<html>
<head>
<meta content="text/html; charset=UTF-8" http-equiv="Content-Type">
</head>
<body bgcolor="#FFFFFF" text="#000000">
Hi,<br>
<br>
I'm not sure if this is a naive question, but is there any speed or
performance difference when using VecScatterCreateToZero or similar
routine, compared to MPI standard routines such as mpi_gather,
mpi_gatherv etc?<br>
<pre class="moz-signature" cols="72">Yours sincerely,
TAY wee-beng</pre>
<br>
On 16/4/2012 6:26 PM, Jed Brown wrote:
<blockquote
cite="mid:CAM9tzSk1dK-0c0qZ6BUoi_MqBXTukQdtfqDHoNVP27Jbtj7RrQ@mail.gmail.com"
type="cite"><br>
<br>
<div class="gmail_quote">On Mon, Apr 16, 2012 at 11:25, Abraham
Taicher <span dir="ltr"><<a moz-do-not-send="true"
href="mailto:ataicher@ices.utexas.edu">ataicher@ices.utexas.edu</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"> Hi,<br>
<br>
I have a parallel vector spread across all processors that I
would like to gather into a single processor, say the root
processor. Is there PETSc functionality to do this? I tried
looking for a PETSc gather function but the one I found, <a
moz-do-not-send="true"
href="http://www.mcs.anl.gov/petsc/petsc-current/docs/manualpages/Vec/VecStrideGather.html"
target="_blank">VecStrideGather</a>, does not seem to
apply. Should I simply use the MPI routine MPI_Gather?<br>
</div>
</blockquote>
<div><br>
</div>
<div><a moz-do-not-send="true"
href="http://www.mcs.anl.gov/petsc/petsc-current/docs/manualpages/Vec/VecScatterCreateToZero.html">http://www.mcs.anl.gov/petsc/petsc-current/docs/manualpages/Vec/VecScatterCreateToZero.html</a></div>
<div><br>
</div>
</div>
</blockquote>
</body>
</html>