i965/fs: add a comment about how the rounding mode in fmul is set
authorAndres Gomez <agomez@igalia.com>
Mon, 23 Sep 2019 22:16:11 +0000 (01:16 +0300)
committerAndres Gomez <agomez@igalia.com>
Tue, 24 Sep 2019 08:24:15 +0000 (11:24 +0300)
commit6f1468c371c7ceebf4d70933d60f70ef119fedcc
treebe8c78e5c6b7ecb56aa63686dea45182ebc278ef
parentb3c25e6f9953b6c7d196b47c6ba1987f681edf7d
i965/fs: add a comment about how the rounding mode in fmul is set

After
1711bf6cf2d ("intel/fs: Generate better code for fsign multiplied by a value"),
the conflicts resolution for setting the rounding mode after the
fused fmul and fsign optimization is non obvious.

Basically, the optimization doesn't really result in a MUL, or any
other operation which would need to have the rounding mode set. Hence,
we set it just before the actual MUL in the treatment of fmul.

Fixes: ba1e25e1aa6 ("i965/fs: set rounding mode when emitting fadd, fmul and ffma instructions")
Suggested-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Signed-off-by: Andres Gomez <agomez@igalia.com>
Reviewed-by: Caio Marcelo de Oliveira Filho <caio.oliveira@intel.com>
Reviewed-by: Samuel Iglesias Gonsálvez <siglesias@igalia.com>
src/intel/compiler/brw_fs_nir.cpp