It depends, if the optimization is too hardware-dependent it might hurt/regress performance on other platforms. One would have to find ways to generalize and auto-tune it based on known features of the local hardware architecture.
Yes, easiest is to separate it into a set of options. Then have a bunch of Json/yaml files, one for each hw configuration. From there, the community can fiddle with the settings and share new settings if new hardware is released.
Yes, easiest is to separate it into a set of options. Then have a bunch of Json/yaml files, one for each hw configuration. From there, the community can fiddle with the settings and share new settings if new hardware is released.