Re: [OMPI devel] MPI_Info args to spawn - resolving deprecated values?

2020-04-08 Thread George Bosilca via devel
Deprecate, warn and convert seems reasonable. But for how long ? As the number of automatic conversions OMPI supports has shown a tendency to increase, and as these conversions happen all over the code base, we might want to setup a well defined path to deprecation, what and when has been deprecat

Re: [OMPI devel] MPI_Info args to spawn - resolving deprecated values?

2020-04-08 Thread Jeff Squyres (jsquyres) via devel
On Apr 8, 2020, at 9:51 AM, Ralph Castain via devel wrote: > > We have deprecated a number of cmd line options (e.g., bynode, npernode, > npersocket) - what do we want to do about their MPI_Info equivalents when > calling comm_spawn? > > Do I silently convert them? Should we output a deprecat

[OMPI devel] MPI_Info args to spawn - resolving deprecated values?

2020-04-08 Thread Ralph Castain via devel
We have deprecated a number of cmd line options (e.g., bynode, npernode, npersocket) - what do we want to do about their MPI_Info equivalents when calling comm_spawn? Do I silently convert them? Should we output a deprecation warning? Return an error? Ralph

Re: [OMPI devel] --mca coll choices

2020-04-08 Thread Luis Cebamanos via devel
Thanks George, I'll try to search for those examples through the mailing list messages. I suspect it is not going to be easy to find them though. Regards, Luis On 07/04/2020 22:29, George Bosilca via devel wrote: All the collective decisions are done on the first collective on each communica