Re: [MIT-Scheme-devel] Symmetric MultiProcessing

[Matt Birkholz]

> From: Taylor R Campbell <address@hidden>
> Date: Tue, 18 Aug 2015 22:39:22 +0000
> 
> [...] or prove that the memory barriers are not necessary for other
> reasons.

I thought we were all cool with assuming word-sized memory coherency.
Doesn't the x86-64 architecture guarantee that a word like constant-
space-queue will be written atomically?

> I'm also a little puzzled about the queue scheme.  It seems like now
> we waste constant space for all the pairs that were used only for the
> purpose of queueing objects to be purified.

Yes, you puzzled that one out.  I traded a few pairs for a straight-
forward implementation.  You would prefer that the queue not be
purified during a GC interrupt?  Only by explicit application of
flush-purification-queue!?  I'm cool with that.