> From:   "Andreas Raab" < andreas.raab at g... >
> Date:   Wed Jul 16, 2003  7:01 pm
> > Also, here are some macro numbers below. Most likely all
> > three within the range of error.
>
> Thanks. I can't spot anything that indicates that there's a significant
> improvement in general (not that surprising though I had hoped that we  
> may
> get a percent or two out of them).

Actually if we look at cpu execution for the macrobenchmarks I see this  
data
across 200,747 samples

56.4% interpret
5.0 MarkAndTrace
4.5 sweepPhase
3.4 instantiateSmallClasssizeInBytes  (allocateOrRecycleContext 2.0%,  
primitiveBlockCopy  0.8%...)
3.0 updatePointersInRangeFromTo  (via incCompBody)
3.0 primitiveResponse
1.9 primitiveValue
1.6 primitiveBlockCopy
1.5 lookupMethodInClass
1.1 instantiateClassindexableSizedoFill
0.9 updatePointersInRootObjectsFromto

(lots more to make 100%).
So 13.5% is GC related.
4.5% is allocation  related
--
======================================================================== 
===
John M. McIntosh <johnmci at smalltalkconsulting.com> 1-800-477-2659
Corporate Smalltalk Consulting Ltd.  http://www.smalltalkconsulting.com
======================================================================== 
===