<div class="gmail_quote">On Tue, Mar 13, 2012 at 10:38, Paul Mullowney <span dir="ltr"><<a href="mailto:paulm@txcorp.com">paulm@txcorp.com</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">
<div bgcolor="#ffffff" text="#000000">In bjacobi.c, the following comments are given for PCCreate_BJacobi.<br></div></blockquote><div><br></div><div>These things should definitely be fixed, but I said "jacobi" (without the "b").</div>
<div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex"><div bgcolor="#ffffff" text="#000000">
<br>
Developer Notes: This preconditioner does not currently work with
CUDA/CUSP for a couple of
reasons.
<br>
(1) It creates seq vectors as work vectors that should be
cusp
<br>
(2) The use of VecPlaceArray() is not handled properly by CUSP (that
is it will not know where the ownership of the vector is so may use
wrong values) even if it did know the ownership it may induce extra
copy ups and downs. Satish suggests a VecTransplantArray() to handle
two vectors sharing the same pointer and handling the CUSP side as
well instead of VecGetArray()/VecPlaceArray(). <br>
<br>
<br>
I've had some success with comment (2) above in regards to
Singleblock BJacobi. I haven't yet tried it for Multiblock or
Multiproc.</div></blockquote></div><br>