Global collective reduction operation mismatch sample

In this sample processes with odd rank numbers use MPI_MAX as a reduction operation, the others use MPI_MIN.

Usage Instructions:

Linux*:

Ensure that the corresponding compiler, Intel® MPI Library, and Intel® Trace Analyzer and Collector are already in your PATH, and complete these steps:
1. Build the sample:
  $ make
2. Run the sample:
  $ make run
3. Review the output.
Microsoft* Windows*:

Ensure that the corresponding compilers, Microsoft* Visual Studio*, Intel® MPI Library, and Intel® Trace Analyzer and Collector are already in your PATH, and complete these steps:
1. Build the sample:
  > build.bat release
2. Run the sample:
  > build.bat run
3. Review the output.

System Requirements:

Hardware:
Systems based on the Intel® 64 architecture:
- Intel® Core™ processor family or higher
- Intel® Xeon® processors recommended
- 1 GB of RAM per core
- 2 GB of RAM per core recommended
- 1 GB of free hard disk space
For Linux*:
Operating Systems:
- Red Hat* Enterprise Linux* 6, 7
- Fedora* 20, 21
- CentOS* 6.0
- SuSE* Linux Enterprise Server* 11, 12
- Ubuntu* LTS 12.04, 14.04
- Debian* 6, 7
MPI implementations:
- Intel® MPI Library 4.x
- Intel® MPI Library 5.x
Compilers:
- GNU*: C, C++, Fortran 77 3.3 or newer, Fortran 95 4.0 or newer
- Intel® Composer XE 2015 or newer
For Microsoft* Windows*:
Operating Systems:
- Microsoft* Windows HPC Server* 2012
- Microsoft* Windows HPC Server* 2016
- Microsoft* Windows 7*
- Microsoft* Windows 10*
MPI implementations:
- Intel® MPI Library 4.x
- Intel® MPI Library 5.x
Compilers:
- Intel® Composer XE 2015 or newer
- Microsoft* Visual Studio 2013*
- Microsoft* Visual Studio 2015*