Shared vs non shared PMC timings

[Leopold Toetsch]

To estimate the costs of shared PMCs I have run this program[1], once 
with .Ref and once with .SharedRef.

There are 2 major issues:
1) PMC initialization (new_p_ic_p): The shared PMC needs additionally 
the allocation of the synchronize structure and the MUTEX_INIT.
2) PMC access (set_p_i): locking/unlocking the mutex

Here are snippets from the profile:

with SharedRef
 CODE  OP FULL NAME            CALLS  TOTAL TIME   AVG T. ms
 ----  -----------------     -------  ----------  ----------
  753  new_p_ic_p             100000    0.157785      0.0016
  905  set_p_i                100000    0.049269      0.0005
with Ref
 CODE  OP FULL NAME            CALLS  TOTAL TIME   AVG T. ms
 ----  -----------------     -------  ----------  ----------
  753  new_p_ic_p             100000    0.051330      0.0005
  905  set_p_i                100000    0.011356      0.0001
(Overall timings aren't really comparable, the SharedRef also does a 
LOCK for mark, which slows that down as well)

Linux 2.2.16, Athlon 800, unoptimized Parrot build.
leo
[1]
     set I0, 100000
     set I1, 0
lp:
     new P0, .PerlInt
     new P1, .Ref, P0   # or .SharedRef
     set P1, I1
     inc I1
     lt I1, I0, lp
     end