[Bug 34156] r600g performance regression between 780c183b and 862ebb41

bugzilla-daemon at freedesktop.org bugzilla-daemon at freedesktop.org
Tue Mar 1 23:29:39 PST 2011


--- Comment #7 from Henri Verbeet <hverbeet at gmail.com> 2011-03-01 23:29:39 PST ---
I'm seeing some performance impact from 077c448d, mostly due to the extra calls
to evergreen_context_pipe_state_set_vs_resource() /
evergreen_context_pipe_state_set_ps_resource(). The earlier commits don't seem
to make much of a difference for me. (And I'd be surprised if they did, that
code is only called during shader compilation.) As for the issue with 077c448d,
constant buffer updates happen a lot, and that commit made them more expensive,
so that makes some sense. On the other hand, it seems to me that this also
implies state updates being disproportionately expensive. That would make it a
general problem with the r600 winsys.

Configure bugmail: https://bugs.freedesktop.org/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are the assignee for the bug.

More information about the dri-devel mailing list