CUDA with fast-math flags already does this, so it should work for CPU.
Details
Details
Diff Detail
Diff Detail
Event Timeline
Comment Actions
Looks like this patch needs more work... Revoking for now.
@Ronny G (nutel),
approx pow may give a visible bias. All powf function are some kind of approximations, but a good one at least should look like a smooth function (and be precise enough, of course). If you overlay your images in divide mode, you can see this bias. For example, pow vs fastpow, pow vs approxpow.
