BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//pretalx//pretalx.com//pyconhk2024//talk//UGFV3S
BEGIN:VTIMEZONE
TZID:HKT
BEGIN:STANDARD
DTSTART:20000101T000000
RRULE:FREQ=YEARLY;BYMONTH=1
TZNAME:HKT
TZOFFSETFROM:+0800
TZOFFSETTO:+0800
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
UID:pretalx-pyconhk2024-UGFV3S@pretalx.com
DTSTART;TZID=HKT:20241116T140000
DTEND;TZID=HKT:20241116T143000
DESCRIPTION:- Numba is a popular JIT compiler that translates Python code i
 nto optimized machine code for various hardware targets\, and Numba-CUDA s
 upports compilation of Python code for execution on NVIDIA devices. Whilst
  Numba-CUDA provides many basic accelerated programming function blocks ou
 t of the box\, manually creating bindings for a CUDA device library is sti
 ll laborious. \n- Numbast is an auto device binding generation tool create
 d by NVIDIA. Numbast provides an end-to-end binding generation mechanism t
 hat quickly bridges the gap between the CUDA ecosystem and Python CUDA.\n-
  In this talk\, attendees will learn about recent progress of accelerated 
 computing in Python with Numba-CUDA\, the internal mechanisms of Numbast\,
  and get hands-on experience of crafting CUDA kernels in Numba-CUDA\, as w
 ell as creating bindings with Numbast.\n- Additionally\, we will provide a
 n insight into how Numba is used across RAPIDS\, Nvidia’s accelerated co
 mputing solution that focuses on making accelerated computing more accessi
 ble to the general python community. Time permitting\, we will also introd
 uce how user-defined functions (UDF) are used in `cudf.pandas`.
DTSTAMP:20260515T235226Z
LOCATION:LT8
SUMMARY:Numbast: Bridging the gap between CUDA C++ and Python - Michael Wan
 g
URL:https://pretalx.com/pyconhk2024/talk/UGFV3S/
END:VEVENT
END:VCALENDAR