<div class="gmail_quote">On Sat, Aug 27, 2011 at 16:09, Likun Tan <span dir="ltr"><<a href="mailto:likunt@andrew.cmu.edu">likunt@andrew.cmu.edu</a>></span> wrote:<br><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">
<div id=":1r6">the size of temp and H is 9*9*201, the size of S is 9*9.<br>
<br>
I used 2 processors, the returned values are<br>
temp: 0 0 0 9 9 101<br>
temp: 0 0 101 9 9 100<br></div></blockquote><div><br></div><div>temp is partitioned in the z direction. Each processor holds the full 9x9 cross-section of the "rod".</div><div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">
<div id=":1r6">
H: 0 0 101 9 9 100<br>
S: 0 5 101 9 4 100<br></div></blockquote><div><br></div><div>The 9x9 cross-section is partitioned. The value of zs and p are just left over from the earlier call, so they don't mean anything here.</div><div> </div><blockquote class="gmail_quote" style="margin:0 0 0 .8ex;border-left:1px #ccc solid;padding-left:1ex;">
<div id=":1r6">
<br>
I am not sure what you mean by how DAs were constructed, the command i<br>
used for construction is:<br>
DACreate2d(PETSC_COMM_WORLD, DA_NONPERIODIC, DA_STENCIL_STAR, 9, 9,<br>
PETSC_DECIDE, PETSC_DECIDE, 1, 0, PETSC_NULL, PETSC_NULL, &da2D);<br>
DACreate3d(PETSC_COMM_WORLD, DA_NONPERIODIC, DA_STENCIL_STAR, 9, 9, 201,<br>
PETSC_DECIDE, PETSC_DECIDE, PETSC_DECIDE, 1, 0, PETSC_NULL, PETSC_NULL,<br>
PETSC_NULL, &da3D); </div></blockquote><div><br></div><div>You can prevent PETSc from partitioning in the z-direction by changing the "p" parameter from PETSC_DECIDE to 1:</div><div><br></div><div><div><div>
DACreate3d(PETSC_COMM_WORLD, DA_NONPERIODIC, DA_STENCIL_STAR, 9, 9, 201,</div><div>PETSC_DECIDE, PETSC_DECIDE, 1, 1, 0, PETSC_NULL, PETSC_NULL,</div><div>PETSC_NULL, &da3D); </div></div></div><div><br></div><div><br></div>
</div>