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

[bugzilla-daemon at freedesktop.org]

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

--- Comment #3 from Eero Tamminen <eero.t.tamminen at intel.com> ---
(In reply to Mark Janes from comment #2)
> more precise bisection:
...
> intel/nir: Call nir_lower_io_to_scalar_early

Thanks!  Does this explain also the performance drops in other tests?

GfxBench Tessellation test is tessellation shader bound, SynMark GSCloth is
transform feedback / streamout / geometry shader test, GpuTest Julia FP64 is
fragment shader ALU test, GfxBench ALU2 is ALU & texture access scheduling test
and Heaven is bound by overall fragment shader perf.


PS. any idea about whether something is going to be done about regression bug
107223, which seems to cause E2E RBC getting disabled in several tests.

-- 
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/20180808/ba374042/attachment-0001.html>