[Caice-csse] NVIDIA Workshop: Accelerated Computing with cuPyNumeric

[N Narayanan]

This workshop may be of interest to several of our faculty and graduate students - Hari






NVIDIA Workshop: Accelerated Computing with cuPyNumeric



Data & time: Monday, June 23,  2025, 1:00 P.M. - 3:00 P.M.
Venue: Virtual on Zoom
Fee: Free
Registration: Register here!<https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fdocs.google.com%2Fforms%2Fd%2Fe%2F1FAIpQLSeXBQb__HPqr6p9E2FJv0CpbNvEzo_By6f7Ixi2TKpQAI3Zqg%2Fviewform%3Fusp%3Dheader&data=05%7C02%7Ccaice-csse%40eng.auburn.edu%7C7fdae7ef86fb416d869a08dda5332086%7Cccb6deedbd294b388979d72780f62d3b%7C0%7C0%7C638848361194557772%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&sdata=d0Ff7RVOiv5DarIGFtun2Wy2JeGNhRsPIhPtBWkiFro%3D&reserved=0>

Registration Deadline: June 9th, 2025



This workshop will give an introduction to cuPyNumeric and wider Legate ecosystem. We will begin with an introduction to High Performance Computing (HPC) workflows, discuss the complexity of scaling multi-GPU and multi-node applications, introduce the Legate<https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fdeveloper.nvidia.com%2Flegate&data=05%7C02%7Ccaice-csse%40eng.auburn.edu%7C7fdae7ef86fb416d869a08dda5332086%7Cccb6deedbd294b388979d72780f62d3b%7C0%7C0%7C638848361194590141%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&sdata=bZcRlQf%2BJNOTTOhTmyaHBJ8ASjGX76xmVrephwTaBFI%3D&reserved=0> ecosystem and discuss the Legate runtime stack, touch on profiling with cuPyNumeric<https://nam11.safelinks.protection.outlook.com/?url=https%3A%2F%2Fdeveloper.nvidia.com%2Fcupynumeric&data=05%7C02%7Ccaice-csse%40eng.auburn.edu%7C7fdae7ef86fb416d869a08dda5332086%7Cccb6deedbd294b388979d72780f62d3b%7C0%7C0%7C638848361194607571%7CUnknown%7CTWFpbGZsb3d8eyJFbXB0eU1hcGkiOnRydWUsIlYiOiIwLjAuMDAwMCIsIlAiOiJXaW4zMiIsIkFOIjoiTWFpbCIsIldUIjoyfQ%3D%3D%7C0%7C%7C%7C&sdata=nFukslz9Pyt317vuoMAkl4oqBFGAXA%2FCGojGiCxSWMM%3D&reserved=0>, and finally end by walking through several interactive examples.



Learning Objective: Learn how to build a HPC workflow and how to use cuPyNumeric to scale to multi-GPU and multi-node applications.



Prerequisites: Beginner level Python



Any questions, please contact UFIT Research Computing's AI and RSE Manager Ying Zhang at yingz at ufl.edu<mailto:yingz at ufl.edu>


-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.eng.auburn.edu/pipermail/caice-csse/attachments/20250606/eb6126f3/attachment.htm>