add readme

Author: Ehsan Totoni

README.rst

@@ -0,0 +1,58 @@
+*****
+HPAT
+*****
+
+A compiler-based framework for big data in Python
+#################################################
+
+High Performance Analytics Toolkit (HPAT) is a compiler-based framework for big
+data analytics and machine learning on cluster/cloud environments that
+is both easy to use and extremely fast; it is orders of magnitude faster than
+alternatives like `Apache Spark <http://spark.apache.org/>`_.
+
+HPAT automatically or semi-automatically parallelizes analytics tasks written in
+Numpy and pandas and generates efficient MPI code using Numba and LLVM.
+These academic papers describe the underlying methods in HPAT:
+
+- `HPAT paper at ICS'17 <http://dl.acm.org/citation.cfm?id=3079099>`_
+- `HPAT at HotOS'17 <http://dl.acm.org/citation.cfm?id=3103004>`_
+- `HiFrames on arxiv <https://arxiv.org/abs/1704.02341>`_
+
+Installing HPAT
+===============
+
+These commands install HPAT and its dependencies such as Numba, LLVM and HDF5
+on Ubuntu Linux::
+
+    $ sudo apt install llvm-4.0 make libc6-dev gcc-4.8
+    $ # download and install Anaconda python distribution
+    $ conda create -n HPAT
+    $ source activate HPAT
+    $ conda install numpy scipy pandas gcc mpich2 llvmlite
+    $ git clone https://github.com/IntelLabs/numba.git
+    $ cd numba
+    $ git checkout hpat_req
+    $ python setup.py develop
+    $ cd ..
+    $ # download hdf5 and cd inside
+    $ CC=mpicc CXX=mpicxx ./configure --enable-parallel
+    $ make; make install
+    $ cd ..
+    $ export HDF5_DIR=/home/user/hdf5-1.10.1/hdf5/
+    $ export C_INCLUDE_PATH=$C_INCLUDE_PATH:$HDF5_DIR/include
+    $ export CPLUS_INCLUDE_PATH=$CPLUS_INCLUDE_PATH:$HDF5_DIR/include
+    $ export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:$HDF5_DIR/lib
+    $ export LIBRARY_PATH=$LIBRARY_PATH:$HDF5_DIR/lib
+    $ git clone https://github.com/h5py/h5py.git
+    $ cd h5py
+    $ python setup.py configure --hdf5=$HDF5_DIR
+    $ LDSHARED="mpicc -shared" CXX=mpicxx LD=mpicc CC="mpicc" python setup.py install
+    $ cd ..
+    $ git clone https://github.com/IntelLabs/hpat.git
+    $ cd hpat
+    $ LDSHARED="mpicxx -shared" CXX=mpicxx LD=mpicxx CC="mpicxx -std=c++11" python setup.py develop
+
+Commands for running the logistic regression example::
+
+    $ python generate_data/gen_logistic_regression.py
+    $ mpirun -n 2 python examples/logistic_regression.py