<html>
<head>
<meta content="text/html; charset=ISO-8859-1"
http-equiv="Content-Type">
</head>
<body bgcolor="#FFFFFF" text="#000000">
<br>
<div class="moz-cite-prefix">On 10/29/2014 06:43 PM, Jörg
Saßmannshausen wrote:<br>
</div>
<blockquote
cite="mid:201410292243.58843.j.sassmannshausen@ucl.ac.uk"
type="cite">
<pre wrap="">Hi all,
thanks again for the wealth of information.
Now, given that I am not interested in transporting files over the IB network
but I am doing parallel calculations, I would have thought that the latency
here is more important than the speed?
Thus, if FDR has a higher latency than QDR, does that mean my performance is
decreasing when I am running a calculation between nodes?</pre>
</blockquote>
<br>
It depends on the size of the messages sent back and forth during
the calculations, and the frequency of communications: is there
communications every time step, every x time steps, etc. Latency
affects the communications time for all messages, it's just more
noticeable for small messages since it represents a larger
percentage of the total communication time.<br>
<br>
For example, if your doing some kind of particle physics code, where
each node gets a volume of space, at the end of each time step, each
node needs to share the updated information about the particles
along it's borders with the it's neighbor nodes on the corresponding
borders. This is known as a 'halo' exchange'. How much data a halo
exchange requires depends on the problem and how finely it's
decomposed across the compute nodes, but I'm sure it can be enough
data where the higher bandwidth of FDR is beneficial. <br>
<br>
If your application has a lot of barriers, but little data exchanges
between nodes, latency would be more important, since the size of
barrier messages are very small. <br>
<br>
I'm not a big fan of the cliche response 'it depends', but it's
cliche because it does apply to many questions on this list. If FDR
is hurting the performance of your apps, it really depends on the
specifics of your applications. <br>
<br>
<blockquote
cite="mid:201410292243.58843.j.sassmannshausen@ucl.ac.uk"
type="cite">
<pre wrap="">
For those of you who are into Chemistry code: I am using VASP, cp2k, quantum
espresso and cpmd mainly. All of that is plain wave code. </pre>
</blockquote>
I'm not familiar enough with the nitty-gritty of any of these codes
to comment on their behavior. <br>
<blockquote
cite="mid:201410292243.58843.j.sassmannshausen@ucl.ac.uk"
type="cite">
<pre wrap="">
All the best from a wet London
Jörg
On Mittwoch 29 Oktober 2014 Prentice Bisbal wrote:
</pre>
<blockquote type="cite">
<pre wrap="">On 10/28/2014 04:43 PM, Mark Hahn wrote:
</pre>
<blockquote type="cite">
<pre wrap="">On Tue, 28 Oct 2014, John Hearns wrote:
</pre>
<blockquote type="cite">
<pre wrap="">Here is a very good post from Glenn Lockwood regarding FDR versus
dual-rail QDR:
<a class="moz-txt-link-freetext" href="http://glennklockwood.blogspot.co.uk/2013/05/fdr-infiniband-vs-dual-rail">http://glennklockwood.blogspot.co.uk/2013/05/fdr-infiniband-vs-dual-rail</a>
-qdr.html
</pre>
</blockquote>
<pre wrap="">
indeed, very nice. though also quite surprising - is it known that
FDR is so terrible for latency? seems astonishing to me.
</pre>
</blockquote>
<pre wrap="">
Yes, it was known to me. I had already known that FDR was worse than QDR
for latency, but I don't remember my source. I don't know if I'd
characterize it as "so terrible", though.
</pre>
</blockquote>
<pre wrap="">
</pre>
<br>
<fieldset class="mimeAttachmentHeader"></fieldset>
<br>
<pre wrap="">_______________________________________________
Beowulf mailing list, <a class="moz-txt-link-abbreviated" href="mailto:Beowulf@beowulf.org">Beowulf@beowulf.org</a> sponsored by Penguin Computing
To change your subscription (digest mode or unsubscribe) visit <a class="moz-txt-link-freetext" href="http://www.beowulf.org/mailman/listinfo/beowulf">http://www.beowulf.org/mailman/listinfo/beowulf</a>
</pre>
</blockquote>
<br>
<pre class="moz-signature" cols="72">--
Prentice Bisbal
Manager of Information Technology
Rutgers Discovery Informatics Institute (RDI2)
Rutgers University
<a class="moz-txt-link-freetext" href="http://rdi2.rutgers.edu">http://rdi2.rutgers.edu</a></pre>
</body>
</html>