1 Some explanations on the MPI implementation of a subset of NPB 3.3 (NPB3.3-MPI)
2 ----------------------------------------------------------------------
4 NPB-MPI is a sample MPI implementation based on NPB2.4 and NPB3.0-SER.
5 This subset contains three of the original benchmarks: one in Fortran: EP;
6 one in C: IS, as well as the DT benchmark, written in C, introduced in NPB3.2-MPI.
11 Before compilation, one needs to check the configuration file
12 'make.def' in the config directory and modify the file if necessary.
13 If it does not (yet) exist, copy 'make.def.template' or one of the
14 sample files in the NAS.samples subdirectory to 'make.def' and
15 edit the content for site- and machine-specific data. Then
17 make <benchmark-name> NPROCS=<number> CLASS=<class> \
18 [SUBTYPE=<type>] [VERSION=VEC]
20 where <benchmark-name> is "dt", "ep", or "is",
21 <number> is the number of processes
22 <class> is "S", "W", "A", "B", "C", "D", or "E"
24 Classes C, D and E are not available for DT.
25 Class E is not available for IS.
27 Class D for IS (Integer Sort) requires a compiler/system that
28 supports the "long" type in C to be 64-bit.
33 The executable is named <benchmark-name>.<class>.<nprocs>
34 The executable is placed in the bin subdirectory (or in the directory
35 BINDIR specified in make.def, if you've defined it). The method for
36 running the MPI program depends on your local system.