> 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
