On 07.02.2022 18:06, Andrew Cooper wrote: > On 07/02/2022 08:11, Jan Beulich wrote: >> (And of >> course I still have that conversion to POPCNT alternatives patching pending, >> where Roger did ask for some re-work in reply to v2, but where it has >> remained unclear whether investing time into that wouldn't be in vein, >> considering some of your replies on v1. Thus would have further shrunk the >> difference, without me meaning to say the change here isn't a good one.) > > There is a perfectly clear and simple way forward. It's the one which > doesn't fight the optimiser and actively regress the code generation in > the calling functions, and add an unreasonable quantity technical debt > into the marginal paths. > > I will ack a version where you're not adding complexity for negative gains.
Thanks, at least some form of a reply. I'm afraid I can't really translate this to which parts of the change you'd be okay with and which parts need changing. I didn't think I would "fight the optimiser and actively regress the code generation in the calling functions" in v2 (this may have been different in v1, but I haven't gone back to check; I wonder though whether you're mixing this with e.g. the BMI patching series I've long given up on). Jan
