[Bug 97035] [regression] WebGL demo iamnop.com/particles is very slow and spends far too long compiling shaders

bugzilla-daemon at freedesktop.org bugzilla-daemon at freedesktop.org
Mon Sep 5 07:51:52 UTC 2016


Comment # 8 <https://bugs.freedesktop.org/show_bug.cgi?id=97035#c8>  on bug 97035 <https://bugs.freedesktop.org/show_bug.cgi?id=97035>  from  <mailto:eero.t.tamminen at intel.com> Eero Tamminen 
Had some troubles at first with ezBench, but finally it bisected this.



As expected, the same commit caused 5x increase in compilation speed and even

larger drop in performance.  This was the commit:

-----------------------------

commit 5886cd79a0ed10b887840f6afb980a5a6a47e26e

Author:     Kenneth Graunke <kenneth at whitecape.org <mailto:kenneth at whitecape.org> >

AuthorDate: Wed Apr 6 22:34:39 2016 -0700

Commit:     Kenneth Graunke <kenneth at whitecape.org <mailto:kenneth at whitecape.org> >

CommitDate: Mon Apr 11 18:43:55 2016 -0700



    nir: Do basic constant reassociation.



    Many shaders contain expression trees of the form:



        const_1 * (value * const_2)



    Reorganizing these to



        (const_1 * const_2) * value



    will allow constant folding to combine the constants.  Sometimes, these

    constants are 2 and 0.5, so we can remove a multiply altogether.  Other

    times, it can create more immediate constants, which can actually hurt.



    Finding a good balance here is tricky.  While much more could be done,

    this simple patch seems to have a lot of positive benefit while having

    a low downside.

-----------------------------



According to Pekka, he's seen performance drops with above commit also with

other test(s).



For the almost identical, but slightly smaller shader attached here, there was

no perf regression.



(Matt's later "Drop -fno-strict-aliasing" commit improved compilation speed

slightly.)

  _____  

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/20160905/e2bd2fad/attachment-0002.html>
-------------- next part --------------
An embedded and charset-unspecified text was scrubbed...
Name: ATT00001.txt
URL: <https://lists.freedesktop.org/archives/intel-3d-bugs/attachments/20160905/e2bd2fad/attachment.txt>


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