[petsc-dev] Implementing longer pipelines with VecDotBegin and VecDotEnd

[Jed Brown]

Barry Smith <bsmith at mcs.anl.gov> writes:
>> VecNormBegin(X,&norm);
>> function(X,&norm);
>> VecNormEnd(X,&norm);
>
> and function() used split reduction with the &norm argument it would get a false match so yes your request argument would be required. But we could eliminate that possibly by checking for each new begin if its arguments exactly match an outstanding begin and erroring in that case. Thus eliminating the need for the publicly visible request? Does this still support all "reasonable" use cases?

Yeah, I think this would be sufficient.
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 832 bytes
Desc: not available
URL: <http://lists.mcs.anl.gov/pipermail/petsc-dev/attachments/20170325/82767f40/attachment.sig>