HP XC System 3.x Software User Manual
Page 106
the rule). Typically the rules for an object file target is a single compilation line, so it is common to talk
about concurrent compilations, though GNU make is more general.
On non-cluster platforms or command nodes, matching concurrency to the number of cores often works
well. It also often works well to specify a few more jobs than cores so that one job can proceed while
another is waiting for I/O. On an HP XC system, there is the potential to use compute nodes to do
compilations, and there are a variety of ways to make this happen.
One way is to prefix the actual compilation line in the rule with an srun command. So, instead of executing
cc foo.c -o foo.o
it would execute srun cc foo.c -o foo.o. With concurrency, multiple
command nodes would have multiple srun commands instead of multiple cc commands. For projects
that recursively run make on subdirectories, the recursive make can be run on the compute nodes. For
example:
$ cd subdir; srun $(MAKE)...
Further, if the recursive make is run remotely, it can be told to use concurrency on the remote node. For
example:
$ cd subdir; srun -n1 -N1 $(MAKE) -j4...
This can cause multiple makes to run concurrently, each building their targets concurrently. The -N1
option is used to reserve the entire node, because it is intended to be used for multiple compilations. The
following examples illustrate these ideas. In GNU make, a $(VARIABLE) that is unspecified is replaced
with nothing. Therefore, not specifying PREFIX keeps the original Makefile's behavior, but specifying
PREFIX
to appropriate srun command prefixes will cause concurrency within the build.
For more information about GNU parallel make, see the make manpage. For additional sources of GNU
information, see the references provided in
.
In this section, three different ways to parallelize a make procedure are illustrated. The smg98 package is
used to illustrate these three procedures. The smg98 package is available at the following URL:
These procedures take advantage of the GNU make -j switch, which specifies the number of jobs to run
simultaneously. See the make manpage for more information about this switch.
The following parallel make approaches are described:
•
— Go through the directories serially and have the make procedure within
each directory be parallel. (Modified Makefile: Makefile_type1).
•
— Go through the directories in parallel and have the make procedure within
each directory be serial (Modified Makefile: Makefile_type2).
•
— Go through the directories in parallel and have the make procedure within
each directory be parallel (Modified Makefile: Makefile_type3).
The original Makefile is shown below:
#BHEADER***********************************************************
# (c) 1998 The Regents of the University of California
#
# See the file COPYRIGHT_and_DISCLAIMER for a complete copyright
# notice, contact person, and disclaimer.
#
# $Revision: 1.1 $
#EHEADER***********************************************************
SHELL = /bin/sh
srcdir = .
HYPRE_DIRS =\
utilities\
struct_matrix_vector\
struct_linear_solvers\
106
Advanced Topics