You cannot select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
psblas3/README

197 lines
6.4 KiB
Plaintext

13 years ago
This directory contains the PSBLAS library, version 3.0.
This version requires a working Fortran 2003 compiler; we do not use
all of the language features (specifically, so far we did not employ
FINAL subroutines), but the features we use were sufficient in
identifying bugs in ALL compilers we tried (all the bugs have been
reported and mostly fixed by the respective vendors).
The new internals have been completely overhauled, and in many cases
rewritten; they now enable a much better interfacing with user-defined
storage formats. If the user is only interested in the predefined
formats, then the user's guide should be sufficient; what is somewhat
lacking is documentation on how to add to the library, i.e. a
developers' guide; stay tuned.
The architecture of the Fortran 2003 sparse BLAS is described in
S. Filippone, A. Buttari:
Object-Oriented Techniques for Sparse Matrix Computations in Fortran
2003,
13 years ago
ACM Trans. on Math. Software, vol. 38, No. 4, 2012.
Version 1.0 of the library was described in:
20 years ago
S. Filippone, M. Colajanni
PSBLAS: A library for parallel linear algebra computation on sparse matrices
ACM Trans. on Math. Software, 26(4), Dec. 2000, pp. 527-550.
UTILITIES
The test/util directory contains some utilities to convert to/from
Harwell-Boeing and MatrixMarket file formats.
20 years ago
DOCUMENTATION
See docs/psblas-3.0.pdf; an HTML version of the same document is
available in docs/html.
Please consult the sample programs, especially
test/pargen/ppde[23]d.f90
20 years ago
OTHER SOFTWARE CREDITS
We originally included a modified implementation of some of the
Sparker (serial sparse BLAS) material; this has been completely
rewritten, way beyond the intention(s) and responsibilities of the
original developers.
The main reference for the serial sparse BLAS is:
20 years ago
Duff, I., Marrone, M., Radicati, G., and Vittoli, C.
Level 3 basic linear algebra subprograms for sparse matrices: a user
level interface
ACM Trans. Math. Softw., 23(3), 379-401, 1997.
INSTALLING
To compile and run our software you will need the following
prerequisites (see also SERIAL below):
1. A working version of MPI
2. A version of the BLAS; if you don't have a specific version for
your platform you may try ATLAS available from
http://math-atlas.sourceforge.net/
3. We have had good results with the METIS library, from
http://www-users.cs.umn.edu/~karypis/metis/metis/main.html
psblas-dev: README base/comm/psb_dgather.f90 base/comm/psb_dhalo.f90 base/comm/psb_dovrl.f90 base/comm/psb_dscatter.F90 base/comm/psb_ihalo.f90 base/comm/psb_zgather.f90 base/comm/psb_zhalo.f90 base/comm/psb_zovrl.f90 base/comm/psb_zscatter.F90 base/internals/psi_dswapdata.F90 base/internals/psi_dswaptran.F90 base/internals/psi_iswapdata.F90 base/internals/psi_iswaptran.F90 base/internals/psi_zswapdata.F90 base/internals/psi_zswaptran.F90 base/modules/Makefile base/modules/cutil.c base/modules/fakempi.c base/modules/psb_comm_mod.f90 base/modules/psb_const_mod.f90 base/modules/psb_desc_type.f90 base/modules/psb_error_mod.F90 base/modules/psb_inter_desc_type.f90 base/modules/psb_penv_mod.F90 base/modules/psb_psblas_mod.f90 base/modules/psb_realloc_mod.F90 base/modules/psb_serial_mod.f90 base/modules/psb_sort_mod.f90 base/modules/psb_spmat_type.f90 base/modules/psb_spsb_mod.f90 base/modules/psb_tools_mod.f90 base/modules/psi_mod.f90 base/modules/psi_serial_mod.f90 base/psblas/psb_damax.f90 base/psblas/psb_dasum.f90 base/psblas/psb_daxpby.f90 base/psblas/psb_ddot.f90 base/psblas/psb_dnrm2.f90 base/psblas/psb_dnrmi.f90 base/psblas/psb_dspmm.f90 base/psblas/psb_dspsm.f90 base/psblas/psb_zamax.f90 base/psblas/psb_zasum.f90 base/psblas/psb_zaxpby.f90 base/psblas/psb_zdot.f90 base/psblas/psb_znrm2.f90 base/psblas/psb_znrmi.f90 base/psblas/psb_zspmm.f90 base/psblas/psb_zspsm.f90 base/serial/aux/dasr.f90 base/serial/aux/dasrx.f90 base/serial/aux/dmsort_dw.f90 base/serial/aux/dmsort_up.f90 base/serial/aux/dmsr.f90 base/serial/aux/dmsrx.f90 base/serial/aux/dsr.f90 base/serial/aux/dsrx.f90 base/serial/aux/zacmp_mod.f90 base/serial/aux/zalcmp_mod.f90 base/serial/aux/zalsr.f90 base/serial/aux/zalsrx.f90 base/serial/aux/zamsort_dw.f90 base/serial/aux/zamsort_up.f90 base/serial/aux/zamsr.f90 base/serial/aux/zamsrx.f90 base/serial/aux/zasr.f90 base/serial/aux/zasrx.f90 base/serial/aux/zlcmp_mod.f90 base/serial/aux/zlsr.f90 base/serial/aux/zlsrx.f90 base/serial/coo/dcoomm.f base/serial/coo/dcoomv.f base/serial/coo/dcoonrmi.f base/serial/coo/dcoorws.f base/serial/coo/dcoosm.f base/serial/coo/dcoosv.f base/serial/coo/zcoomm.f base/serial/coo/zcoomv.f base/serial/coo/zcoonrmi.f base/serial/coo/zcoorws.f base/serial/coo/zcoosm.f base/serial/coo/zcoosv.f base/serial/csr/dcrnrmi.f base/serial/csr/dcsrck.f base/serial/csr/dcsrmm.f base/serial/csr/dcsrmv.f base/serial/csr/dcsrmv2.f base/serial/csr/dcsrmv3.f base/serial/csr/dcsrmv4.f base/serial/csr/dcsrrws.f base/serial/csr/dcsrsm.f base/serial/csr/dcsrsv.f base/serial/csr/zcrnrmi.f base/serial/csr/zcsrck.f base/serial/csr/zcsrmm.f base/serial/csr/zcsrrws.f base/serial/csr/zcsrsm.f base/serial/csr/zsrmv.f base/serial/csr/zsrsv.f base/serial/dp/dcoco.f base/serial/dp/dcocr.f base/serial/dp/dcrco.f base/serial/dp/dcrcr.f base/serial/dp/dcrjd.f base/serial/dp/dcsrp1.f base/serial/dp/dcsrrp.f base/serial/dp/dgind_tri.f base/serial/dp/dgindex.f base/serial/dp/djadrp.f base/serial/dp/djadrp1.f base/serial/dp/djdco.f base/serial/dp/djdcox.f base/serial/dp/dvtfg.f base/serial/dp/reordvn.f base/serial/dp/zcoco.f base/serial/dp/zcocr.f base/serial/dp/zcrco.f base/serial/dp/zcrcr.f base/serial/dp/zcrjd.f base/serial/dp/zgind_tri.f base/serial/dp/zgindex.f base/serial/f77/daxpby.f base/serial/f77/dcsmm.f base/serial/f77/dcsnmi.f base/serial/f77/dcsrp.f base/serial/f77/dcsrws.f base/serial/f77/dcssm.f base/serial/f77/dgelp.f base/serial/f77/dlpupd.f base/serial/f77/dswmm.f base/serial/f77/dswsm.f base/serial/f77/smmp.f base/serial/f77/zaxpby.f base/serial/f77/zcsmm.f base/serial/f77/zcsnmi.f base/serial/f77/zcsrws.f base/serial/f77/zcssm.f base/serial/f77/zgelp.f base/serial/f77/zlpupd.f base/serial/f77/zswmm.f base/serial/f77/zswsm.f base/serial/jad/djadmm.f base/serial/jad/djadmv.f base/serial/jad/djadmv2.f base/serial/jad/djadmv3.f base/serial/jad/djadmv4.f base/serial/jad/djadnr.f base/serial/jad/djadrws.f base/serial/jad/djadsm.f base/serial/jad/djadsv.f base/serial/jad/djdnrmi.f base/serial/jad/djdrws.f base/serial/psb_dcoins.f90 base/serial/psb_dcsmm.f90 base/serial/psb_dcsmv.f90 base/serial/psb_dcsnmi.f90 base/serial/psb_dcsrp.f90 base/serial/psb_dcsrws.f90 base/serial/psb_dcssm.f90 base/serial/psb_dcssv.f90 base/serial/psb_dgelp.f90 base/serial/psb_dneigh.f90 base/serial/psb_dnumbmm.f90 base/serial/psb_dspcnv.f90 base/serial/psb_dspgetrow.f90 base/serial/psb_dspgtdiag.f90 base/serial/psb_dspscal.f90 base/serial/psb_dsymbmm.f90 base/serial/psb_getrow_mod.f90 base/serial/psb_regen_mod.f90 base/serial/psb_update_mod.f90 base/serial/psb_zcoins.f90 base/serial/psb_zcsmm.f90 base/serial/psb_zcsmv.f90 base/serial/psb_zcsnmi.f90 base/serial/psb_zcsrp.f90 base/serial/psb_zcsrws.f90 base/serial/psb_zcssm.f90 base/serial/psb_zcssv.f90 base/serial/psb_zgelp.f90 base/serial/psb_zneigh.f90 base/serial/psb_znumbmm.f90 base/serial/psb_zspcnv.f90 base/serial/psb_zspgetrow.f90 base/serial/psb_zspgtdiag.f90 base/serial/psb_zspscal.f90 base/serial/psb_zsymbmm.f90 base/tools/psb_dallc.f90 base/tools/psb_dasb.f90 base/tools/psb_dfree.f90 base/tools/psb_dins.f90 base/tools/psb_dsphalo.F90 base/tools/psb_dspins.f90 base/tools/psb_zallc.f90 base/tools/psb_zasb.f90 base/tools/psb_zfree.f90 base/tools/psb_zins.f90 base/tools/psb_zsphalo.F90 base/tools/psb_zspins.f90 docs/pdf/datastruct.tex docs/pdf/penv.tex docs/userguide.pdf krylov/psb_dbicg.f90 krylov/psb_dcg.f90 krylov/psb_dcgs.f90 krylov/psb_dcgstab.F90 krylov/psb_dcgstabl.f90 krylov/psb_drgmres.f90 krylov/psb_krylov_mod.f90 krylov/psb_zbicg.f90 krylov/psb_zcg.f90 krylov/psb_zcgs.f90 krylov/psb_zcgstab.f90 krylov/psb_zcgstabl.f90 krylov/psb_zrgmres.f90 prec/psb_dbjac_aply.f90 prec/psb_dbjac_bld.f90 prec/psb_dgprec_aply.f90 prec/psb_dilu_fct.f90 prec/psb_dprc_aply.f90 prec/psb_dprecset.f90 prec/psb_prec_mod.f90 prec/psb_prec_type.f90 prec/psb_zbjac_aply.f90 prec/psb_zbjac_bld.f90 prec/psb_zgprec_aply.f90 prec/psb_zilu_fct.f90 prec/psb_zprc_aply.f90 prec/psb_zprecset.f90 test/fileread/df_sample.f90 test/fileread/getp.f90 test/fileread/zf_sample.f90 test/pargen/ppde.f90 test/util/Makefile util/psb_hbio_mod.f90 util/psb_mat_dist_mod.f90 util/psb_metispart_mod.F90 util/psb_mmio_mod.f90 util/psb_read_mat_mod.f90 Merged kind type names changes from r:2905:2906 in branches/psblas-2.2-maint.
17 years ago
This is optional; it is used in the util and test/fileread
directories but only if you specify --with-metis.
4. If you have the AMD package of Davis, Duff and Amestoy, you can
specify --with-amd (see ./configure --help for more details).
The configure script will generate a Make.inc file suitable for
building the library.
The script is capable of recognizing the needed libraries with their
default names; if they are in unusual places consider adding the paths
with --with-libs, or explicitly specifying the names in --with-blas, etc.
Please note that a common way for the configure script to fail is to
specify inconsistent MPI vs. plain compilers, either directly or
indirectly via environment variables; e.g. specifying the Intel
compiler with FC=ifort while at the same time having an MPIFC=mpif90
which points to GNU Fortran.
The best way to avoid this situation is (in our opinion) to use the
environment modules package (see http://modules.sourceforge.net/), and
load the relevant variables with (e.g.)
module load gnu46 openmpi
This will delegate to the modules setup to make sure that the version
of openmpi in use is the one compiled with the gnu46 compilers.
After the configure script has completed you can always tweak the
Make.inc file yourself.
psblas-dev: README base/comm/psb_dgather.f90 base/comm/psb_dhalo.f90 base/comm/psb_dovrl.f90 base/comm/psb_dscatter.F90 base/comm/psb_ihalo.f90 base/comm/psb_zgather.f90 base/comm/psb_zhalo.f90 base/comm/psb_zovrl.f90 base/comm/psb_zscatter.F90 base/internals/psi_dswapdata.F90 base/internals/psi_dswaptran.F90 base/internals/psi_iswapdata.F90 base/internals/psi_iswaptran.F90 base/internals/psi_zswapdata.F90 base/internals/psi_zswaptran.F90 base/modules/Makefile base/modules/cutil.c base/modules/fakempi.c base/modules/psb_comm_mod.f90 base/modules/psb_const_mod.f90 base/modules/psb_desc_type.f90 base/modules/psb_error_mod.F90 base/modules/psb_inter_desc_type.f90 base/modules/psb_penv_mod.F90 base/modules/psb_psblas_mod.f90 base/modules/psb_realloc_mod.F90 base/modules/psb_serial_mod.f90 base/modules/psb_sort_mod.f90 base/modules/psb_spmat_type.f90 base/modules/psb_spsb_mod.f90 base/modules/psb_tools_mod.f90 base/modules/psi_mod.f90 base/modules/psi_serial_mod.f90 base/psblas/psb_damax.f90 base/psblas/psb_dasum.f90 base/psblas/psb_daxpby.f90 base/psblas/psb_ddot.f90 base/psblas/psb_dnrm2.f90 base/psblas/psb_dnrmi.f90 base/psblas/psb_dspmm.f90 base/psblas/psb_dspsm.f90 base/psblas/psb_zamax.f90 base/psblas/psb_zasum.f90 base/psblas/psb_zaxpby.f90 base/psblas/psb_zdot.f90 base/psblas/psb_znrm2.f90 base/psblas/psb_znrmi.f90 base/psblas/psb_zspmm.f90 base/psblas/psb_zspsm.f90 base/serial/aux/dasr.f90 base/serial/aux/dasrx.f90 base/serial/aux/dmsort_dw.f90 base/serial/aux/dmsort_up.f90 base/serial/aux/dmsr.f90 base/serial/aux/dmsrx.f90 base/serial/aux/dsr.f90 base/serial/aux/dsrx.f90 base/serial/aux/zacmp_mod.f90 base/serial/aux/zalcmp_mod.f90 base/serial/aux/zalsr.f90 base/serial/aux/zalsrx.f90 base/serial/aux/zamsort_dw.f90 base/serial/aux/zamsort_up.f90 base/serial/aux/zamsr.f90 base/serial/aux/zamsrx.f90 base/serial/aux/zasr.f90 base/serial/aux/zasrx.f90 base/serial/aux/zlcmp_mod.f90 base/serial/aux/zlsr.f90 base/serial/aux/zlsrx.f90 base/serial/coo/dcoomm.f base/serial/coo/dcoomv.f base/serial/coo/dcoonrmi.f base/serial/coo/dcoorws.f base/serial/coo/dcoosm.f base/serial/coo/dcoosv.f base/serial/coo/zcoomm.f base/serial/coo/zcoomv.f base/serial/coo/zcoonrmi.f base/serial/coo/zcoorws.f base/serial/coo/zcoosm.f base/serial/coo/zcoosv.f base/serial/csr/dcrnrmi.f base/serial/csr/dcsrck.f base/serial/csr/dcsrmm.f base/serial/csr/dcsrmv.f base/serial/csr/dcsrmv2.f base/serial/csr/dcsrmv3.f base/serial/csr/dcsrmv4.f base/serial/csr/dcsrrws.f base/serial/csr/dcsrsm.f base/serial/csr/dcsrsv.f base/serial/csr/zcrnrmi.f base/serial/csr/zcsrck.f base/serial/csr/zcsrmm.f base/serial/csr/zcsrrws.f base/serial/csr/zcsrsm.f base/serial/csr/zsrmv.f base/serial/csr/zsrsv.f base/serial/dp/dcoco.f base/serial/dp/dcocr.f base/serial/dp/dcrco.f base/serial/dp/dcrcr.f base/serial/dp/dcrjd.f base/serial/dp/dcsrp1.f base/serial/dp/dcsrrp.f base/serial/dp/dgind_tri.f base/serial/dp/dgindex.f base/serial/dp/djadrp.f base/serial/dp/djadrp1.f base/serial/dp/djdco.f base/serial/dp/djdcox.f base/serial/dp/dvtfg.f base/serial/dp/reordvn.f base/serial/dp/zcoco.f base/serial/dp/zcocr.f base/serial/dp/zcrco.f base/serial/dp/zcrcr.f base/serial/dp/zcrjd.f base/serial/dp/zgind_tri.f base/serial/dp/zgindex.f base/serial/f77/daxpby.f base/serial/f77/dcsmm.f base/serial/f77/dcsnmi.f base/serial/f77/dcsrp.f base/serial/f77/dcsrws.f base/serial/f77/dcssm.f base/serial/f77/dgelp.f base/serial/f77/dlpupd.f base/serial/f77/dswmm.f base/serial/f77/dswsm.f base/serial/f77/smmp.f base/serial/f77/zaxpby.f base/serial/f77/zcsmm.f base/serial/f77/zcsnmi.f base/serial/f77/zcsrws.f base/serial/f77/zcssm.f base/serial/f77/zgelp.f base/serial/f77/zlpupd.f base/serial/f77/zswmm.f base/serial/f77/zswsm.f base/serial/jad/djadmm.f base/serial/jad/djadmv.f base/serial/jad/djadmv2.f base/serial/jad/djadmv3.f base/serial/jad/djadmv4.f base/serial/jad/djadnr.f base/serial/jad/djadrws.f base/serial/jad/djadsm.f base/serial/jad/djadsv.f base/serial/jad/djdnrmi.f base/serial/jad/djdrws.f base/serial/psb_dcoins.f90 base/serial/psb_dcsmm.f90 base/serial/psb_dcsmv.f90 base/serial/psb_dcsnmi.f90 base/serial/psb_dcsrp.f90 base/serial/psb_dcsrws.f90 base/serial/psb_dcssm.f90 base/serial/psb_dcssv.f90 base/serial/psb_dgelp.f90 base/serial/psb_dneigh.f90 base/serial/psb_dnumbmm.f90 base/serial/psb_dspcnv.f90 base/serial/psb_dspgetrow.f90 base/serial/psb_dspgtdiag.f90 base/serial/psb_dspscal.f90 base/serial/psb_dsymbmm.f90 base/serial/psb_getrow_mod.f90 base/serial/psb_regen_mod.f90 base/serial/psb_update_mod.f90 base/serial/psb_zcoins.f90 base/serial/psb_zcsmm.f90 base/serial/psb_zcsmv.f90 base/serial/psb_zcsnmi.f90 base/serial/psb_zcsrp.f90 base/serial/psb_zcsrws.f90 base/serial/psb_zcssm.f90 base/serial/psb_zcssv.f90 base/serial/psb_zgelp.f90 base/serial/psb_zneigh.f90 base/serial/psb_znumbmm.f90 base/serial/psb_zspcnv.f90 base/serial/psb_zspgetrow.f90 base/serial/psb_zspgtdiag.f90 base/serial/psb_zspscal.f90 base/serial/psb_zsymbmm.f90 base/tools/psb_dallc.f90 base/tools/psb_dasb.f90 base/tools/psb_dfree.f90 base/tools/psb_dins.f90 base/tools/psb_dsphalo.F90 base/tools/psb_dspins.f90 base/tools/psb_zallc.f90 base/tools/psb_zasb.f90 base/tools/psb_zfree.f90 base/tools/psb_zins.f90 base/tools/psb_zsphalo.F90 base/tools/psb_zspins.f90 docs/pdf/datastruct.tex docs/pdf/penv.tex docs/userguide.pdf krylov/psb_dbicg.f90 krylov/psb_dcg.f90 krylov/psb_dcgs.f90 krylov/psb_dcgstab.F90 krylov/psb_dcgstabl.f90 krylov/psb_drgmres.f90 krylov/psb_krylov_mod.f90 krylov/psb_zbicg.f90 krylov/psb_zcg.f90 krylov/psb_zcgs.f90 krylov/psb_zcgstab.f90 krylov/psb_zcgstabl.f90 krylov/psb_zrgmres.f90 prec/psb_dbjac_aply.f90 prec/psb_dbjac_bld.f90 prec/psb_dgprec_aply.f90 prec/psb_dilu_fct.f90 prec/psb_dprc_aply.f90 prec/psb_dprecset.f90 prec/psb_prec_mod.f90 prec/psb_prec_type.f90 prec/psb_zbjac_aply.f90 prec/psb_zbjac_bld.f90 prec/psb_zgprec_aply.f90 prec/psb_zilu_fct.f90 prec/psb_zprc_aply.f90 prec/psb_zprecset.f90 test/fileread/df_sample.f90 test/fileread/getp.f90 test/fileread/zf_sample.f90 test/pargen/ppde.f90 test/util/Makefile util/psb_hbio_mod.f90 util/psb_mat_dist_mod.f90 util/psb_metispart_mod.F90 util/psb_mmio_mod.f90 util/psb_read_mat_mod.f90 Merged kind type names changes from r:2905:2906 in branches/psblas-2.2-maint.
17 years ago
After you have Make.inc fixed, run
make
to compile the library; go to the test directory and its
subdirectories to get test programs done.
If you specify --prefix=/path you can do make install and the
libraries will be installed under /path/lib, while the module files
will be installed under /path/include.
SERIAL
Configuring with --enable-serial will provide a fake MPI stub library
that enables running in pure serial mode; no MPI installation is
needed in this case (but note that the fake MPI stubs are only
guaranteed to cover what we use internally, it's not a complete
replacement).
EXPERIMENTAL
We have an experimental flag --enable-long-integers that will enable having
8-byte integer data, allowing an index space larger than 2G; some
small cases have been tested but we do not offer full guarantee (yet).
COMPILER NOTES.
This code is confirmed to work with the following compilers (or
later versions thereof):
NAGware 5.2;
GNU 4.6.1;
Cray CCE 8.0.1;
They are all recognized by the configure script.
To make the script work with the Cray CCE environment, it is
recommended to use the following:
./configure FC=ftn F77=ftn CC=cc MPF90=ftn MPF77=ftn MPCC=cc
with both CCE and GNU lower-level compilers.
XLF 13.1 configures correctly, but then fails with ICEs (Internal
Compiler Error) at build time. We do not yet know whether XLF 14
compiles correctly.
13 years ago
For the GNU compilers 4.6.x we are aware of a number of memory management
issues that might surface in your applications; all of them (that
we're aware of) are solved in version 4.7.0.
13 years ago
The Intel compiler up to version 12.1 fails to compile, as of the last
version we got access to.
KNOWN ISSUES.
13 years ago
An annoying problem exists with some versions of MPI: if the configure
script sets -DMPI_MOD the MPI call interfaces will be resolved by
using the MPI Fortran module.
However usage of the module may cause compilation to fail when
coupled with the debugging option -g, because the compiler complains
that it cannot find a matching interface for some of the
communication routines.
The solution: either take out the -g option, or, if you really need to
debug, edit Make.inc to force -DMPI_H in place of -DMPI_MOD.
20 years ago
TODO:
Fix all reamining bugs. Bugs? We dont' have any ! ;-)
20 years ago
The PSBLAS team.
RELATED SOFTWARE
If you are looking for more sophisticated preconditioners, you may be
interested in the package MLD2P4 from http://www.mld2p4.it
Contact: Salvatore Filippone salvatore.filippone@uniroma2.it
Credits for version 3.0:
Salvatore Filippone
Alfredo Buttari
Credits for version 2.2:
Michele Martone contributed the initial version of the configure
machinery.
Credits for version 2.0:
20 years ago
Salvatore Filippone
Alfredo Buttari
Credits for version 1.0:
17 years ago
Salvatore Filippone
Michele Colajanni
20 years ago
Fabio Cerioni
Stefano Maiolatesi
Dario Pascucci