Parallel NN layer

parallel.py

# PARALLEL:
from contractpool import ContractPool  # imaginary 'contractpool' library, similar to python's `multiprocessing`

W = parameter(M, N)

def forward(x_: float32[N]) -> float32:
    # matrix-vector multiplication:
    zs = float32[M]  # let's imagine we have a float32 dtype in Vyper
    with ContractPool(dot, M) as p:
        p.map(W, x_, out=zs)  # launches M subcontracts asynchronously, each subcontract writes values to zs
        p.sync()  # stop main contract execution here until all subcontracts have finished writing to `zs`, then continue

    # summation:
    y = sum(zs)  # scalar

    return y