==================
MAGMA README FILE
==================

* To INSTALL MAGMA, modify the make.inc file to indicate where 
  CUDA, CPU BLAS, and LAPACK are installed on your system. Examples are given
  in make.inc.mkl-*, make.inc.acml, make.inc.atlas, and make.inc.macos
  showing how to link to MKL, ACML, ATLAS, and MacOS veclib BLAS, respectively.
  
  The make.inc files assume $CUDADIR is set in your environment.
  For bash (sh), put in ~/.bashrc (with your system's path):
      export CUDADIR=/usr/loca/cuda
  For csh/tcsh, put in ~/.cshrc:
      setenv CUDADIR /usr/local/cuda
  
  The MKL make.inc files assume $MKLROOT is set in your environment.
  For bash (sh), put in ~/.bashrc (with your system's path):
      source /opt/intel/composerxe/mkl/bin/mklvars.sh intel64
  For csh/tcsh, put in ~/.cshrc:
      source /opt/intel/composerxe/mkl/bin/mklvars.csh intel64
  
  The ACML make.inc file assumes $ACMLDIR and $CBLASDIR are set in your environment.
  If not installed, install CBLAS from http://www.netlib.org/blas/
  For bash (sh), put in ~/.bashrc (with your system's path):
      export ACMLDIR=/opt/acml-4.4.0/gfortran64_mp
      export CBLASDIR=/opt/CBLAS
  For csh/tcsh, put in ~/.cshrc:
      setenv ACMLDIR  /opt/acml-4.4.0/gfortran64_mp
      setenv CBLASDIR /opt/CBLAS
  
  The ATLAS make.inc file assumes $ATLASDIR and $LAPACKDIR are set in your environment.
  If not installed, install LAPACK from http://www.netlib.org/lapack/
  For bash (sh), put in ~/.bashrc (with your system's path):
      export ATLASDIR=/opt/atlas
      export LAPACKDIR=/opt/LAPACK
  For csh/tcsh, put in ~/.cshrc:
      setenv ATLASDIR  /opt/atlas
      setenv LAPACKDIR /opt/LAPACK
  
  Creating a shared library requires adding the -fPIC option in make.inc to
  OPTS, FOPTS, F77OPTS, and NVOPTS. This is demonstrated in make.inc.mkl-shared.
  
  After proper modification of the make.inc file, running:
  
      make
  
  will create libmagma.a in 'lib' and testing drivers in 'testing'.
  With the appropriate -fPIC options in make.inc, running:
  
      make shared
      make testing
  
  will create both libmagma.a and libmagma.so, and the testers.
  
  To install libraries and include files in a given prefix, run:
  
      make install prefix=/usr/local/magma
  
  The default prefix is /usr/local/magma. You can also set prefix in make.inc.
  
  For multi-GPU functions, set $MAGMA_NUM_GPUS to set the number of GPUs to use.
  For multi-core BLAS libraries, set $OMP_NUM_THREADS or $MKL_NUM_THREADS or
  $VECLIB_MAXIMUM_THREADS to set the number of CPU threads, depending on your
  BLAS library.

* A short standalone EXAMPLE is provided in directory 'example'. This is
  intended to show the minimum needed to start using MAGMA, without all the
  extra Makefiles, headers, and libraries used in testing. You must edit
  example/Makefile to reflect your make.inc, or use pkg-config, as described in
  example/README.txt.

* To TEST MAGMA, go to directory 'testing'. Provided are a number of
  drivers testing different routines. These drivers are also useful
  as examples on how to use MAGMA, as well as to benchmark the performance.

  The testers print "ok" or "failed" for whether the error passes the tolerance.
  In some cases, the tolerance may be too strict, so a test may "fail" even
  though it is only slightly above the tolerance. Error values around 1e-15 for
  double and double-complex, and 1e-7 for single and single-complex, are
  generally acceptable. Values larger than 1e-4 are very suspicious.

* To TUNE MAGMA, you can modify the blocking factors for the algorithms of
  interest in file 'control/get_nb.cpp'. The default values are tuned for
  general Tesla (1.x), Fermi (2.x), and Kepler (3.x) GPUs. If you have 
  a Fermi (C2050), you can also compare your performance to what we get, 
  given in file 'testing/results_fermi.txt', as an easy check for your 
  installation.

* To RUN EXPERIMENTAL MAGMA, go to directory 'exp' and type 'make'.  Then 
  type 'export MKL_NUM_THREADS=1'.  Next go to directory 'testing'.  
  Provided are drivers testing multi-core Choleskey, QR, and LU; and 
  single GPU all, available CPU cores QR.  Typing a given driver name will 
  result in clear instructions on what to provide on the command line.  

  Note that on some systems the experimental code must be linked against 
  sequential MKL.  If you notice excessively poor performance, change 
  make.inc to link against sequential MKL.

For more INFORMATION, please refer to the MAGMA homepage and user forum:
  
  http://icl.cs.utk.edu/magma/
  http://icl.cs.utk.edu/magma/forum/

The MAGMA project supports the package in the sense that reports of 
errors or poor performance will gain immediate attention from the 
developers. Such reports, descriptions of interesting applications, 
and other comments should be posted on the MAGMA user forum.