function [job,ch] = job_config(example, ...
                               cluster_name, ...
                               partition_name, ...
                               walltime, ...
                               tasks_per_node, ...
                               num_worker)

%===============================================================================
% MATLAB MPS EXAMPLE
% -> configuration script to initialze MPS and submit job 
%===============================================================================
% input:
% example .................... name of user function without extension ".m"
% cluster_name ............... name of cluster, e. g.: cm4 (refers to the HPC
%                              machine, e.g. CoolMUC-4)
% partition_name ............. name of queue/partition, e. g.: cm4_std
%                              Details on cluster/partition names:
%                              https://doku.lrz.de/x/AgaVAg
% walltime, tasks_per_node ... equivalent to Slurm parameters
% num_worker ................. number of MPS workers
% return values:
% job ........................ job handle
% ch ......................... cluster object handle
%===============================================================================

%===============================================================================
% Step 1: cluster configuration
%===============================================================================
configCluster(cluster_name, partition_name);

%===============================================================================
% Step 2: job configuration
%===============================================================================
ch = parcluster;
jobdir = fullfile(getenv('SCRATCH'), 'MdcsDataLocation/coolmuc/', version('-release'));
if ~exist(jobdir)
    mkdir(jobdir);
end
ch.JobStorageLocation = jobdir; 
ch.AdditionalProperties.WallTime = walltime;
ch.AdditionalProperties.ProcsPerNode = tasks_per_node;
ch.saveProfile;

%===============================================================================
% Step 3: job submission to Slurm
%===============================================================================
% Command:
%   job = ch.batch(@myfunction, n_arg_out, {arg_in_1, ..., arg_in_n}, 'Pool', np)
% Input:
%   @myfunc ...... reference to user-defined function/script myfunc.m
%   n_arg_out .... number of expected output arguments
%   {arg_in_#} ... list of input arguments of myfunction
%   'Pool', np ... key-value-pair: define size of pool (number of workers)
%
% Help via Matlab commands:
%   help batch
%   doc batch

fhandle = eval(sprintf('@%s', example));
job = ch.batch(fhandle, 4, {}, 'Pool', num_worker);

function [nlabs,comptime,Cref,Cfin] = myfunction_spmd

%===================================================================
% MATLAB EXAMPLE: PARALLEL HELLO WORLD USING PCT TOOLBOX
%                 -> matrix-matrix multiplication C = A*B
%
% return values:
% nlabs ...... total number of workers (just FYI and used by data
%              distribution functions)
% comptime ... time needed for multiplication
% Cref ....... reference result obtained from serial computation
% Cfin ....... result obtained from parallel computation
%===================================================================

%===================================================================
% Input
%===================================================================
% exemplary matrices
SIZE_A = [2000 100];
SIZE_B = [100 8000];

A = zeros(SIZE_A);
B = zeros(SIZE_B);

for n=1:SIZE_A(1)
    A(n,:) = linspace(1,n, SIZE_A(2));
end
for n=1:SIZE_B(1)
    B(n,:) = linspace(1,n, SIZE_B(2));
end

% reference result
Cref = A*B;

%===================================================================
% Manage parallel pool
%===================================================================
% get number of workers:
spmd
    nl = numlabs;
end
nlabs = nl{:};

% disallow Threading
maxNumCompThreads(1);

%===================================================================
% Parallel work
%===================================================================
SIZE_C = [SIZE_A(1) SIZE_B(2)];

% parallel environment
spmd
    % distribute data to all workers
    Ad = codistributed(A, codistributor2dbc([nlabs 1]));
    Bd = codistributed(B, codistributor2dbc([1 nlabs]));
    Cd = zeros(SIZE_C, codistributor2dbc([1 nlabs]));

    % timing
    tic;
    Cd = Ad*Bd;
    t = toc;
end

% collect data from all workers => final result
Cfin = gather(Cd);

comptime = t{:}

function [nlabs,comptime,Cref,C] = myfunc_parfor

%===================================================================
% MATLAB EXAMPLE: PARALLEL HELLO WORLD USING PCT TOOLBOX
%                 -> matrix-matrix multiplication C = A*B
%
% return values:
% nlabs ...... total number of workers (just FYI and used by data
%              distribution functions)
% comptime ... time needed for multiplication
% Cref ....... reference result obtained from serial computation
% Cfin ....... result obtained from parallel computation
%===================================================================

%===================================================================
% Input
%===================================================================
% exemplary matrices
SIZE_A = [2000 100];
SIZE_B = [100 8000];

A = zeros(SIZE_A);
B = zeros(SIZE_B);

for n=1:SIZE_A(1)
    A(n,:) = linspace(1,n, SIZE_A(2));
end
for n=1:SIZE_B(1)
    B(n,:) = linspace(1,n, SIZE_B(2));
end

% reference result
Cref = A*B;

%===================================================================
% Manage parallel pool
%===================================================================
% get number of workers:
spmd
    nl = numlabs;
end
nlabs = nl{:};

% disallow Threading
maxNumCompThreads(1);

%===================================================================
% Parallel work
%===================================================================
SIZE_C = [SIZE_A(1) SIZE_B(2)];
C = zeros(SIZE_C);

% timing
tic;
% parallel environment
parfor n=1:SIZE_A(1)
    % compute
    C(n,:) = A(n,:)*B;
end
comptime = toc;