[pypy-commit] extradoc extradoc: Mention the PYPYSTM reports. This is actually the most important new feature...
arigo
noreply at buildbot.pypy.org
Mon Mar 30 11:31:43 CEST 2015
Author: Armin Rigo <arigo at tunes.org>
Branch: extradoc
Changeset: r5518:a0b6c0fb4b6c
Date: 2015-03-30 11:32 +0200
http://bitbucket.org/pypy/extradoc/changeset/a0b6c0fb4b6c/
Log: Mention the PYPYSTM reports. This is actually the most important
new feature...
diff --git a/blog/draft/stm-mar2015.txt b/blog/draft/stm-mar2015.txt
--- a/blog/draft/stm-mar2015.txt
+++ b/blog/draft/stm-mar2015.txt
@@ -25,7 +25,39 @@
PyPy-STM instead of the regular PyPy and your program should still
work. See `current status`_ for more information.
+This work was done by Remi Meier and Armin Rigo. Thanks to all donors
+for `crowd-funding the STM work`_ so far! As usual, it took longer
+than we would have thought. I really want to thank the people that
+kept making donations anyway. Your trust is greatly appreciated!
+
.. _`current status`: http://pypy.readthedocs.org/en/latest/stm.html#current-status-stmgc-c7
+.. _`crowd-funding the STM work`: http://pypy.org/tmdonate2.html
+.. _`July 2014 release`: http://morepypy.blogspot.ch/2014/07/pypy-stm-first-interesting-release.html
+
+
+What's new?
+-----------
+
+Compared to the `July 2014 release`_, the main addition is a way to
+get reports about STM conflicts. This is an essential new feature.
+
+To understand why this is so important, consider that if you already
+played around with the previous release, chances are that you didn't
+get very far. It probably felt like a toy: on very small examples it
+would nicely scale, but on any larger example it would not scale at
+all. You didn't get any feedback about why, but the underlying reason
+for that is that, in any large example, there are a few unexpected STM
+conflicts that occur all the time. This prevents any parallelization.
+
+Now PyPy-STM is no longer a black box: you have a way to learn about
+these conflicts and fix them. The tl;dr version is to run::
+
+ PYPYSTM=stmlog pypy yourprogr.py
+ print_stm_log.py stmlog
+
+
+Performance
+-----------
The performance is now more stable than it used to be. More
precisely, the best case is "25%-40% single-core slow-down with
@@ -35,13 +67,6 @@
that, we should not get more than 2x single-core slow-down in the
worst case. Please report such cases as bugs!
-This work was done by Remi Meier and Armin Rigo. Thanks to all donors
-for `crowd-funding the STM work`_ so far! (As usual, it took longer
-than we would have thought. I really want to thank the people that
-kept making donations anyway. Your trust is greatly appreciated!)
-
-.. _`crowd-funding the STM work`: http://pypy.org/tmdonate2.html
-
TransactionQueue
----------------
More information about the pypy-commit
mailing list