On Thu, Nov 9, 2017 at 12:27 PM, Jan Vesely <jan.ves...@rutgers.edu> wrote: > On Thu, 2017-11-09 at 03:58 +0100, srol...@vmware.com wrote: >> From: Roland Scheidegger <srol...@vmware.com> >> >> r600 used the clamped version for rcp, whereas both evergreen and cayman >> used the ieee version. I don't know why that discrepancy exists (it does so >> since day 1) but there does not seem to be a valid reason for this, so make >> it consistent. This seems now safer than before the previous commit (using >> the mystery dx10 clamp). >> Note that rsq still uses clamped version (as before even though the table >> may have suggested otherwise for evergreen) for r600/eg, but not for cayman. > > just layman's opinion here. Does TGSI not mandate specific behaviour > wrt nans and infinities for this OP? > >> I just don't feel lucky enough to change this (it should also be noted r600 >> supports sqrt natively, which is always ieee, therefore might not really see >> rsqrt with glsl often presumably). > > why would that be? isn't RECIPSQRT_IEEE(x) still optimization over > RECIP_IEEE(SQRT(x))?
More like the other way... SQRT is an opt of 1/RSQ. Traditionally GPUs haven't had SQRT ops. NVIDIA still doesn't have one. Shader code tends to be written with that knowledge in mind. -ilia _______________________________________________ mesa-dev mailing list mesa-dev@lists.freedesktop.org https://lists.freedesktop.org/mailman/listinfo/mesa-dev
