[Bug 91788] [HSW Regression] Synmark2_v6 Multithread performance case FPS reduced by 36%

bugzilla-daemon at freedesktop.org bugzilla-daemon at freedesktop.org
Sat Aug 29 01:40:54 PDT 2015


https://bugs.freedesktop.org/show_bug.cgi?id=91788

Matt Turner <mattst88 at gmail.com> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |currojerez at riseup.net

--- Comment #2 from Matt Turner <mattst88 at gmail.com> ---
I'm bisecting it to

commit 3569742ec458c0a881857d9deb782c1e11f195d8
Author: Francisco Jerez <currojerez at riseup.net>
Date:   Fri Nov 22 16:00:33 2013 -0800

    i965: Define implementation constants for ARB_shader_image_load_store.

    Reviewed-by: Paul Berry <stereotype441 at gmail.com>

    v2: Drop VS support pre-Gen8, drop GS support.

    Reviewed-by: Kenneth Graunke <kenneth at whitecape.org>

Specifically, commenting out the assignment of ctx->Const.MaxImageUnits brings
performance back to previous levels.

Running strings on synmark indeed shows "GL_ARB_shader_image_load_store", so
the benchmark may be doing additional work with the extension enabled.

-- 
You are receiving this mail because:
You are the QA Contact for the bug.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.freedesktop.org/archives/intel-3d-bugs/attachments/20150829/57506f47/attachment.html>


More information about the intel-3d-bugs mailing list