[Bug 107510] [GEN8+] up to 10% perf drop on several 3D benchmarks

bugzilla-daemon at freedesktop.org bugzilla-daemon at freedesktop.org
Tue Aug 7 11:42:34 UTC 2018


https://bugs.freedesktop.org/show_bug.cgi?id=107510

            Bug ID: 107510
           Summary: [GEN8+] up to 10% perf drop on several 3D benchmarks
           Product: Mesa
           Version: git
          Hardware: Other
                OS: All
            Status: NEW
          Keywords: regression
          Severity: normal
          Priority: medium
         Component: Drivers/DRI/i965
          Assignee: intel-3d-bugs at lists.freedesktop.org
          Reporter: eero.t.tamminen at intel.com
        QA Contact: intel-3d-bugs at lists.freedesktop.org

There's up to 10% performance drop on *all* GEN8+ platforms.

On SKL GT2, the regressions are following:
- 10% GfxBench Tessellation (onscreen & offscreen)
- 5% SynMark2 GSCloth
- 2-3% GpuTest Julia FP64
- 1-2% Unigine Heaven (high quality with tessellation, no AA)
- 1% GfxBench ALU2 (onscreen & offscreen), SynMark PSPom

On other GEN8+ platforms the regressing cases are the same, but percentages
differ somewhat.  Performance didn't improve in any test.

Setup:
- Mesa from git
- drm-tip kernel and X server git versions within couple of months
- Modifier support enabled (shouldn't matter as offscreen versions also
regress)

Regressions happen between following Mesa git versions:
0ea243dcd502e18fde160179faf90639fb012288 2018-07-30 16:31:05 freedreno/a5xx:
fix txf_ms
d5175d21c7e8e205a1ea80644b3cc887a586e6e1 2018-08-02 23:30:57 nir: add fall
through comment to nir_gather_info

Between these there are a lot of commits that could potentially affect
performance, but I don't currently have time to bisect this (maybe next week). 
I filed this in hopes that somebody else would have...

-- 
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/20180807/93a9b767/attachment-0001.html>


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