BEGIN:VCALENDAR VERSION:2.0 PRODID:icalendar-ruby CALSCALE:GREGORIAN BEGIN:VEVENT DTSTAMP:20260707T223348Z UID:ab75ab46-9cd1-4a60-8c4b-a3d19a648cc9 DTSTART:20190408T070000Z DTEND:20190411T160000Z DESCRIPTION:The registration to this course is now open.\n\nAll PATC Cours es at BSC do not charge fees.\n\nPLEASE BRING YOUR OWN LAPTOP.\n\nLocal We b Page: This course will provide very good introduction to the PUMPS Summ er School run jointly with NVIDIA -also  at Campus Nord\, Barcelona. For further information visit the school website  as this school has attende e selection process.\nYou may also be interested in our Introduction to Op enACC course.\n\nConvener: \nAntonio Peña\, Computer Sciences Senior Re searcher\, Accelerators and Communications for High Performance Computing\ , BSC\n\nObjectives: \n\nThe aim of this course is to provide students wi th knowledge and hands-on experience in developing applications software f or processors with massively parallel computing resources. In general\, we refer to a processor as massively parallel if it has the ability to compl ete more than 64 arithmetic operations per clock cycle. Many commercial of ferings from NVIDIA\, AMD\, and Intel already offer such levels of concurr ency. Effectively programming these processors will require in-depth knowl edge about parallel programming principles\, as well as the parallelism mo dels\, communication models\, and resource limitations of these processors .\n\nAgenda:\n\nDAY 1\n\nSession 1 / 9:00am – 1:00 pm (3:30 h lectures)\ n\nL1 9:00-10:45 The GPU hardware: Many-core Nvidia developments\n\n10:45- 11:15 Coffee break\n\nL2 11:15-13:00 CUDA Programming: Threads\, blocks\, kernels\, grids\n\n13:00-14:00 Lunch break\n\n \n\nSession 2 / 2:00pm – 6:00 pm (3:30 h lectures)\n\nL3 14:00-15:45 CUDA Tools: Compiling\, debug ging\, profiling\, occupancy calculator\n\n15:45-16:15 Coffee break\n\nL4 16:15-18:00 CUDA Examples(1): VectorAdd\, Stencil\, ReverseArray\n\n \n\n DAY 2\n\nSession 3 / 9:00am – 1:00 pm (3:30 h lectures)\n\nL5   9:00-1 0:45 CUDA Examples (2): Matrices Multiply. Assorted optimizations\n\n10:45 -11:15 Coffee break\n\nL6 11:15-13:00 CUDA Examples (3): Dynamic paralleli sm\, Hyper-Q\, unified memory\n\n13:00-14:00 Lunch break\n\n \n\nSession 4 / 2:00pm – 6:00 pm (3:30 h practical)\n\nH1 14:00-15:45 Hands-on Lab 1 \n\n15:45-16:15 Coffee break\n\nH2 16:15-18:00 Hands-on Lab 2\n\n \n\nDAY 3\n\nSession 5 / 9:00am – 1:00 pm (3:30 h lectures)\n\nL7 9:00-10:45 In side Pascal: Multiprocessors\, stacked memory\, NV-link\n\n10:45-11:15 Cof fee break\n\nL8 11:15-13:00 OpenACC and other approaches to GPU computing\ n\n13:00-14:00 Lunch break\n\n \n\nSession 6 / 2:00pm – 6:00 pm (3:30 h practical)\n\nH3 14:00-15:45 Hands-on Lab 3\n\n15:45-16:15 Coffee break\n \nH4 16:15-18:00 Hands-on Lab 4\n\n \n\nDAY 4\n\nSession 7 / 9:00am – 1 :00 pm (3:30 h practical)\n\nH5 9:00-10:45 Hands-on Lab 5\n\n10:45-11:15 C offee break\n\nH6 11:15-13:00 Hands-on Lab 6\n\n13:00-14:00 Lunch break\n\ n \n\nSession 8 / 2:00pm – 6:00 pm (3:30 h practical)\n\nH7 14:00-15:45 Hands-on Lab 7\n\n 15:45-16:15 Coffee break\n\nH8 16:15-18:00 Free Hands -on Lab\n\nEnd of Course\n\nThe target audiences of the course are studen ts who want to develop exciting applications for these processors\, as wel l as those who want to develop programming tools and future implementation s for these processors.\n\nLevel: INTERMEDIATE: for trainees with some the oretical and practical knowledge\; those who finished the beginners course \n\nADVANCED: for trainees able to work independently and requiring guidan ce for solving complex problems\n\nPrerequisites: Basics of C programming and concepts of parallel processing will help\, but are not critical to fo llow the lectures.\nhttps://events.prace-ri.eu/event/768/ SUMMARY:Introduction to CUDA Programming @ BSC URL;VALUE=URI:https://events.prace-ri.eu/event/768/ END:VEVENT END:VCALENDAR