From Kenneth Duda <A HREF="http://www-dsg.stanford.edu/KennethDuda.html"
  >homepage</a>, one of the authors:

<cite>The Cache Kernel is the privileged-mode portion of V++, a scalable multiprocessor *(OS). The Cache Kernel does not attempt to manage all system _(object)s, but rather serves as a cache of active _(object)s. It is up to _(user)-mode application _(kernel)s to serve as backing store for these _(object)s.</cite>

See the paper:
<p>
D.R. Cheriton and K.J. Duda.  A caching model of operating system kernel functionality.  In <i>Proceedings of the First Symposium on Operating System Design and Implementation.</i> USENIX, November, 1994.
<a href="ftp://ftp.dsg.stanford.edu/pub/papers/cachekernel/main.html">Hypertext</a> or <a href="ftp://ftp.dsg.stanford.edu/pub/papers/cachekernel.ps.Z">compressed PostScript</a>
or the <a href="ftp://ftp.dsg.stanford.edu/pub/papers/cachekernel.abstract">abstract</a>.  Slides from the OSDI 94 presentation, <a
href="papers/cachekernel/OSDI-slides.ps">PostScript</a>
</p>
