Hector Martin

@marcan42 oh gods that is a horrifying ratio of memory reads to arithmetic

@marcan42 I look at https://github.com/marcan/cl-waifu2x/commit/89176cc52b99ea7bdb0b9b71589379f3d751fe95#diff-d2a065162d2048b6908eee284e028eafR24 … and recoil in horror

@marcan42 are those at least in local memory, or are these all global reads... *sob*

@FioraAeterna Global... I've been trying to use local memory to reuse data but everything I try makes it *slower*. *sob*

@FioraAeterna The "kernels" are distinct 3x3 convolutions. So there are 128x128 independent 3x3 kernels, for each in,out pair.

@marcan42 does this mean there's 128^2 coefficients?

@FioraAeterna 3² × 128² coefficients, yes.