s into ISP and see what it says wrt the FIB status.
I'm not fibbing... :-)
Cheers,
Ganesh
p.s. I said that FIB does the analysis for one data set. As in our
paper, we have shown that in many cases, a static analyzer can determine
that a program is data independent. In that case, the FIB anal
Thank you, Jeff and Ganesh.
My current research is trying to rewrite some collective MPI
operations to work with our system. Barrier is my first step, maybe I
will have bcast and reduce in the future. I understand that some
applications used too many unnecessary barriers. But here what I
We have a paper on the very topic that Jeff just mentioned :
Subodh Sharma, Sarvani Vakkalanka, Ganesh Gopalakrishnan, Robert M.
Kirby, Rajeev Thakur, and William Gropp, `` A Formal Approach to Detect
Functionally Irrelevant Barriers in MPI Programs,'' Recent Advances in
Parall
hical user interfaces that show communication matches
and its coverage guarantees make it useful for everyone - whether
someone new to MPI or an advanced user. We will be very glad to assist you!
Ganesh Gopalakrishnan
School of Computing, University of Utah
isp-...@cs.utah.edu
--
