On 9/26/18 8:33 PM, Cesar Philippidis wrote: > This patch adds nvptx support for the atomic FETCH_AND_OP functions. I > recall that this used to be important for OpenACC reductions back in the > GCC 5.0 days before Nathan split reductions into four phases. Nowadays, > atomic reductions use a spin lock that's implemented directly by the > nvptx BE. Therefore, I'm not sure if the nvptx port still needs support > for atomic fetch_and_*. > > Tom and Thomas, do either of you have any thoughts on this? Should I > commit it to trunk?
I'd say no. I can think of only one possible use for this, which is to be able use -fno-inline-atomics to workaround problems in atomics in ptx, and I think that that's not sufficiently valuable to start maintaining these routines in trunk. Thanks, - Tom > I bootstrapped and regtested it for x86_64 Linux > with nvptx offloading.
