[m-rev.] diff: six percent speedup

[Zoltan Somogyi]

On 04-Apr-2005, Fergus Henderson <fjh at cs.mu.OZ.AU> wrote:
> Out of curiousity, do you have any intuition as to why the results
> are different now?

There are two possibilities. First, the terms being compared are probably
larger now, so the benefit of avoiding a check of the terms when the pointers
are equal is probably larger. Second, CPUs these days have pretty good branch
prediction, which makes the cost of testing the pointers relatively smaller.
I don't know their relative weights.

Zoltan.
--------------------------------------------------------------------------
mercury-reviews mailing list
post:  mercury-reviews at cs.mu.oz.au
administrative address: owner-mercury-reviews at cs.mu.oz.au
unsubscribe: Address: mercury-reviews-request at cs.mu.oz.au Message: unsubscribe
subscribe:   Address: mercury-reviews-request at cs.mu.oz.au Message: subscribe
--------------------------------------------------------------------------