From ee5a2ff5e708baaaebdb6f5256df05681c4f2247 Mon Sep 17 00:00:00 2001 From: Wolfgang Bangerth Date: Wed, 28 Sep 2011 02:46:07 +0000 Subject: [PATCH] Augment a note as suggested by Timo. git-svn-id: https://svn.dealii.org/trunk@24454 0785d39b-7218-0410-832d-ea1e28bc413d --- deal.II/examples/step-32/doc/intro.dox | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/deal.II/examples/step-32/doc/intro.dox b/deal.II/examples/step-32/doc/intro.dox index b99428a5d3..98922c4542 100644 --- a/deal.II/examples/step-32/doc/intro.dox +++ b/deal.II/examples/step-32/doc/intro.dox @@ -755,7 +755,11 @@ each node, then using threads doesn't make the program any faster. Consequently, you probably want to use the --disable-threads flag when configuring your deal.II installation for this machine. On the other hand, if you want to run this program on a -single multicore machine, then it may make sense to use threads. +single multicore machine, then it may make sense to use threads. That said, at +the time of writing this, we only use the WorkStream class for assembling +(parts of) linear systems, while 75% or more of the run time of the program is +spent in the linear solvers that are not parallelized — in other words, +the best we could hope is to parallelize the remaining 25%.

The testcase

-- 2.39.5