[Bug 103258] [GEN9+] Misrendering and 5% performance drop in GfxBench Manhattan 3.0 & CarChase

[bugzilla-daemon at freedesktop.org]

https://bugs.freedesktop.org/show_bug.cgi?id=103258

--- Comment #1 from Eero Tamminen <eero.t.tamminen at intel.com> ---
Martin's ezBench bisected the performance regression to following commit:
------------------------------------------------------
commit ea0d2e98ecb369ab84e78c84709c0930ea8c293a
Author:     Kenneth Graunke <kenneth at whitecape.org>
AuthorDate: Thu Oct 5 20:31:01 2017 -0700
Commit:     Kenneth Graunke <kenneth at whitecape.org>
CommitDate: Tue Oct 10 14:57:04 2017 -0700

    i965: Disable auxiliary buffers when there are self-dependencies.

    Jason and I investigated several OpenGL CTS failures where the tests
    bind the same texture for rendering and texturing, at the same time.
    This has defined results as long as the reads happen before writes,
    or the regions are non-overlapping.  Normally, this just works out.

    However, CCS can cause problems.  If the shader is reading one set of
    pixels, and writing to different pixels that are adjacent, they may end
    up being covered by the same CCS block.  So rendering may be writing a
    CCS block, while the sampler is trying to read it.  Corruption ensues.

    Disabling CCS is unfortunate, but safe.

    Fixes several KHR-GL45.texture_barrier.* subtests.

    Reviewed-by: Nanley Chery <nanley.g.chery at intel.com>
    Reviewed-by: Jason Ekstrand <jason at jlekstrand.net>
------------------------------------------------------

(On SKL GT2, both tests drop ~4%.)

There isn't yet render validation for GfxBench, so bisecting that will take a
bit more work.

-- 
You are receiving this mail because:
You are the assignee for the bug.
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/20171013/e6fbdb77/attachment.html>