A continuation of the series under review to show the current path to load balancing. After the HWSP timeline reworking, we have the removal of global seqno, and then the patches to construct a virtual engine with load balancing across the equivalent siblings. Wrt veng, the changes since last time all centre around improving the uapi to remove more implicit choices baked into the kernel and some bugfixes that came and went thanks due to per-context seqno. -Chris
_______________________________________________ Intel-gfx mailing list Intel-gfx@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/intel-gfx
