[virtmach] Your VM

[David Rush]

jlane@nwlink.com writes:
> Fjellstrom (?) wrote:
> > Now I have a question: does any one know for sure
> > if an array of function pointers is faster than
> > a switch case? I know threaded code is faster but
> > is an function pointer array? (will it help the
> > cpu cache enough to make a difference?)
> 
> Assuming that the switch and array are both dense, i.e.
> all or nearly all possible positions in the table are
> in use, then it depends on which compiler you are using.
> Many compilers will generate an indirect jump through a
> table of pointers for a dense switch.  Generally, the
> compiler can generate better code for this internally
> than can be written in source code, so the switch version
> is likely to be faster.

It's worth noting that your most-used instructions may benefit from
being if-dispatched depending on underlying CPU issues. In particular,
CPUs with branch predictors can't use them on jump tables, so you can
easily get I-cache misses and pipeline stalls. Additionally, if
branches can often take advantage of CPU delay slots. But all of that
comes under the heading of 'performance tuning'; you have to do it for
each machine your VM will run on, but that's why you wrote a VM
anyway, isn't it? To isolate your machine dependencies...

david rush
-- 
Communism is inequality, but not as property is. Property is
exploitation of the weak by the strong. Communism is exploitation of
the strong by the weak.
	-- What is Property? (Pierre-Joseph Proudhon)