<div dir="ltr">Sorry about the slow response. Do you only want the square kernels with static (compile-time) size? These are currently implemented as macros, but it's not a problem to modify them to be functions. C99 provides a well-defined mechanism to have a single version with external linkage, but also encourage inlining.<br>
<br>I'm considering providing a set of kernels that would support non-square matrices, but the naming conventions would have to change and my applications would frequently not know the size statically (but it would typically be ~10 or less, so calling BLAS doesn't make sense).</div>
<div class="gmail_extra"><br><br><div class="gmail_quote">On Fri, Dec 21, 2012 at 3:29 AM, Aldo Bonfiglioli <span dir="ltr"><<a href="mailto:aldo.bonfiglioli@unibas.it" target="_blank">aldo.bonfiglioli@unibas.it</a>></span> wrote:<br>
<blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex">Dear all,<br>
would it be possible to have a unified interface (also Fortran callable)<br>
to the PetscKernel_A_gets_inverse_A_ routines?<br>
I find them very useful within my own piece<br>
of Fortran code to solve small dense linear system (which I have<br>
to do very frequently).<br>
I have my own interface, at present, but I need to<br>
change it as needed when a new PETSc version is released.<br>
<br>
Regards,<br>
Aldo<br>
<span class="HOEnZb"><font color="#888888">--<br>
Dr. Aldo Bonfiglioli<br>
Associate professor of Fluid Flow Machinery<br>
Scuola di Ingegneria<br>
Universita' della Basilicata<br>
V.le dell'Ateneo lucano, 10 85100 Potenza ITALY<br>
tel:<a href="tel:%2B39.0971.205203" value="+390971205203">+39.0971.205203</a> fax:<a href="tel:%2B39.0971.205215" value="+390971205215">+39.0971.205215</a><br>
<br>
<br>
Publications list <<a href="http://publicationslist.org/aldo.bonfiglioli" target="_blank">http://publicationslist.org/aldo.bonfiglioli</a>><br>
</font></span></blockquote></div><br></div>