Consider maximizing grid utilization

[maleadt]

We currently maximize block utilization (taking the max threads), which may leave SMs underutilized. We should consider first selecting an optimal amount of blocks, before maximizing the thread could:

    config = launch_configuration(kernel.fun)
    threads = min(length(ps), config.threads)
    # XXX: this kernel performs much better with all blocks active
    blocks = max(cld(length(ps), threads), config.blocks)
    threads = cld(length(ps), blocks)

I'm sure this will lead to some kernels performing worse, though, but it's probably a good thing to test.

[maleadt]

Attempt in JuliaGPU/GPUArrays.jl#389