Dan Sugalski <[EMAIL PROTECTED]> wrote:
> At 4:38 PM -0500 11/4/04, Matt Diephouse wrote:
>>On Tue, 2 Nov 2004 13:35:09 -0500, Dan Sugalski <[EMAIL PROTECTED]> wrote:
>>> What, think this warrants a 0.1.2 release? I'm not so sure about
>>> that. It's not that big a deal...
>>
>>In the past week, Parrot has seen a dramatic speedup. We're in about
>>the best shape we've been in in the past 4 months:
>>
>> http://www.sidhe.org/~timeparrot/graphs/A/sum.png
>>
>>Seems like a pretty big deal.
Raw function calling speed demonstrated by {oo,}fib [1] isn't there, where
it should. But fixing this needs some bigger changes. Anyway I'm glad
that the numbers indicate that the indirect register addressing is the
way to go.
[1] AFAIK a non-recursive benchmark is missing. Is it possible to get
timings for older versions for 3 TODO benchmarks:
Calling some nested functions and returning 1 result repeatedly. One for
PMC-only args/returns, one for int, and one for all 4 kinds of registers.
> Hrm. Okay, then, if I've not managed to make a mess of things with
> the stuff I've been doing, why don't we do a 0.1.2 performance
> release? Between the speedups and the gentler effects of -t it seems
> likely to be worth it for people who're working with parrot to do
> stuff.
Or wait for the new register allocator?
leo
