On Thu, Jun 22, 2017 at 12:25 PM, Timothy Arceri <tarc...@itsqueeze.com> wrote: > On 22/06/17 18:46, Samuel Pitoiset wrote: >> >> Here's a shader-db report: >> >> https://pastebin.com/raw/QBMnF2pv >> >> This doesn't sound like a total win actually... > > > I'm surprised to see this. I thought we pretty much unrolled everything > already, although maybe that was what happened after NIR unrolling. > > I've done a full shader-db run and I'm getting very different results from > you: > > https://pastebin.com/XRH7Vbvv > > There are still a little mixed but they look much more positive.
The problem with our shader-db stats is that they have very little to do with performance changes. The code size increase is expected. Ignore register usage, instead, look at max waves. SGPR spilling is cheap - measurements can be done to see whether it's measurable. Marek _______________________________________________ mesa-dev mailing list mesa-dev@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/mesa-dev
