Talk:NVLink

unclear edit and addition from a non-registered user

https://en.wikipedia.org/w/index.php?title=NVLink&diff=807482204&oldid=807382178 - what might the insertion of "(no! 16)" mean? i feel like i dont get it right now. at least not in the present form. shall this be hidden/removed? what else makes sense? --Alexander.stohr (talk) 15:54, 7 August 2019 (UTC)

more sources and publications

• https://www.nvidia.de/object/nvidia-nvlink-technology-mar25-2014-de.html (German language press release)
• https://www.forbes.com/sites/moorinsights/2018/08/24/nvidia-reveals-xavier-soc-details/ "Also, the SOC includes an NVLink port to enable the SOC to access 2 discrete full-fledged Volta GPUs—for the more demanding work such as Level 5 fully autonomous driving."
• http://on-demand.gputechconf.com/gtc/2018/presentation/s8868-cuda-on-xavier-what-is-new.pdf - a few pages do mention Xavier along with NVlink - an emphasize is on the aspect of "cache coherency".
• https://www.anandtech.com/show/13245/hot-chips-2018-nvidia-xavier-soc-live-blog - see notes and image at time 08:10PM EDT

--Alexander.stohr (talk) 16:20, 7 August 2019 (UTC)

PNY spam ?

There is a lot of strange link to pny hardware reseller. Is that spam ?

parallel processing ?

an application of parallel processing for computer graphics, yes or no? should be stated. It says it's succesor of SLI. 89.201.184.8 (talk) 08:06, 26 April 2020 (UTC)

All modern GPUs use parallel processing. —DIYeditor (talk) 00:18, 14 July 2023 (UTC)

Universal parrell black or white what 8s a line. 2601:647:CB01:DDC0:2921:7FDE:CF8D:CDBB (talk) 00:08, 14 July 2023 (UTC)

What? —DIYeditor (talk) 00:18, 14 July 2023 (UTC)