Author: Carl Friedrich Bolz <[email protected]>
Branch: extradoc
Changeset: r4638:0861f8806bd5
Date: 2012-08-16 18:39 +0200
http://bitbucket.org/pypy/extradoc/changeset/0861f8806bd5/
Log: address another reviewer comment
diff --git a/talk/dls2012/paper.tex b/talk/dls2012/paper.tex
--- a/talk/dls2012/paper.tex
+++ b/talk/dls2012/paper.tex
@@ -889,12 +889,6 @@
\section{Benchmarks}
-
-\revd{
-It isn't clear from the paper, but a reader might conclude that the bulk of the
-time savings are from removing boxing/unboxing operations.
-}
-
The loop peeling optimization was implemented in the PyPy
framework in about 450 lines of RPython code. That means that the
JIT-compilers generated for all
interpreters implemented with RPython now can take advantage of
@@ -1130,7 +1124,11 @@
We can observe that PyPy (even without loop peeling) is orders of magnitude
faster than CPython. This is due to the JIT compilation
advantages and optimizations we discussed in previous
-work~\cite{bolz_allocation_2011, bolz_runtime_2011}. The geometric mean of the
+work~\cite{bolz_allocation_2011, bolz_runtime_2011}, the main improvement for
+these concrete benchmarks come from the allocation removal/unboxing
+optimization.
+
+The geometric mean of the
speedup of loop peeling is 70\%, which makes benchmark times
comparable with native-compiled C code. We attribute the performance gap to C
code to
the relative immaturity of RPython's JIT machine code backend as well as
missing
_______________________________________________
pypy-commit mailing list
[email protected]
http://mail.python.org/mailman/listinfo/pypy-commit
