[Libre-soc-dev] SV whitepaper

lkcl luke.leighton at gmail.com
Sat May 7 20:58:03 BST 2022


https://libre-soc.org/openpower/sv/SimpleV_rationale/?updated

i figured it was time to do not just a comparative analysis and rationale of SimpleV but also to document the next advancements, where things can go next.

for example by adding ZOLC as a first priority for 3D, Texture image XY scaling can be done as a Memory-driven (Snitch-like) deterministic schedule either through one massive instruction (Horizontal-First) or several smaller ones

OR... and this is cool...

by having Extra-V-like coordinated pushing of the Texture Instructions *down to the memory* there would be no need for a L1 Texture Cache *at all*.  ZOLC Deterministic Schedules would send coordinated OpenCAPI requests down to the actual Memory ICs, and give them a fragment of code to execute that would *also* include OpenCAPI requests for data that the *Memory* IC needed.

thoughts appreciated because this is an absolutely mental concept that starts to go waaay down the rabbithole.

l.


More information about the Libre-soc-dev mailing list