[Bug 109517] [GEN9+] 14-24% perf drop in SynMark2 v7 CSDof

[bugzilla-daemon at freedesktop.org]

https://bugs.freedesktop.org/show_bug.cgi?id=109517

Jason Ekstrand <jason at jlekstrand.net> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |kenneth at whitecape.org,
                   |                            |mattst88 at gmail.com

--- Comment #4 from Jason Ekstrand <jason at jlekstrand.net> ---
Ugh...  I'm not really sure what we should do about this one.  Mark's bisect is
exactly correct.  I've looked at the shaders, and there seems to be two issues:

 1) There's one SIMD8 shader which schedules massively differently for no
apparent reason.

 2) There's a SIMD16 shader which starts spilling way more than it was before

In both cases, I have no idea why it's happening beyond the fact that our
current RA and scheduling has rather random behaviour at times.  Using SENDS
should only ever decrease register pressure and increase RA freedom because it
no longer has to build the message into a single hunk and can just send the two
bits (address and data) separately.

As I said in the commit message I have another (unfortunately not public yet)
customer workload where the opposite happens and using SENDS decreases spilling
and improves performance by 2x.

Ken, Matt, Any thoughts?

-- 
You are receiving this mail because:
You are the QA Contact for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <https://lists.freedesktop.org/archives/intel-3d-bugs/attachments/20190211/73c930a8/attachment-0001.html>