Hi,
On 12.05.2016 11:05, Kenneth Graunke wrote:
On Thursday, May 12, 2016 11:15:58 AM PDT Eero Tamminen wrote:
The known cases where this workaround caused slowdown were fixed, so
why not just unconditionally enable it?
Or is there still some case where workaround causes a measurable slowdown?
I mean, it still makes sin/cos instructions twice as slow unless the
sin/cos happens to be multiplied by a constant. So that's still fairly
unfortunate.
Multiply is faster instruction than sin/cos, and depending on what else
the shader does, good scheduler may be able to hide latency of
additional multiply, so I don't think it's quite that bad. :-)
Though, if there's really nothing hurt by this, then it might be
reasonable.
- Eero
_______________________________________________
mesa-dev mailing list
mesa-dev@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/mesa-dev
