| commit | 2d2737dcfe60f1e1b601c2c75a2695a544c9a3dc | [log] [tgz] |
|---|---|---|
| author | Jason Ekstrand <jason.ekstrand@intel.com> | Mon Oct 22 16:44:59 2018 -0500 |
| committer | Jason Ekstrand <jason@jlekstrand.net> | Mon Jan 14 19:27:06 2019 +0000 |
| tree | b167db1e8e395512504798f60d56075114358cd4 | |
| parent | 09c3ff01dfd72aa84334fe82cc3319594fc99ac6 [diff] |
nir: Add a bool to float32 lowering pass From @jekstrand's nir-1-bit-bool branch, with improved ior/inot lowering. ior: fmax instead of fadd allows removing the fsat. inot: seq(x, 0) can be better than fsub(1, x). On a2xx, it works better with the scalar instruction set. Reviewed-by: Jonathan Marek <jonathan@marek.ca>