Help is very welcome for any of the below:

• Automated optimisation / tuning of the algorithms' settings, e.g. block_size, per device; the measured values would go into each backend's tunings, from which Auto chooses.

  • Maybe something like:

  AK.@tune begin    reduce(f, src; init=init,           alg=AK.BlockReduce(block_size=$block_size, switch_below=$switch_below))    block_size=(64, 128, 256, 512, 1024)    switch_below=(1, 10, 100, 1000, 10000)end

• Run the benchmark suite in CI to catch performance regressions.

• Other ideas? Post an issue, or open a discussion on the Julia Discourse.