Re: Loop jamming!?

> I understood "In the extreme case, the slower loop is not slowed down"
> to mean there are *no* programs that will slow as a result of loop
> jamming. I contend such programs *do* exist. These two assertions can
> not both be true. Either such programs exist, or they do not.




Every compiler optimization performed has a risk of producing slower
code. A good compiler can catch many of these instances by analysis
before the transformation; however, no compiler can catch all of
these instances.


Usually, a rule of thumb is to perform the transformation if
it results in a performance enhancement a majority of the time,
and the downside risk is minimal.


Loop jamming/fusion increases the number of generated instructions,
and can thus introduce page faulting in the body of the loop where no page
fault existed before. Obviously, this would slow down your code.


--

Return to the comp.compilers page.
Search the comp.compilers archives again.