Editing Parallel package

The Parallel execution package provides utilities to work with clusters, but also functions to parallelize work among cores of a single machine.

To install: {{Codeline|pkg install -forge parallel}}

And then, once on each octave session, {{Codeline|pkg load parallel}}

== multicore parallelization (parcellfun, pararrayfun) ==


See also the [[NDpar package]], for an extension of these functions to N-dimensional arrays

=== calculation on a single array ===

{{Code|simple|<pre>
# fun is the function to apply 
fun = @(x) x^2;

vector_x = 1:10;

vector_y = pararrayfun(nproc, fun, vector_x)
</pre>
}}

should output

<code><pre>
parcellfun: 10/10 jobs done

vector_y =

     1     4     9    16    25    36    49    64    81   100
</pre></code>

{{Codeline|nproc}} returns the number of cpus available (number of cores or twice as much with hyperthreading). One can use {{Codeline|nproc - 1}} instead, in order to leave one cpu free for instance.

{{Codeline|fun}} can be replaced by {{Codeline|@myfun}} if the function resides in the {{Codeline|myfun.m}} file.

In the previous example, the function was executed once for each element of the input {{Codeline|vector_x}}.
If the function is vectorized (can act on a vector and not just on scalar input), then it can be much more efficient to use the {{Codeline|"Vectorized", true}} option.

{{Code|vectorized|<pre>
# fun is the function to apply, vectorized (see the dot)
fun = @(x) x.^2;

vector_x = 1:10;

vector_y = pararrayfun(nproc, fun, vector_x, "Vectorized", true, "ChunksPerProc", 1)
</pre>
}}
should output

<code><pre>
parcellfun: 4/4 jobs done
vector_y =

     1     4     9    16    25    36    49    64    81   100
</pre></code>

The {{Codeline|"ChunksPerProc"}} option is mandatory with {{Codeline|"Vectorized", true}}. {{Codeline|1}} means that each proc will do its job in one shot (chunk). This number can be increased to use less memory for instance. A higher number of {{Codeline|"ChunksPerProc"}} allows also more flexibility in case of long calculations on a busy machine. If one cpu has finished all its jobs, it can take over the pending jobs of another.

=== Output in cell arrays ===

The following sample code was an answer to [http://stackoverflow.com/questions/27422219/for-every-row-reshape-and-calculate-eigenvectors-in-a-vectorized-way this question]. The goal was to diagonalize 2x2 matrices contained as rows of a 2d array (each row of the array being a flattened 2x2 matrix).

{{code|diagonalize NxN matrices contained in an array|
<pre>
A = [0.6060168 0.8340029 0.0064574 0.7133187;
0.6325375 0.0919912 0.5692567 0.7432627;
0.8292699 0.5136958 0.4171895 0.2530783;
0.7966113 0.1975865 0.6687064 0.3226548;
0.0163615 0.2123476 0.9868179 0.1478827];

N = 2;
[eigenvectors, eigenvalues] = pararrayfun(nproc, 
                                @(row_idx) eig(reshape(A(row_idx, :), N, N)), 
                                1:rows(A), "UniformOutput", false)
</pre>
}}

With {{codeline|"UniformOutput", false}}, the outputs are contained in cell arrays (one cell per slice). In the sample above, both {{codeline|eigenvectors}} and {{codeline|eigenvalues}} are {{codeline|1x5}} cell arrays.

== cluster operation ==

Documentation can be found in the {{codeline|README.parallel}} or {{codeline|README.bw}} files, located inside the {{codeline|doc}} directory of the parallel package.

[[Category:Octave Forge]]