Re: [RFC PATCH 0/12] drm/fabric: vendor-neutral topology infrastructure for scale-up accelerator interconnects

From
Austin, Alex (DCCG) <alex.austin@amd.com>
Date
2026-09-22 16:24:14
Also in
dri-devel, linux-doc, linux-kselftest, lkml
Reply to
Konstantin Sinyuk, 2026-08-24
Modern GPUs and AI accelerators are increasingly connected through scale-up
fabrics such as AMD xGMI today and emerging UALink systems [4]. Linux lacks
common, vendor-neutral infrastructure for reporting which accelerators are
directly connected, through which ports, and in what state.

Sorry for jumping in late to this discussion. We have hardware that uses
UALoE (https://www.amd.com/en/products/rackscale-solutions/helios.html).
The suggestion from Jason is sensible: a new subsystem for fabrics and
reuse ethernet stuff from networking subsystem where possible. We would
like to continue discussing this -  Alejandro and I will be attending
Plumbers virtually.

Thanks,

Alex
Thread (33 messages) 33 messages, 7 authors, last reply 2026-09-25
Keyboard shortcuts
hback out one level
jnext message in thread / next series-diff position
kprevious message in thread / previous series-diff position
ldrill in
Escclose help / fold thread tree
?toggle this help