>Andreas Raab writes:
>
> > One of my problems with Exupery is that I've only seen claims about byte
> > code speed and if you know where the time goes in a real-life
> > environment then you know it ain't bytecodes. In other words, it seems
> > to me that Exupery is optimizing the least significant portion of the
> > VM. I'd be rather more impressed if it did double the send speed.
>
>Then be impressed. Exupery has had double Squeak's send performance
>since March 2005.
>
> http://people.squeakfoundation.org/person/willembryce/diary.html?start=23

Way back when we were playing around with J3, we put together the macroBenchmark methods as a more realistic indication of performance than the various micro benchmarks.  Are they still available?  If not, they can be run in older images (3.4 has them and runs them even now).  They have the minor downside of changing with tweaks to the image, but they have the upside of being quite realistic and absolutely comparable from VM to VM.  I highly recommend them to anyone serious about performance evaluation.

	- Dan

PS:  As a reminder, here is what they do...
	"1:	Decompile, pretty-print, and compile a bunch of methods.
		Does not install in classes, so does not flush cache."
	"2:	Build morphic tiles for all methods over 800 bytes (;-).
		Does no display."
	"3:	Translate the interpreter with inlining.
		Does not include any plugins."
	"4:	Run the context step simulator.
		200 iterations printing pi and 15 factorial."
	"5:	Run the InterpreterSimulator for 150,000 bytecodes.
		Will only run if you have mini.image in your directory."
	"6:	Open 10 browsers and close them.
		Includes browsing to a specific method."
	"7:	Play a game of FreeCell with display, while running the MessageTally.
		Thanks to Bob Arning for the clever part of this one."