You are viewing a plain text version of this content. The canonical link for it is here.
Posted to issues@commons.apache.org by "Gilles (Commented) (JIRA)" <ji...@apache.org> on 2011/10/08 04:03:29 UTC
[jira] [Commented] (MATH-650) FastMath has static code which slows
the first access to FastMath
[ https://issues.apache.org/jira/browse/MATH-650?page=com.atlassian.jira.plugin.system.issuetabpanels:comment-tabpanel&focusedCommentId=13123349#comment-13123349 ]
Gilles commented on MATH-650:
-----------------------------
{{FastMathLoadCheck}} (revision 1180294):
{noformat}
Using exp(100); how=compute
times result
42677576 2.688117e+43
5338 2.688117e+43
1831 2.688117e+43
1759 2.688117e+43
Using exp(100); how=resources
times result
12930977 2.688117e+43
4650 2.688117e+43
2322 2.688117e+43
2496 2.688117e+43
Using exp(100); how=array
times result
12281292 2.688117e+43
4824 2.688117e+43
1807 2.688117e+43
1877 2.688117e+43
Using max(0,0); how=compute
times result
3293 0.000000e+00
1110 0.000000e+00
375 0.000000e+00
376 0.000000e+00
Using max(0,0); how=resources
times result
2680 0.000000e+00
713 0.000000e+00
382 0.000000e+00
367 0.000000e+00
Using max(0,0); how=array
times result
3065 0.000000e+00
520 0.000000e+00
370 0.000000e+00
376 0.000000e+00
{noformat}
> FastMath has static code which slows the first access to FastMath
> -----------------------------------------------------------------
>
> Key: MATH-650
> URL: https://issues.apache.org/jira/browse/MATH-650
> Project: Commons Math
> Issue Type: Improvement
> Affects Versions: Nightly Builds
> Environment: Android 2.3 (Dalvik VM with JIT)
> Reporter: Alexis Robert
> Priority: Minor
> Attachments: FastMathLoadCheck.java, LucTestPerformance.java
>
>
> Working on an Android application using Orekit, I've discovered that a simple FastMath.floor() takes about 4 to 5 secs on a 1GHz Nexus One phone (only the first time it's called). I've launched the Android profiling tool (traceview) and the problem seems to be linked with the static portion of FastMath code named "// Initialize tables"
> The timing resulted in :
> - FastMath.slowexp (40.8%)
> - FastMath.expint (39.2%)
> \- FastMath.quadmult() (95.6% of expint)
> - FastMath.slowlog (18.2%)
> Hoping that would help
> Thanks!
> Alexis Robert
--
This message is automatically generated by JIRA.
If you think it was sent incorrectly, please contact your JIRA administrators: https://issues.apache.org/jira/secure/ContactAdministrators!default.jspa
For more information on JIRA, see: http://www.atlassian.com/software/jira