[Mesa-dev] RFC NIR vectorise varyings

Sun Oct 28 01:02:56 UTC 2018

This fixes the regressions in the glxbench tessellation benchmark
[1].

I'm sending as a RFC as there are mixed results with cycles in fs.

Also Intels CI system reports some failures but I cannot reproduce
these locally. Maybe someone can have a closer look at the internal
CI results [2]? 

[1] https://bugs.freedesktop.org/show_bug.cgi?id=107510
[2] https://mesa-ci.01.org/tarceri/builds/970/group/63a9f0ea7bb98050796b649e85481845