julia> using CUDA

julia> xcpu = rand(3,3)
3×3 Matrix{Float64}:
 0.783023   0.240864   0.854814
 0.0488199  0.0840899  0.600029
 0.190407   0.872661   0.386219

julia> sortperm(xcpu; dims=1)
3×3 Matrix{Int64}:
 2  5  9
 3  4  8
 1  6  7

julia> xgpu = cu(xcpu)
3×3 CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}:
 0.783023   0.240864   0.854814
 0.0488199  0.0840899  0.600029
 0.190407   0.872661   0.386219

julia> sortperm(xgpu; dims=1)
ERROR: MethodError: no method matching bitonic_sort!(::Tuple{CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, CuArray{Int64, 1, CUDA.Mem.DeviceBuffer}}; dims::Int64)

Closest candidates are:
  bitonic_sort!(::Any; by, lt, rev) got unsupported keyword argument "dims"
   @ CUDA ~/.julia/packages/CUDA/tVtYo/src/sorting.jl:850

Stacktrace:
 [1] kwerr(::NamedTuple{(:dims,), Tuple{Int64}}, ::Function, ::Tuple{CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}, CuArray{Int64, 1, CUDA.Mem.DeviceBuffer}})
   @ Base ./error.jl:165
 [2] sortperm!(I::CuArray{Int64, 1, CUDA.Mem.DeviceBuffer}, c::CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}; initialized::Bool, kwargs::Base.Pairs{Symbol, Int64, Tuple{Symbol}, NamedTuple{(:dims,), Tuple{Int64}}})
   @ CUDA ~/.julia/packages/CUDA/tVtYo/src/sorting.jl:984
 [3] sortperm(c::CuArray{Float32, 2, CUDA.Mem.DeviceBuffer}; kwargs::Base.Pairs{Symbol, Int64, Tuple{Symbol}, NamedTuple{(:dims,), Tuple{Int64}}})
   @ CUDA ~/.julia/packages/CUDA/tVtYo/src/sorting.jl:989
 [4] top-level scope
   @ REPL[5]:1
 [5] top-level scope
   @ ~/.julia/packages/CUDA/tVtYo/src/initialization.jl:185