[Mesa-dev] [PATCH 07/12] nir: Don't use ffma in nir_lower_wpos_ytransform().

Kenneth Graunke kenneth at whitecape.org
Thu May 19 06:55:03 UTC 2016


On Thursday, May 19, 2016 8:39:45 AM PDT Michael Schellenberger Costa wrote:
> Hi Kenneth,
> 
> Am 19.05.2016 um 00:00 schrieb Kenneth Graunke:
> > ffma is an explicitly fused multiply add with higher precision.
> > The optimizer will take care of promoting mul/add to fma when
> > it's beneficial to do so.
> > 
> > This fixes failures on Gen4-5 when using this pass, as those platforms
> > don't actually implement fma().
> I assume here you mean ffma()?
> --Michael

Either, really - fma() is the GLSL built-in function for fused
multiply-adds, which corresponds to the NIR opcode 'ffma', and
the i965 opcode 'mad'.

--Ken
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 819 bytes
Desc: This is a digitally signed message part.
URL: <https://lists.freedesktop.org/archives/mesa-dev/attachments/20160518/878a3f29/attachment.sig>


More information about the mesa-dev mailing list