All - I'm trying to clean up the MX situation in 1.7 with regards to the fake mpool and have some questions. It looks like the point of the fake mpool is to translate a memory hook release into a free call in some other library. My question is why we're using the mpool to do that. Since opal allows multiple registrations to the alloc/release hooks, it would appear that one could just register another handler and bypass the mpool infrastructure altogether. Can anyone comment on this?
Thanks, Brian -- Brian W. Barrett Scalable System Software Group Sandia National Laboratories