[pypy-commit] extradoc extradoc: add something about automatic barrier placement
Raemi
noreply at buildbot.pypy.org
Fri May 2 11:35:43 CEST 2014
Author: Remi Meier <remi.meier at inf.ethz.ch>
Branch: extradoc
Changeset: r5219:511162cc1095
Date: 2014-05-02 11:35 +0200
http://bitbucket.org/pypy/extradoc/changeset/511162cc1095/
Log: add something about automatic barrier placement
diff --git a/talk/icooolps2014/position-paper.tex b/talk/icooolps2014/position-paper.tex
--- a/talk/icooolps2014/position-paper.tex
+++ b/talk/icooolps2014/position-paper.tex
@@ -337,6 +337,14 @@
parallel programming forward. Together with sequential consistency it
provides a lot of simplification for parallel applications.
+While one can argue that STM requires the insertion of read and write
+barriers in the whole program, this can be done automatically and
+locally by a program transformation\cite{felber07}. There are attempts
+to do the same for fine-grained locking\cite{bill06} but they require
+a whole program analysis since locks are inherently non-composable.
+The effectiveness of these approaches still has to be proven for our
+use case.
+
%% - overhead (100-1000\%) (barrier reference resolution, kills performance on low \#cpu)
%% (FastLane: low overhead, not much gain)\\
%% - unlimited transaction length (easy atomic blocks)
@@ -456,6 +464,17 @@
processor's hardware transactional memory support. \emph{SIGARCH
Comput. Archit. News 38}, 5 (April 2010)
+\bibitem{felber07}
+ Felber, Pascal, et al. "Transactifying applications using an open
+ compiler framework." \emph{TRANSACT}, August (2007): 4-6.
+
+\bibitem{bill06}
+ Bill McCloskey, Feng Zhou, David Gay, and Eric
+ Brewer. 2006. Autolocker: synchronization inference for atomic
+ sections. \emph{In Conference record of the 33rd ACM SIGPLAN-SIGACT
+ symposium on Principles of programming languages (POPL '06)}. ACM,
+ New York, NY, USA
+
\end{thebibliography}
More information about the pypy-commit
mailing list