On Wed, 24 May 2000, Stefan Matthias Aust wrote:

> At 02:01 24.05.00 -0700, Raab, Andreas wrote:
> 
> >of bucks for a C compiler. Good enough reason?! No? Well, for the second
> >reason: Have a look at the tinyBenchmarks of a 2.7 and the new 2.8 VM.
> >That'll convince you. OpenSource rules!
> 
> Well, the "1 tinyBenchmarks" numbers are quite impressive.  I get
> about 12% speedup in message sends and 70% in bytecodes.

Andreas: do these speedups only come from Ian's label-goto-hack in the
interpreter loop?
 
> However, when I do a "Time millisecondsToRun: [1 tinyBenchmarks]", the old 
> VM is about 0.2 seconds (or 4%) faster, that is 4.8 instead of 5 seconds.

Which means nothing because the test is calibrated automatically to run a
certain time.

-- Bert