Re: more fun with proposals
Jarek Nieplocha (j_nieplocha@pnl.gov)
Thu, 11 Jul 1996 15:21:40 -0700
In message <9607111755.AA9863@watngi03.watson.ibm.com>you write:
> The alternative proposal is probably not more efficient than the original one.
> It provides a higher level of abstraction than the original one, and is more
> removed from the underlying h/w mechanisms. Thus, it may be less efficient for
> some codes. The reason I have written it down and want it to be discussed is
> that I am unconfortable with the large number of "auxiliary" functions and
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
> concepts that we are introducing: counters, fences, coherence operations, etc.
> I don't believe in magic: easier to use and more efficient. I want us to have
> a discussion on the tradeoffs we are willing to make between ease of use and
> efficiency on some machines.
>
Should we delete counters once again? At least four operations would be gone and the
interface to remaining operations simpler :-)
The functionality counters introduced could be easily built on top of remaining functions.
Of course on certain plaforms, the efficiency of counter operations would be sacrificed
but we have yet to see real applications that would be complaining.
Jarek