space profiling

[Stephen Weeks]

> One  problem  (perhaps not a big deal) with statically allocating the bins is
> that you have to know the number of allocation points. 

No problem.  I think it is easy for Matthew to recognize frontier increments.

> If the bins are statically allocated, then the code at an allocation point is
> going to look like:
> 
>     save flags some where
>     addl    <allocation size>, <low 32 bits of counter>
>     adcl    $0, <high 32 bits of counter>
>     restore flags from some where

Yuck, but it makes sense.

> Ok, I agree, the fixed bins is a win.

Excellent.

> Did you agree or disagree that for timing the bins should still be 96 bits on
> output?   I  think  they should just so that the code in mlprof doesn't worry
> about more than one kind of bin.  Going to the sparse variety  will  probably
> save more space than this will cost us.

I agree.  One format for both time and space, sparse, 96 bit.