Update description of the -y option

Also make sure ParMETIS is mentioned as well as METIS

INSTALL.swift

@@ -138,14 +138,15 @@ before you can build it.
                            =====================
 
 
- - METIS:
-	a build of the METIS library can be optionally used to
-        optimize the load between MPI nodes (requires an MPI
-        library). This should be found in the standard installation
-        directories, or pointed at using the "--with-metis"
-        configuration option.  In this case the top-level installation
-        directory of the METIS build should be given. Note to use
-        METIS you should supply at least "--with-metis".
+ - METIS/ParMETIS:
+	a build of the METIS or ParMETIS library should be used to
+        optimize the load between MPI nodes. This should be found in the
+        standard installation directories, or pointed at using the
+        "--with-metis" or "--with-parmetis" configuration options.
+        In this case the top-level installation directory of the build
+        should be given. Note to use METIS or ParMETIS you should supply at
+        least "--with-metis". ParMETIS is preferred over METIS when there
+        is a choice.
 
 - libNUMA:
 	a build of the NUMA library can be used to pin the threads to

README

@@ -65,8 +65,8 @@ Parameters:
     -T, --timers=<int>                Print timers every time-step.
     -v, --verbose=<int>               Run in verbose mode, in MPI mode 2 outputs
                                       from all ranks.
-    -y, --task-dumps=<int>            Time-step frequency at which task graphs
-                                      are dumped.
+    -y, --task-dumps=<int>            Time-step frequency at which task analysis
+                                      files and/or tasks are dumped.
     -Y, --threadpool-dumps=<int>      Time-step frequency at which threadpool
                                       tasks are dumped.
 

README.md

@@ -113,8 +113,8 @@ Parameters:
     -T, --timers=<int>                Print timers every time-step.
     -v, --verbose=<int>               Run in verbose mode, in MPI mode 2 outputs
                                       from all ranks.
-    -y, --task-dumps=<int>            Time-step frequency at which task graphs
-                                      are dumped.
+    -y, --task-dumps=<int>            Time-step frequency at which task analysis
+                                      files and/or tasks are dumped.
     -Y, --threadpool-dumps=<int>      Time-step frequency at which threadpool
                                       tasks are dumped.
 

doc/Doxyfile.in

@@ -1976,7 +1976,7 @@ SEARCH_INCLUDES        = YES
 # preprocessor.
 # This tag requires that the tag SEARCH_INCLUDES is set to YES.
 
-INCLUDE_PATH           =
+INCLUDE_PATH           = @top_srcdir@/src
 
 # You can use the INCLUDE_FILE_PATTERNS tag to specify one or more wildcard
 # patterns (like *.h and *.hpp) to filter out the header-files in the

doc/RTD/source/CommandLineOptions/index.rst

@@ -60,7 +60,7 @@ can be found by typing ``./swift -h``::
     -T, --timers=<int>                Print timers every time-step.
     -v, --verbose=<int>               Run in verbose mode, in MPI mode 2 outputs
                                       from all ranks.
-    -y, --task-dumps=<int>            Time-step frequency at which task graphs
-                                      are dumped.
+    -y, --task-dumps=<int>            Time-step frequency at which task analysis
+                                      files and/or tasks are dumped.
     -Y, --threadpool-dumps=<int>      Time-step frequency at which threadpool
                                       tasks are dumped.

doc/RTD/source/GettingStarted/compiling_code.rst

@@ -41,9 +41,9 @@ FFTW
 ~~~~
 Version 3.3.x or higher is required for periodic gravity.
 
-METIS
-~~~~~
-METIS is used for domain decomposition and load balancing.
+ParMETIS or METIS
+~~~~~~~~~~~~~~~~~
+One is required for domain decomposition and load balancing.
 
 libNUMA
 ~~~~~~~

doc/RTD/source/GettingStarted/running_on_large_systems.rst

@@ -26,9 +26,8 @@ system (i.e. over MPI on several nodes). Here are some recommendations:
 + Run with threads pinned. You can do this by passing the ``-a`` flag to the
   SWIFT binary. This ensures that processes stay on the same core that spawned
   them, ensuring that cache is accessed more efficiently.
-+ Ensure that you compile with METIS. More information is available in an
-  upcoming paper, but using METIS allows for work to be distributed in a
-  more efficient way between your nodes.
++ Ensure that you compile with ParMETIS or METIS. These are required if
+  want to load balance between MPI ranks.
 
 Your batch script should look something like the following (to run on 16 nodes
 each with 2x16 core processors for a total of 512 cores):

src/partition.c

@@ -71,7 +71,7 @@ const char *initial_partition_name[] = {
 /* Simple descriptions of repartition types for reports. */
 const char *repartition_name[] = {
     "none", "edge and vertex task cost weights", "task cost edge weights",
-    "particle memory weights",
+    "memory balanced, using particle vertex weights",
     "vertex task costs and edge delta timebin weights"};
 
 /* Local functions, if needed. */
@@ -1587,7 +1587,7 @@ static void repart_memory_metis(struct repartition *repartition, int nodeID,
 
     /* And repartition. */
 #ifdef HAVE_PARMETIS
-  if (repartition_partition->usemetis) {
+  if (repartition->usemetis) {
     pick_metis(nodeID, s, nr_nodes, weights, NULL, repartition->celllist);
   } else {
     pick_parmetis(nodeID, s, nr_nodes, weights, NULL, refine,