<div class="gmail_extra">On Wed, Nov 7, 2012 at 11:45 AM, Hong Zhang <span dir="ltr"><<a href="mailto:hzhang@mcs.anl.gov" target="_blank">hzhang@mcs.anl.gov</a>></span> wrote:<br><div class="gmail_quote"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div class="im"><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div><div class="gmail_extra"><br></div></div><div class="gmail_extra">However, the broken routine is still used for Cholesky. Why not delete MatMatSolve_MUMPS entirely?</div>
</blockquote></div><div>Pushed fix for Cholesky.</div></blockquote><div><br></div><div>Why not actually delete the MatMatMult_MUMPS stub? It's dead code that is never called and doesn't do anything now. I don't think it saves work to keep the fragment around for some indeterminate time in the future when it might be relevant. Meanwhile, existence of the symbol makes it easy to accidentally think it must be called.</div>
<div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div><br></div><div>I'll implement sequential MatMatSolve_MUMPS there.</div></blockquote><div><br></div>
<div>What do you mean?</div><div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div>For parallel, we may implement multiple VecScatter?</div></blockquote></div>
<br></div><div class="gmail_extra">To scatter several vectors at once, or something else?</div>