<div class="gmail_quote">On Thu, Mar 8, 2012 at 13:26, 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">If we choose this option, will <br>
-mat_type cusp<br>
allow one to use the CUSPARSE TriSolve for ILU or ICC?<br>
<br>
Alternatively, if one uses <br>
-mat_type cusparse<br>
for SpMV, will one be able to use the CUSP AMG and Poly
preconditioners?<br></div></blockquote><div><br></div><div>The preconditioner should make a copy if it needs to. For factorization, there can be a -pc_factor_mat_solver_package {cusparse,txpetscgpu} to select which implementation is used (for any matrix type that is used).</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">
<div class="gmail_quote">
<div><br>
</div>
</div>
Since I am new to this, what would PETSc developers like to see?<br></div></blockquote><div><br></div><div>I would have -mat_type cusp and -mat_type cusparse, with both implementations residing in PETSc. But I don't know where you want to go with txpetscgpu.</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>
One more wrinkle. Given the naming conventions, should the vector
types be<br>
-vec_type thrust<br>
instead of <br>
-vec_type cusp<br>
<br>
The vectors only rely on Thrust capabilities at the moment.</div></blockquote></div><br><div>I think so, yes.</div>