   #[1]Monte Carlo eXtreme: GPU-based Monte Carlo Simulations

Installation Instructions for MCX

          1. [2]System Requirements

          2. [3]Download and Install

          3. [4]Testing hardware support

          4. [5]Testing hardware support for MCXLAB

          5. [6]Running MCX with GUI

          6. [7]Compiling MCX from source code

                6.1. [8]Download the source code

                6.2. [9]Install the compilers

                6.3. [10]Setup paths

                6.4. [11]make your binary

1. System Requirements

   We aim to port MCX for all modern GPUs. Currently, we have two MCX
   editions, the CUDA-edition is supported only on the NVIDIA graphics
   card, and an [12]OpenCL-edition, supported for all OpenCL-compliant
   computing devices (Intel/AMD CPUs, NVIDIA GPU and AMD GPUs, etc). In
   order to run MCX (CUDA-edition), you have to make sure you have the
   right hardware and software support, this includes:

     * a CUDA enabled graphics card made by NVIDIA
     * the latest graphics driver for the GPU, update from [13]NVIDIA's
       website.

   Starting from v0.9, MCX/MCXLAB released packages are compiled with CUDA
   library statically linked (embedded). Therefore, you do not need to
   install CUDA library in order to run MCX/MCXLAB.

   You must use a CUDA capable NVIDIA graphics card in order to use MCX. A
   list of CUDA capable cards can be found at [14]here. The oldest
   graphics card that MCX supports is the "Fermi" series (circa 2010).
   Using the latest NVIDIA card is expected to produce the best speed. The
   default release of MCX supports atomic operations and photon detection
   within a single binary. In the below webpage, we summarized the speed
   differences between different generations of NVIDIA GPUs

   [15]http://mcx.space/gpubench/

   Windows users: if you use [16]MCXStudio, please follow this video
   tutorial (Lesson 6) to apply a registry fix to enable MCX to run more
   than 5 seconds on your computer. Alternatively, you may use the Windows
   installer to install MCX. This is important!

   [17]http://mcx.space/wiki/index.cgi/wiki/index.cgi?Demo/MCXStudio#Lesso
   n_6_Fix_Unspecified_launch_failure_error_on_Windows_11_minutes

2. Download and Install

   To install MCX, you need to download the binary executable compiled for
   your computer architecture (32 or 64bit) and platform, extract the
   package and run the executable under the <mcx root>/bin directory.

3. Testing hardware support

   To test if your system supports MCX, you need to open a terminal (for
   Windows users, please click on the Start menu and type "cmd", then
   enter), and type

 cd "path/to/mcx/bin"

   where path/to/mcx/bin should be replaced to the actual extracted bin
   folder from the downloaded package. If your path contains space, you
   must enclose it with double-quotes.

   Once you are in the bin/ folder, you can then type

 mcx -L

   You may see 3 possible outcomes

     * 1. mcx successfully prints at least 1 supported GPU on your system
       - to this end, MCX is ready to use
     * 2. mcx shows the below error

 No CUDA-capable GPU device found

 MCX ERROR(-1):No GPU device found
  in unit mcextreme.c:54

   If your are certain your system has a working NVIDIA GPU, it is likely
   that your GPU driver was not up to date or was not installed properly.
   Please check your driver installation again.
     * 3. mcx gives an error or pops up an error window showing that some
       libraries (*.dll on Windows, or *.so on Linux, or *.dylib on Mac)
       are missing. If the missing library is a CUDA library, that means
       the binary was not compiled with static-linking and you must
       download the library file separately. You may google this missing
       file, and download it and place it inside your system folder.

   In the event that your system does not have supported GPU, you may
   consider using [18]MCX-CL instead - MCX-CL has the same functionality
   as MCX but it can also be executed on AMD/Intel CPUs and GPUs.

4. Testing hardware support for MCXLAB

   If you use MCXLAB, you may use the below procedure to test if it can
   use your GPU. First, open MATLAB or octave, then type

 addpath('/path/to/mcxlab/')

   so that mcx.mex* file is in the search path. You may type

 which mcx

   or
 which mcxlab

   to confirm it is added to MATLAB. Then you can use the below command to
   query your GPUs

 info=mcxlab('gpuinfo')

   You must see valid output from this call, otherwise, your system does
   not have GPU or it is not properly configured to run MCXLAB.

5. Running MCX with GUI

   If you are used to graphics interfaces, you can find an executable
   mcxstudio under the same folder as mcx. [19]MCX Studio is a
   cross-platform interface to interact with MCX. It gives users a
   straightforward way to set various of parameters for a MCX session, and
   organize different sessions into projects that can be saved for later
   use. Please read [20]README to see how to use this tool to create, run
   and save the simulation sessions.

6. Compiling MCX from source code

   If you want to compile an executable on your machine from the source
   code, you should follow the steps described below:

   To compile MCX/MCXLAB, you need to install [21]CUDA toolkit (version
   7-10 is supported). Once you install the CUDA library, you need to
   setup the system environment variable in order to let the compiler find
   the needed CUDA run-time library. For Linux and Mac OS users, you might
   need to add the following settings to your shell initialization file.
   Use "echo $SHELL" command to identify your shell type. For c-shell,
   i.e. csh/tcsh, add the following lines to your ~/.cshrc file
  if ("uname -p" =~ "*_64" ) then
          setenv LD_LIBRARY_PATH "/usr/local/cuda/lib64"
  else
          setenv LD_LIBRARY_PATH "/usr/local/cuda/lib"
  endif
  setenv PATH "/usr/local/cuda/bin:$PATH"

   and for "bash" or "sh" users, add
  if [[ "uname -p" =~ .*_64 ]]; then
          export LD_LIBRARY_PATH="/usr/local/cuda/lib64"
  else
          export LD_LIBRARY_PATH="/usr/local/cuda/lib"
  fi
  export PATH="/usr/local/cuda/bin:$PATH"

   to your ~/.bash_profile. If the libcudart.so* file is installed in a
   non-standard folder, please replace the paths in the above scripts to
   your installation path where libcudart.so resides.

6.1. Download the source code

   You need to first download the source code from the [22]Download page.

6.2. Install the compilers

   You need install the CUDA and C compilers on your system, this includes
     * 1. CUDA compiler and run-time libraries: this will be installed
       when you download and install the CUDA driver/sdk/tools from
       [23]this link
     * 2. GNU toolchain: you need to have gcc and make commands on your
       system. Usually
          + for Debian-based Linux users, you can get these basic
            compiling tools by a single command:
sudo apt-get install build-essential
            and then type your own password
          + for Redhat-based systems:
su -c 'yum groupinstall "Development Tools"'
            and then type the root password
          + for Windows users, you need to install [24]MinGW, a minimum
            Unix system on Windows, the [25]automatic-installer can be
            downloaded from [26]here.
          + for Mac OS users, the GNU compilers can be installed from the
            Xcode tools from [27]this link
     * 3. For Windows, you also need to install [28]Microsoft Visual C++
       200x Express Edition (or the full version; the Express edition is
       free. MCX was tested with VC++2005).

6.3. Setup paths

   For Linux/Mac OS users, you need to make sure you have followed the
   instructions to setup the paths described in the "Running MCX" section.

   For Windows, one need to add the path to nvcc (by default,
   C:\CUDA\bin), path to cl.exe (by default, C:\Program Files\Microsoft
   Visual Studio 8\VC\bin) and path to gcc/make (by default, C:\MinGW\bin)
   to your Path environment variable. You can follow the screenshots as in
   [29]this tutorial, and paste the following string at the beginning of
   the variable value field.
 C:\Program Files\Microsoft Visual Studio 8\VC\bin;C:\MinGW\bin;C:\CUDA\bin;

   If you have installed VC2008, you need to replace "Microsoft Visual
   Studio 8" to "Microsoft Visual Studio 9".

   If you have installed CUDA, MSVC or MinGW at a non-standard location,
   please open the Makefile under <mcx>/src to update all the
   library/include directories to the actual path.

6.4. make your binary

   For Linux/Mac OS, you need to open an terminal, "cd" to <mcx>/src, and
   type "make". This will compile MCX with the default option, i.e.
   non-atomic memory write, LL5 RNG and fast-math library. You can "cat
   Makefile" and see other options. If everything is working ok, you
   should see a binary file generated under <mcx>/bin.

   For Windows, you need to double click on a shortcut named "MSYS", a
   terminal will pop up. Then type "cd /path/to/your/mcx/src", then type
   "make". The binary will be generated as <mcx>/bin/mcx.exe.

References

   1. http://mcx.space/wiki/index.cgi?action=rss
   2. https://mcx.space/wiki/index.cgi?Doc/Installation#System_Requirements
   3. https://mcx.space/wiki/index.cgi?Doc/Installation#Download_and_Install
   4. https://mcx.space/wiki/index.cgi?Doc/Installation#Testing_hardware_support
   5. https://mcx.space/wiki/index.cgi?Doc/Installation#Testing_hardware_support_for_MCXLAB
   6. https://mcx.space/wiki/index.cgi?Doc/Installation#Running_MCX_with_GUI
   7. https://mcx.space/wiki/index.cgi?Doc/Installation#Compiling_MCX_from_source_code
   8. https://mcx.space/wiki/index.cgi?Doc/Installation#Download_the_source_code
   9. https://mcx.space/wiki/index.cgi?Doc/Installation#Install_the_compilers
  10. https://mcx.space/wiki/index.cgi?Doc/Installation#Setup_paths
  11. https://mcx.space/wiki/index.cgi?Doc/Installation#make_your_binary
  12. https://mcx.space/wiki/index.cgi?MCXCL
  13. https://www.nvidia.com/Download/index.aspx
  14. https://developer.nvidia.com/cuda-gpus
  15. http://mcx.space/gpubench/
  16. https://mcx.space/wiki/index.cgi?Learn#mcxstudio
  17. http://mcx.space/wiki/index.cgi/wiki/index.cgi?Demo/MCXStudio#Lesson_6_Fix_Unspecified_launch_failure_error_on_Windows_11_minutes
  18. https://mcx.space/wiki/index.cgi?MCXCL
  19. https://mcx.space/wiki/index.cgi?Doc/MCXStudio
  20. https://mcx.space/wiki/index.cgi?Doc/README
  21. https://developer.nvidia.com/cuda-toolkit
  22. https://mcx.space/wiki/index.cgi?Download
  23. http://www.nvidia.com/object/cuda_get.html
  24. http://www.mingw.org/
  25. http://sourceforge.net/projects/mingw/files/
  26. http://sourceforge.net/projects/mingw/files/Automated MinGW Installer/
  27. http://developer.apple.com/technology/xcode.html
  28. http://www.microsoft.com/Express/VC/
  29. http://technet.microsoft.com/en-us/library/aa997841(EXCHG.65).aspx
