From: Matthew Wilcox > Sent: 27 August 2020 13:31 > On Thu, Aug 27, 2020 at 06:19:44PM +0800, Shaokun Zhang wrote: > > From: Yuqi Jin <jinyuqi@xxxxxxxxxx> > > > > It is well known that the performance of atomic_add is better than that of > > atomic_cmpxchg. > > I don't think that's well-known at all. Especially since on (probably) every architecture except x86 atomic_add() is implemented using atomic_cmpxchg(). David - Registered Address Lakeside, Bramley Road, Mount Farm, Milton Keynes, MK1 1PT, UK Registration No: 1397386 (Wales)
