Re:Make your program slower with threads
by frozenport on Sunday December 07, 2014 @02:33AM
(#8711568)
Moreover, he probably improved the single threaded version, and should re-check the scaling curve. There should be a `1 with random_r`, `2 with random_r`, and `3 with random_r`.
Re:Make your program slower with threads
by onestone on Sunday December 07, 2014 @09:56AM
(#8712327)
It's unlikely the single-threaded version was improved noticeably. Futexes are nearly zero-cost when not contended.
I left the random_r numbers with single threads out of the post for exactly this reason. Performance with random_r on a single thread was less than 3% faster, with a slightly higher variance (which I can't explain, to be honest).
Yes, absolutely. That can be done using the global state (i.e. calling rand() or random()), or is probably better done by pulling from the system entropy pool (via /dev/urandom on Linux).
Still no good; you can get spurious correlations between rng outputs on each core. You need something like L'Ecuyer RNG streams.
Re:Make your program slower with threads
by ScottBurson on Sunday December 07, 2014 @02:05PM
(#8713168)
Well, using /dev/urandom is a vast improvement over doing nothing.
But your point is well taken. People doing serious Monte Carlo simulations should probably use a more sophisticated RNG.
Re:Make your program slower with threads
by Dylan16807 on Sunday December 07, 2014 @03:42AM
(#8711689)
It's just an example.
You have to be sure to seed the generator differently in each thread, before calling 'random_r'.