On Tue, 9 Oct 2018 09:18:35 +0100, The Natural Philosopher
 declaimed the following:

>Dennis Lee Bieber  wrote:
>>   I ran a benchmark about two+ years ago which required significant swap
>> space to complete; otherwise the Out-of-Memory monitor would kill it
>> (somewhat strange, since the program was designed to take a failure from
>> malloc() as signal to shut down and report results -- and that part worked
>> on a No-OS embedded system).
>
>Why would malloc() fail if there was swap space?

 The other way the program shutdown/reported results is when the /time/
to run a "step" suddenly increases drastically. This happens when a
pass/step starts severe swapping.

 The HINT algorithm, in simple terms, tends to double the needed memory
on each pass, measuring the "improvement" in the calculation. It did take
some tuning of the parameters to get it to run with reasonable results on
modern processors -- when originally written a 200MHz processor was
practically a supercomputer. Now, the pass time-limit had to be cut down so
much it is beginning to beat against OS time-slices  (so plotting
results for Linux tends to show some spikes, but the No-OS run had smooth
curves).


--
 Wulfraed                 Dennis Lee Bieber         AF6VN
 wlfraed@ix.netcom.com    HTTP://wlfraed.home.netcom.com/

--- SoupGate-Win32 v1.05