Initial Smalltalk execution time

[Christian Thalinger]

On May 1, 2011, at 7:39 AM, Mark Roos wrote:
> Now that the core works I thought I would take a quick look at the execution speed.  For this I 
> executed the same code in our current environment (OS/2 and a mid 90's Smalltalk) and again using 
> our invokeDynamic based vm translation.  The code gets a string, parses in into commands and 
> generates a large string in response.  For us this is a typical socket request/response. 
> 
> On our current environment the first run takes 65ms and subsequent runs 42ms.   
> 
> Caveat,  this is not apples and apples at the execution level but is apples and apples at the 
> user level which is where we care.  And a reminder is that we are translating the Smalltalk bytecodes 
> to jvm codes at runtime.  Also we are translating about 150 methods to do this benchmark. 
> 
> For the jsr292 version the first run is 1 sec,  the next 10 are around 45ms then after executing 
> it 100x the next 10 runs average 12ms.   
> 
> Very promising given that we have not done any optimizing. 

That sounds very interesting.  I'm eager to see where this goes, performance-wise...

-- Christian
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://mail.openjdk.java.net/pipermail/mlvm-dev/attachments/20110502/2b2cf84a/attachment.html