Currently the findmin/findmax functions in CUDA are defined for cases where one passes in them only a single CuArray (link), e.g. findmin(a)
. However, findmin/findmax functions in Base allow to pass in them an additional function as the first argument, e.g. findmin(abs2, a)
.
Would it be hard to extend the existing definitions of CUDA findmin/findmax functions to match the functionality of Base?