<div class="gmail_quote">On Tue, Apr 19, 2011 at 22:44, Ethan Coon <span dir="ltr"><<a href="mailto:ecoon@lanl.gov">ecoon@lanl.gov</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">
<div id=":ct">The short answer -- make the z-size = s. It's not that huge of a hit --<br>
the local arrays are 6*NX*NY*ndofs instead of 5*NX*NY*ndofs.<br></div></blockquote><div><br></div><div>Indeed, though it is potentially about twice as much work because you only have to evaluate residuals on the owned nodes.</div>
<div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;"><div id=":ct">
<br>
Otherwise, I'll try to implement the special-special case of<br>
DMDA_BOUNDARY_PERIODIC, P=1, zl=1, and s > 1 soon.</div></blockquote></div><br><div>Great, thanks.</div>