The Perl Toolchain Summit needs more sponsors. If your company depends on Perl, please support this very important event.

NAME

PDLA::ParallelCPU - Parallel Processor MultiThreading Support in PDLA (Experimental)

DESCRIPTION

PDLA has support (currently experimental) for splitting up numerical processing between multiple parallel processor threads (or pthreads) using the set_autopthread_targ and set_autopthread_size functions. This can improve processing performance (by greater than 2-4X in most cases) by taking advantage of multi-core and/or multi-processor machines.

SYNOPSIS

  use PDLA;
  
  # Set target of 4 parallel pthreads to create, with a lower limit of
  #  5Meg elements for splitting processing into parallel pthreads.
  set_autopthread_targ(4);
  set_autopthread_size(5);
  
  $x = zeroes(5000,5000); # Create 25Meg element array
  
  $y = $x + 5; # Processing will be split up into multiple pthreads
  
  # Get the actual number of pthreads for the last
  #  processing operation.
  $actualPthreads = get_autopthread_actual();
  

Terminology

The use of the term threading can be confusing with PDLA, because it can refer to PDLA threading, as defined in the PDLA::Threading docs, or to processor multi-threading.

To reduce confusion with the existing PDLA threading terminology, this document uses pthreading to refer to processor multi-threading, which is the use of multiple processor threads to split up numerical processing into parallel operations.

Functions that control PDLA PThreads

This is a brief listing and description of the PDLA pthreading functions, see the PDLA::Core docs for detailed information.

set_autopthread_targ

Set the target number of processor-threads (pthreads) for multi-threaded processing. Setting auto_pthread_targ to 0 means that no pthreading will occur.

See PDLA::Core for details.

set_autopthread_size

Set the minimum size (in Meg-elements or 2**20 elements) of the largest PDLA involved in a function where auto-pthreading will be performed. For small PDLAs, it probably isn't worth starting multiple pthreads, so this function is used to define a minimum threshold where auto-pthreading won't be attempted.

See PDLA::Core for details.

get_autopthread_actual

Get the actual number of pthreads executed for the last pdl processing function.

See PDLA::get_autopthread_actual for details.

Global Control of PDLA PThreading using Environment Variables

PDLA PThreading can be globally turned on, without modifying existing code by setting environment variables PDLA_AUTOPTHREAD_TARG and PDLA_AUTOPTHREAD_SIZE before running a PDLA script. These environment variables are checked when PDLA starts up and calls to set_autopthread_targ and set_autopthread_size functions made with the environment variable's values.

For example, if the environment var PDLA_AUTOPTHREAD_TARG is set to 3, and PDLA_AUTOPTHREAD_SIZE is set to 10, then any pdl script will run as if the following lines were at the top of the file:

 set_autopthread_targ(3);
 set_autopthread_size(10);

How It Works

The auto-pthreading process works by analyzing threaded array dimensions in PDLA operations and splitting up processing based on the thread dimension sizes and desired number of pthreads (i.e. the pthread target or pthread_targ). The offsets and increments that PDLA uses to step thru the data in memory are modified for each pthread so each one sees a different set of data when performing processing.

Example

 $x = sequence(20,4,3); # Small 3-D Array, size 20,4,3
 
 # Setup auto-pthreading:
 set_autopthread_targ(2); # Target of 2 pthreads
 set_autopthread_size(0); # Zero so that the small PDLAs in this example will be pthreaded

 # This will be split up into 2 pthreads
 $c = maximum($x);

For the above example, the maximum function has a signature of (a(n); [o]c()), which means that the first dimension of $x (size 20) is a Core dimension of the maximum function. The other dimensions of $x (size 4,3) are threaded dimensions (i.e. will be threaded-over in the maximum function.

The auto-pthreading algorithm examines the threaded dims of size (4,3) and picks the 4 dimension, since it is evenly divisible by the autopthread_targ of 2. The processing of the maximum function is then split into two pthreads on the size-4 dimension, with dim indexes 0,2 processed by one pthread and dim indexes 1,3 processed by the other pthread.

Limitations

Must have POSIX Threads Enabled

Auto-PThreading only works if your PDLA installation was compiled with POSIX threads enabled. This is normally the case if you are running on linux, or other unix variants.

Non-Threadsafe Code

Not all the libraries that PDLA intefaces to are thread-safe, i.e. they aren't written to operate in a multi-threaded environment without crashing or causing side-effects. Some examples in the PDLA core is the fft function and the pnmout functions.

To operate properly with these types of functions, the PPCode flag NoPthread has been introduced to indicate a function as not being pthread-safe. See PDLA::PP docs for details.

Size of PDLA Dimensions and PThread Target

Due to the way a PDLA is split-up for operation using multiple pthreads, the size of a dimension must be evenly divisible by the pthread target. For example, if a PDLA has threaded dimension sizes of (4,3,3) and the auto_pthread_targ has been set to 2, then the first threaded dimension (size 4) will be picked to be split up into two pthreads of size 2 and 2. However, if the threaded dimension sizes are (3,3,3) and the auto_pthread_targ is still 2, then pthreading won't occur, because no threaded dimensions are divisible by 2.

The algorithm that picks the actual number of pthreads has some smarts (but could probably be improved) to adjust down from the auto_pthread_targ to get a number of pthreads that can evenly divide one of the threaded dimensions. For example, if a PDLA has threaded dimension sizes of (9,2,2) and the auto_pthread_targ is 4, the algorithm will see that no dimension is divisible by 4, then adjust down the target to 3, resulting in splitting up the first threaded dimension (size 9) into 3 pthreads.

Speed improvement might be less than you expect.

If you have a 8 core machine and call auto_pthread_targ with 8 to generate 8 parallel pthreads, you probably won't get a 8X improvement in speed, due to memory bandwidth issues. Even though you have 8 separate CPUs crunching away on data, you will have (for most common machine architectures) common RAM that now becomes your bottleneck. For simple calculations (e.g simple additions) you can run into a performance limit at about 4 pthreads. For more complex calculations the limit will be higher.

COPYRIGHT

Copyright 2011 John Cerney. You can distribute and/or modify this document under the same terms as the current Perl license.

See: http://dev.perl.org/licenses/