<html><head><style type='text/css'>p { margin: 0; }</style></head><body><div style='font-family: times new roman,new york,times,serif; font-size: 12pt; color: #000000'>Hi Darshan users/developers<div><br></div><div>As I intended to do data-mining on a large number of Darshan-generated traces, I quickly realized that producing a text output using darshan-parser then parse this output using high-level languages (ruby or python), was extremely inefficient. I turned to the C API, but implementing data-mining algorithms in pure C is also very hard.</div><div><br></div><div>Thus I developed a Ruby extension for Darshan. This extension is available here: http://darshan-ruby.gforge.inria.fr/</div><div>All functionalities currently available in Darshan 2.2.5 for reading binary (bz2-compressed) traces, are now available in Ruby, and can help analyzing traces more easily and faster.</div><div><br></div><div>I hope this tool can be useful to others, feel free to give me some feedbacks :-)</div><div><br></div><div>Phil: you'll find in this package the Makefile.in I was talking about in one of my previous mails.</div><div><br></div><div>Best,</div><div><br><div><span name="x"></span><font size="2"><font size="3">Matthieu Dorier<br>
</font>PhD student at ENS Cachan Brittany and IRISA<br><a href="http://people.irisa.fr/Matthieu.Dorier">http://people.irisa.fr/Matthieu.Dorier</a></font><span name="x"></span><br></div></div></div></body></html>