From: jccharr <jccharr@charr.local>
Date: Wed, 26 Mar 2014 15:25:54 +0000 (+0100)
Subject: change heuristic
X-Git-Tag: ispa14_submission~5
X-Git-Url: https://bilbo.iut-bm.univ-fcomte.fr/and/gitweb/mpi-energy.git/commitdiff_plain/e7ebd4d2766afa9be865d0cead8ce65fb333b53e

change heuristic
---

diff --git a/paper.tex b/paper.tex
index 48f38b1..53a1cf7 100644
--- a/paper.tex
+++ b/paper.tex
@@ -181,7 +181,7 @@ using a multimeter, the slack times, \dots{} Then a method will exploit these
 measurements to compute the scaling factor values for each processor.  This
 operation, measurements and computing new scaling factor, can be repeated as
 much as needed if the iterations are not regular.  Kimura, Peraza, Yu-Liang et
-al.~\cite{11,2,31} used learning methods to select the appropriate scaling
+al.~\cite{11,2,31} used varied heuristics to select the appropriate scaling
 factor values to eliminate the slack times during runtime.  However, as seen
 in~\cite{39,19}, machine learning methods can take a lot of time to converge
 when the number of available gears is big.  To reduce the impact of slack times,