Versions Compared

Old Version 4

changes.mady.by.user Imam, Dr. Shams Mahmood

Saved on

compared with

New Version 19

changes.mady.by.user Cave, Vincent

Saved on

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.

CnC-Python    Image Added

Section
Column
width60%

The CnC-Python system under development in the Habanero project at Rice University builds on past work on the Intel Concurrent Collections (CnC) and Habanero CnC projects.  

A short introduction to the Concurrent Collections model can be found in the following article:

  • The Concurrent Collections Programming Model.  Michael G. Burke, Kathleen Knobe, Ryan Newton, Vivek Sarkar.  Technical Report TR 10-12, Department of Computer Science, Rice University, December 2010.  To appear as a book chapter in Encyclopedia of Parallel Computing, David Padua (Ed.), Springer Verlag, 2011.

To get started with CnC-Python, see the startup instructions for the Rice SUG@R system, or the more general installation instructions.

Once successfully installed, please refer to the following initial examples on how to write CnC-Python programs: Find Primes and Partition String.

Column
width35%
Page Tree Search

Habanero Home

Research Projects

Publications

Target Applications

Multicore Platforms

People

Related Links

Installation instructions:

1. Install babel from https://computation.llnl.gov/casc/components/#page=home

while installing these commands may be helpful:

  • ../babel/configure --prefix=/Users/shamsimam/softwares --enable-maintainer-mode --enable-python LDFLAGS=-L/Users/shamsimam/softwares/lib JAVAPREFIX=/System/Library/Frameworks/JavaVM.framework/Home JNI_INCLUDES=/System/Library/Frameworks/JavaVM.framework/Home/include
  • make -j4
  • sudo make install
  • make check

make check is optional and may take a long while to complete.

2. After installing babel run the following command:
babel-config --dump | grep SUPPORT

you should get output as follows:
SUPPORT_FORTRAN77="false"
SUPPORT_CXX="true"
SUPPORT_JAVA="true"
SUPPORT_PYTHON="true"
SUPPORT_FORTRAN90="false"
SUPPORT_FORTRAN03="false"
SUPPORT_STATIC="true"
SUPPORT_SHARED="true"
BABEL_SUPPORTED_LANGUAGES="c cxx f77 f90 f03 java python"

ensure that Java and Python are supported.

3. Once babel is installed, you now need to install cnc-babel.
Run "ant clean && ant" on the directory to have cnc-babel installed.
Remember to set CNC_HOME environment variable to the distribution directory, this will be used by some later scripts

4. Running examples, e.g. cholesky

...