[gambit-list] Memory ordering considerations in Gambit SMP?

Adam adam.mlmb at gmail.com
Sat Nov 11 17:13:57 EST 2017


Dear Marc,

Are there any constraints on what underlying hardware platform SMP Gambit
can work on, e.g. architectures with strong memory ordering (AMD64) versus
architectures with weak memory ordering (ARM64)?

Does Gambit export any memory barrier primitive?

Do any particular Gambit primitives imply a memory barrier, so these are
abstracted away from the user?

E.g. (thread-send! t (list 1 2 3)) would imply a memory barrier on weakly
ordered systems, if t is being executed on another OS thread, so that when
the message is received on the other side, Gambit has automatically ensured
that the structure is actually accessible on the receiving end?

(https://en.wikipedia.org/wiki/Memory_ordering#Runtime_memory_ordering)

Will appreciate a lot to understand how to manage this.

Thanks!
Adam
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.iro.umontreal.ca/pipermail/gambit-list/attachments/20171112/31143880/attachment.htm>


More information about the Gambit-list mailing list