearning Objectives:\n\nBy the end of this course\, participants wil
 l be able to:\n\n\n	\n	Understand the architecture of GPU accelerators and
  the fundamental differences between GPUs and CPUs.\n	\n	\n	Identify major
  GPU software suites available\, with a focus on CUDA.\n	\n	\n	Utilize CUD
 A for basic GPU programming\, including controlling data movement between 
 CPUs and GPUs.\n	\n	\n	Optimize computational kernels for efficient execut
 ion on GPU hardware.\n	\n	\n	Use cuBLAS\, cuSPARSE\, and CUDA Graphs for e
 fficient GPU computation.\n	\n	\n	Apply cuSOLVER\, cuFFT\, cuRAND\, and Am
 gX for specialized tasks.\n	\n\n\nPrerequisites:\n\n\n	\n	Some prior exper
 ience with C/C++ \n	\n	\n	No prior knowledge of CUDA is necessary\n	\n\n\
 n \n\nNote: Please enter your institutional/corporate email when register
 ing.\n\n \n\nhttps://events.grnet.gr/event/171/
LOCATION:
URL:https://events.grnet.gr/event/171/
END:VEVENT
END:VCALENDAR