From 8aac6cbdc7d022d9552035db77c3f4f094da85c8 Mon Sep 17 00:00:00 2001 From: heister Date: Wed, 4 Jun 2014 22:50:33 +0000 Subject: [PATCH] fix documentation in examples related to disable-threads git-svn-id: https://svn.dealii.org/trunk@33019 0785d39b-7218-0410-832d-ea1e28bc413d --- deal.II/examples/step-17/doc/intro.dox | 6 ------ deal.II/examples/step-32/doc/intro.dox | 6 ++---- deal.II/examples/step-40/doc/intro.dox | 7 +------ 3 files changed, 3 insertions(+), 16 deletions(-) diff --git a/deal.II/examples/step-17/doc/intro.dox b/deal.II/examples/step-17/doc/intro.dox index 631360953f..8845c12f29 100644 --- a/deal.II/examples/step-17/doc/intro.dox +++ b/deal.II/examples/step-17/doc/intro.dox @@ -23,12 +23,6 @@ together with these two additional libraries is described in the README file. -There is an additional caveat: PETSc appears not to co-operate well when using -threads and the program crashes when deal.II is compiled in its usual mode -supporting multithreading. The program can therefore only be compiled and run -if multithreading is disabled upon configuration of deal.II using the ---disable-threads switch to ./configure. - Now, for the details: as mentioned, the program does not compute anything new, so the use of finite element classes etc. is exactly the same as before. The diff --git a/deal.II/examples/step-32/doc/intro.dox b/deal.II/examples/step-32/doc/intro.dox index 6a20022310..46a21c1b61 100644 --- a/deal.II/examples/step-32/doc/intro.dox +++ b/deal.II/examples/step-32/doc/intro.dox @@ -827,10 +827,8 @@ processors busy and you won't get any additional speedup from using threads. For example, if your cluster nodes have 8 cores as they often have at the time of writing this, and if your batch scheduler puts 8 MPI processes on 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. That said, at +faster. Consequently, you probably want to either configure your deal.II without threads, or set the number of threads in MPI_InitFinalize to 1 (third argument), or "export DEAL_II_NUM_THREADS=1" before running. +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, diff --git a/deal.II/examples/step-40/doc/intro.dox b/deal.II/examples/step-40/doc/intro.dox index 0fec405ec8..dcc07c9b98 100644 --- a/deal.II/examples/step-40/doc/intro.dox +++ b/deal.II/examples/step-40/doc/intro.dox @@ -20,12 +20,7 @@ to work properly, this program needs access to the Hypre preconditioner package implementing algebraic multigrid; it can be installed as part of PETSc but has to be explicitly enabled during PETSc configuration; see the page linked to from the installation -instructions for PETSc. Finally, note that -PETSc appears not to co-operate well when using -threads and the program crashes when deal.II is compiled in its usual mode -supporting multithreading. The program can therefore only be compiled and run -if multithreading is disabled upon configuration of deal.II using the ---disable-threads switch to ./configure. +instructions for PETSc. -- 2.39.5