The BSD ring should be able to use the L3$ can run concurrently to the RCS/BCS - i.e. give the concurrency benefits of using the BLT whilst maintain decent cache bandwidth like RCS. The state setup latency should also be less than RCS, but obviously still more than BCS.
Idea from Ben Widawsky.
-- GitLab Migration Automatic Message --
This bug has been migrated to freedesktop.org's GitLab instance and has been closed from further activity.
You can subscribe and participate further through the new bug through this link to our GitLab instance: https://gitlab.freedesktop.org/xorg/driver/xf86-video-intel/issues/16.