> The original code before Phoebe's patch almost gets that right, but is a
> little too conservative in the baremetal cases on both M-class cpus and non
> M-class cpus.

It looks like the overwhelming majority of platforms *do* use the
standard ldrex/strex loops, so I think we should be changing the
default: let any platform with a weird kernel opt itself out of inline
atomics.

Cheers.

Tim.
_______________________________________________
cfe-commits mailing list
[email protected]
http://lists.cs.uiuc.edu/mailman/listinfo/cfe-commits

Reply via email to