   This program is a demonstration of optimization techniques 
   for Intel Xeon processors and Intel Xeon Phi coprocessors:
   a particle binning micro-kernel.
   
   Copyright (c) 2015, Colfax International

   For more information, refer to the 3-part series of publications
   "Optimization Techniques for the Intel MIC Architecture" 
   at Colfax Research:
      http://colfaxresearch.com/?p=6
      http://colfaxresearch.com/?p=709
      http://colfaxresearch.com/?p=1231

   Authors: 
            andrey@colfax-intl.com  Andrey Vladimirov
            ryo@colfax-intl.com     Ryo Asai
            phi@colfax-intl.com     General inquiries

REQUIREMENTS:
  - Intel C++ compiler version 15.0 or greater;
  - Multi-core processor based on Intel architecture;
  - Optionally: an Intel Xeon Phi coprocessor of the 1st generation
  - Linux operating system in order to use the included
    Makefile and benchmark script.

EXAMPLES OF USAGE:
  - To compile the code, run "make"
  - To run a benchmark on the host CPU, run "make run-cpu"
  - To run a benchmark on the coprocessor, run "make run-mic"
  - To produce a single-precision version of the code, 
    edit the Makefile so that the line 
    #PRECISION=-DDOUBLE_PRECISION
    is commented out (i.e., has a # character at the beginning)
  - To produce a double-precision version of the code, 
    edit the Makefile so that the line 
    PRECISION=-DDOUBLE_PRECISION
    is not commented out (i.e., does not have a # character at the beginning)
