d2056ab993
In some cases of flow control, the constant propagation is not able to determine that the source of an instruction must be a constant value. When we still have NIR SSA values, we can easily determine this. Emit the immediate value during code generation to possible avoid spurious loads of constants into registers. I wrote this patch to prevent a couple trivial regressions in vec4 shaders caused by "nir/algebraic: Replace i2b used by bcsel or if-statement with comparison". The final result was quite a bit better than that... No shader-db changes on any Gen8+ platform. v2: Assert that we never get a negation source modifier on Gen8+. Suggested by Ken. This should never happen because we don't normally use vec4 for Gen8+ (requires and environment variable to force it), and there's no code to generate these negations. Still, erring on the side of caution is better. Haswell total instructions in shared programs: 13776218 -> 13764783 (-0.08%) instructions in affected programs: 663931 -> 652496 (-1.72%) helped: 3495 HURT: 1 helped stats (abs) min: 1 max: 30 x̄: 3.28 x̃: 2 helped stats (rel) min: 0.21% max: 10.00% x̄: 1.79% x̃: 1.49% HURT stats (abs) min: 24 max: 24 x̄: 24.00 x̃: 24 HURT stats (rel) min: 12.24% max: 12.24% x̄: 12.24% x̃: 12.24% 95% mean confidence interval for instructions value: -3.39 -3.15 95% mean confidence interval for instructions %-change: -1.84% -1.75% Instructions are helped. total cycles in shared programs: 386818984 -> 386511910 (-0.08%) cycles in affected programs: 20379636 -> 20072562 (-1.51%) helped: 3052 HURT: 476 helped stats (abs) min: 2 max: 12516 x̄: 110.40 x̃: 6 helped stats (rel) min: 0.05% max: 24.68% x̄: 1.58% x̃: 0.69% HURT stats (abs) min: 2 max: 416 x̄: 62.76 x̃: 24 HURT stats (rel) min: 0.10% max: 10.75% x̄: 4.03% x̃: 2.18% 95% mean confidence interval for cycles value: -115.57 -58.51 95% mean confidence interval for cycles %-change: -0.93% -0.73% Cycles are helped. total spills in shared programs: 100482 -> 100480 (<.01%) spills in affected programs: 79 -> 77 (-2.53%) helped: 3 HURT: 1 total fills in shared programs: 96883 -> 96877 (<.01%) fills in affected programs: 85 -> 79 (-7.06%) helped: 4 HURT: 0 Ivy Bridge total instructions in shared programs: 12000562 -> 11990113 (-0.09%) instructions in affected programs: 572581 -> 562132 (-1.82%) helped: 3106 HURT: 0 helped stats (abs) min: 1 max: 30 x̄: 3.36 x̃: 2 helped stats (rel) min: 0.21% max: 10.00% x̄: 1.86% x̃: 1.49% 95% mean confidence interval for instructions value: -3.49 -3.23 95% mean confidence interval for instructions %-change: -1.91% -1.81% Instructions are helped. total cycles in shared programs: 180958504 -> 180664500 (-0.16%) cycles in affected programs: 19991810 -> 19697806 (-1.47%) helped: 2654 HURT: 486 helped stats (abs) min: 2 max: 12516 x̄: 121.61 x̃: 6 helped stats (rel) min: 0.05% max: 20.66% x̄: 1.48% x̃: 0.68% HURT stats (abs) min: 2 max: 396 x̄: 59.18 x̃: 24 HURT stats (rel) min: 0.05% max: 9.62% x̄: 3.82% x̃: 2.16% 95% mean confidence interval for cycles value: -125.62 -61.64 95% mean confidence interval for cycles %-change: -0.76% -0.56% Cycles are helped. Sandy Bridge total instructions in shared programs: 10842336 -> 10835438 (-0.06%) instructions in affected programs: 395340 -> 388442 (-1.74%) helped: 1926 HURT: 0 helped stats (abs) min: 1 max: 22 x̄: 3.58 x̃: 2 helped stats (rel) min: 0.10% max: 9.68% x̄: 1.78% x̃: 1.42% 95% mean confidence interval for instructions value: -3.73 -3.43 95% mean confidence interval for instructions %-change: -1.84% -1.72% Instructions are helped. total cycles in shared programs: 154590074 -> 154569050 (-0.01%) cycles in affected programs: 8159932 -> 8138908 (-0.26%) helped: 1670 HURT: 228 helped stats (abs) min: 2 max: 260 x̄: 18.13 x̃: 6 helped stats (rel) min: 0.02% max: 8.70% x̄: 0.74% x̃: 0.28% HURT stats (abs) min: 2 max: 1798 x̄: 40.58 x̃: 14 HURT stats (rel) min: 0.03% max: 12.97% x̄: 1.04% x̃: 0.31% 95% mean confidence interval for cycles value: -13.51 -8.64 95% mean confidence interval for cycles %-change: -0.60% -0.46% Cycles are helped. Iron Lake and GM45 had similar results. (Iron Lake shown) total instructions in shared programs: 8212357 -> 8206587 (-0.07%) instructions in affected programs: 323664 -> 317894 (-1.78%) helped: 1457 HURT: 0 helped stats (abs) min: 1 max: 12 x̄: 3.96 x̃: 3 helped stats (rel) min: 0.33% max: 11.49% x̄: 1.86% x̃: 1.44% 95% mean confidence interval for instructions value: -4.14 -3.78 95% mean confidence interval for instructions %-change: -1.93% -1.78% Instructions are helped. total cycles in shared programs: 187668016 -> 187657422 (<.01%) cycles in affected programs: 14856234 -> 14845640 (-0.07%) helped: 1372 HURT: 83 helped stats (abs) min: 2 max: 24 x̄: 7.92 x̃: 6 helped stats (rel) min: 0.02% max: 1.14% x̄: 0.12% x̃: 0.08% HURT stats (abs) min: 2 max: 14 x̄: 3.20 x̃: 2 HURT stats (rel) min: 0.03% max: 0.60% x̄: 0.12% x̃: 0.12% 95% mean confidence interval for cycles value: -7.65 -6.91 95% mean confidence interval for cycles %-change: -0.11% -0.10% Cycles are helped. Reviewed-by: Kenneth Graunke <kenneth@whitecape.org>
`Mesa <https://mesa3d.org>`_ - The 3D Graphics Library ====================================================== Source ------ This repository lives at https://gitlab.freedesktop.org/mesa/mesa. Other repositories are likely forks, and code found there is not supported. Build & install --------------- You can find more information in our documentation (`docs/install.html <https://mesa3d.org/install.html>`_), but the recommended way is to use Meson (`docs/meson.html <https://mesa3d.org/meson.html>`_): .. code-block:: sh $ mkdir build $ cd build $ meson .. $ sudo ninja install Support ------- Many Mesa devs hang on IRC; if you're not sure which channel is appropriate, you should ask your question on `Freenode's #dri-devel <irc://chat.freenode.net#dri-devel>`_, someone will redirect you if necessary. Remember that not everyone is in the same timezone as you, so it might take a while before someone qualified sees your question. To figure out who you're talking to, or which nick to ping for your question, check out `Who's Who on IRC <https://dri.freedesktop.org/wiki/WhosWho/>`_. The next best option is to ask your question in an email to the mailing lists: `mesa-dev\@lists.freedesktop.org <https://lists.freedesktop.org/mailman/listinfo/mesa-dev>`_ Bug reports ----------- If you think something isn't working properly, please file a bug report (`docs/bugs.html <https://mesa3d.org/bugs.html>`_). Contributing ------------ Contributions are welcome, and step-by-step instructions can be found in our documentation (`docs/submittingpatches.html <https://mesa3d.org/submittingpatches.html>`_). Note that Mesa uses email mailing-lists for patches submission, review and discussions.