d8888 888 888      88888888888 888      d8b                                 888       888          888       .d8888b.           888                               
      d88888 888 888          888     888      Y8P                                 888   o   888          888      d88P  Y88b          888                               
     d88P888 888 888          888     888                                          888  d8b  888          888      Y88b.               888                               
    d88P 888 888 888          888     88888b.  888 88888b.   .d88b.  .d8888b       888 d888b 888  .d88b.  88888b.   "Y888b.   88888b.  88888b.   .d88b.  888d888 .d88b.  
   d88P  888 888 888          888     888 "88b 888 888 "88b d88P"88b 88K           888d88888b888 d8P  Y8b 888 "88b     "Y88b. 888 "88b 888 "88b d8P  Y8b 888P"  d8P  Y8b 
  d88P   888 888 888          888     888  888 888 888  888 888  888 "Y8888b.      88888P Y88888 88888888 888  888       "888 888  888 888  888 88888888 888    88888888 
 d8888888888 888 888          888     888  888 888 888  888 Y88b 888      X88      8888P   Y8888 Y8b.     888 d88P Y88b  d88P 888 d88P 888  888 Y8b.     888    Y8b.     
d88P     888 888 888          888     888  888 888 888  888  "Y88888  88888P'      888P     Y888  "Y8888  88888P"   "Y8888P"  88888P"  888  888  "Y8888  888     "Y8888  
                                                                 888                                                          888                                        
                                                            Y8b d88P                                                          888                                        
                                                             "Y88P"                                                           888   

All Things WebSphere

Concerns and issues relating to all versions of WebSphere Application Server

Friday, April 13, 2012

 

IBM J9 JIT - Inlining of Virtual Methods - Invariant Argument Preexistence Optimization

With Java 6 the the IBM JIT  is aggressive in optimization leading to world class performance; however sometimes the JIT gets tripped up on itself doing certain optimizations.  If you ran into http://www-01.ibm.com/support/docview.wss?uid=swg1IZ58251 or http://www-01.ibm.com/support/docview.wss?uid=swg1IV15424 or http://www-01.ibm.com/support/docview.wss?uid=swg1IV16044 you may be wondering what is meant by JIT invariant argument optimization and if it makes sense to disable it ?

How does pre-existence work?
For a full and rigorous explanation see Chapter 5 from the paper that introduced the concept:

Assume the following scenario:

void m1(Foo arg)
{
   ...
   arg.m2(); // virtual call or interface call
   ...
}

If at the time of compilation for m1 there is only one implementation for callee m2, then the JIT knows exactly what target to expect and can safely inline the code for it with no guard.
If a class load event extends the hierarchy such that a new implementation for m2 is introduced into the system, the code for m1 may call the wrong target for some type of arguments. The JIT invalidates the old body for m1 and immediately schedules a recompilation for it. While the recompilation is in progress application threads are blocked from entering the old body of caller m1. The new body of m1 will not inline m2, but will actually execute the virtual/interface call (note that the different targets for m2 may already be compiled/optimized on their own). Pre-existence is not going to help in this case.

In a nutshell, pre-existence helps the JIT inline some targets when the class hierarchy indicates it is safe to do so.
1) If the class hierarchy is such that the JIT doesn't know what to inline, then pre-existence does nothing. With or without it it's the same thing.
2) If pre-existence was applied, but later-on the class hierarchy changed in an incompatible way, then the JIT basically needs to undo what pre-existence did. Again, disabling pre-existence from the beginning is not going to hurt this case.

Why have pre-existence enabled?
Some applications, while having deep class hierarchies, load only one implementer for various virtual calls. Experiments have shown improvements from pre-existence  Even when the class hierarchy is extended, we do not see any visible decrease in the performance of  the system due to method invalidation.

When does it make sense to disable pre-existence ?
When an application does a a lot of Dynamic class reloading and deep class hierarchies with interfaces having multiple implementations in mainline path, then it may make sense to disable pre-existence with
-Xjit:disableInvariantArgumentPreexistence generic JVM argument. 

Labels:


Comments:

Post a Comment

Subscribe to Post Comments [Atom]



Links to this post:

Create a Link



<< Home

Archives

December 2006   September 2008   January 2009   February 2009   March 2009   September 2009   October 2009   November 2009   December 2009   January 2010   February 2010   March 2010   April 2010   October 2010   January 2011   February 2011   April 2011   May 2011   June 2011   July 2011   August 2011   September 2011   October 2011   November 2011   December 2011   January 2012   February 2012   March 2012   April 2012   May 2012   June 2012   July 2012   August 2012   September 2012   October 2012   November 2012   January 2013   May 2013   June 2013   July 2013   September 2013   October 2013   June 2014   August 2014  

This page is powered by Blogger. Isn't yours?

Subscribe to Posts [Atom]