|Perl: the Markov chain saw|
Re: STOP Trading Memory for Speedby Aristotle (Chancellor)
|on Sep 25, 2002 at 20:38 UTC||Need Help??|
There's a flaw in your argumentation.
Point 3 refutes point 1, with point 2 bearing no relevance to either. All you have proven is:
You can trade memory to gain speed - so long as you have enough memory.
That, I believe, isn't news to anyone. The fact that the 1000% overhead forced you to go for disk IO rather than all-in-memory is irrelevant because it doesn't have any impact on the relation between CPU speed and memory bandwidth.
You do have a point in complaining about the high overhead approach forcing you to take refuge in disk IO, but that's an entirely different argument from saying that trading memory for clock cycles will backfire when an application fits in memory.
Which of these two different points do you want to discuss?
Makeshifts last the longest.