map!(
    f, dst::AbstractArray, src::AbstractArray, backend::Backend=get_backend(src);

    # CPU settings
    scheduler=:threads,
    max_tasks=Threads.nthreads(),
    min_elems=1,

    # GPU settings
    block_size=256,
)

Apply the function f to each element of src in parallel and store the result in dst. The CPU and GPU settings are the same as for foreachindex.

Examples

import Metal
import AcceleratedKernels as AK

x = MtlArray(rand(Float32, 100_000))
y = similar(x)
AK.map!(y, x) do x_elem
    T = typeof(x_elem)
    T(2) * x_elem + T(1)
end

map(
    f, src::AbstractArray, backend::Backend=get_backend(src);

    # CPU settings
    scheduler=:threads,
    max_tasks=Threads.nthreads(),
    min_elems=1,

    # GPU settings
    block_size=256,    
)

Apply the function f to each element of src and store the results in a copy of src (if f changes the eltype, allocate dst separately and call map!). The CPU and GPU settings are the same as for foreachindex.