Author(s):	Dave Airlie
Location	A2
Date	jan Fri 25	Days Raw Files
Start	14:25	First Raw Start	14:01
Duration	0:45:0	Offset	0:23:51
End	15:10	Last Raw End	15:25
Chapters	00:00 0:00:10 0:06:58 0:36:58
Total cuts_time	43 min.

https://2019.linux.conf.au/schedule/presentation/182/
raw-playlist raw-mp4-playlist encoded-files-playlist host public tweet mp4 svg png

assets release.pdf But_Mummy_I_dont_want_to_use_CUDA_Open_source_GPU_compute.json
logs
Admin: episode episode list cut list raw files day marks day marks day image_files

State:	--------- borked edit encode push to queue post richard review 1 email review 2 make public tweet to-miror conf done
Locked:	clear this to unlock
Locked by:	user/process that locked.
Start:	initially scheduled time from master, adjusted to match reality
Duration:	length in hh:mm:ss
Name:	Video Title (shows in video search results)
Emails:	email(s) of the presenter(s)
Released:	Unknown Yes No has someone authorised pubication
Normalise:
Channelcopy:	m=mono, 01=copy left to right, 10=right to left, 00=ignore.
Thumbnail:	filename.png
Description:	CUDA has become the defacto standard for GPU compute in most fields. AI and Machine Learning via projects like tensorflow are all targeting CUDA as their runtime. CUDA however as one major flaw, it's closed source and requires closed source drivers. This talk will explore the current state of non-CUDA compute stacks, concentrating on the OpenCL, SPIR-V and SYCL projects from Khronos, but also touching on Vulkan compute and other possibilities. It will discuss the some possible problems with AMD ROCm and Intel OpenCL drivers from a Linux platform point of view and try to scope out what a vendor-neutral Linux focused compute stack might look like that has maximal code sharing across vendors and doesn't require shipping various vendor forks of LLVM. markdown
Comment:	production notes