<html> <head> <base href="https://bugs.freedesktop.org/"> </head> <body> <div> <a class="bz_bug_link bz_status_REOPENED " title="REOPENED - [GEN8+] up to 10% perf drop on several 3D benchmarks" href="https://bugs.freedesktop.org/show_bug.cgi?id=107510#c15">Comment # 15</a> on <a class="bz_bug_link bz_status_REOPENED " title="REOPENED - [GEN8+] up to 10% perf drop on several 3D benchmarks" href="https://bugs.freedesktop.org/show_bug.cgi?id=107510">bug 107510</a> from <a class="email" href="mailto:t_arceri@yahoo.com.au" title="Timothy Arceri <t_arceri@yahoo.com.au>"> Timothy Arceri</a> <pre>(In reply to Eero Tamminen from <a href="show_bug.cgi?id=107510#c14">comment #14</a>) > Because exactly same tests were affected both times this perf regression was > introduced to Mesa, I think it's also the cause for the small regressions in > the listed fragment shader bound tests: > - GpuTest v0.7 Julia FP64 > - GfxBench ALU2 > - Unigine Heaven > - SynMark PSPom > > Not just for the larger regressions in the 2 Tessellation & Geometry shader > tests. > > > Of these, PSPom regression was fixed between these commits: > 18cc65edf8: 2018-10-15 17:56:12 i965: Drop assert about number of uniforms > in ARB handling > 322a919a41: 2018-10-16 11:47:55 anv: Implement VK_EXT_pci_bus_info > > (My guess is that "nir: Copy propagation between blocks" commit fixed it.) > > > Timothy's latest patch series: > <a href="https://patchwork.freedesktop.org/series/51642/">https://patchwork.freedesktop.org/series/51642/</a> > > Fixes just the larger tessellation & geometry shader regressions, not the > smaller fragment shader ones (expected as latest version disables the > optimization pass for fragment stage). Splitting and/or vectorising FS inputs seems to case the scheduler to vary wildly. I'm seeing up to +/-50% swings in cycle counts in both directions. I'm not sure what to do about this.</pre> </div> <hr> You are receiving this mail because: <ul> <li>You are the QA Contact for the bug.</li> </ul> </body> </html>