julia> using FoldsCUDA, CUDA, FLoops
julia> using GPUArrays: @allowscalar
julia> xs = CUDA.rand(10^8);
julia> @allowscalar xs[100] = 2;
julia> @allowscalar xs[200] = 2;
julia> @floop CUDAEx() for (x, i) in zip(xs, eachindex(xs))
           @reduce() do (imax = -1; i), (xmax = -Inf32; x)
               if xmax < x
                   xmax = x
                   imax = i
               end
           end
       end
julia> xmax
2.0f0
julia> imax  # the *first* position for the largest value
100

julia> using Transducers, Folds
julia> @allowscalar xs[300] = -0.5;
julia> Folds.reduce(TeeRF(min, max), xs, CUDAEx())
(-0.5f0, 2.0f0)
julia> Folds.reduce(TeeRF(min, max), (2x for x in xs), CUDAEx())  # iterator comprehension works
(-1.0f0, 4.0f0)
julia> Folds.reduce(TeeRF(min, max), Map(x -> 2x)(xs), CUDAEx())  # equivalent, using a transducer
(-1.0f0, 4.0f0)