User manual MATLAB PARALLEL COMPUTING TOOLBOX RELEASE NOTES

[. . . ] Parallel Computing ToolboxTM Release Notes How to Contact The MathWorks Web Newsgroup www. mathworks. com/contact_TS. html Technical Support www. mathworks. com comp. soft-sys. matlab suggest@mathworks. com bugs@mathworks. com doc@mathworks. com service@mathworks. com info@mathworks. com Product enhancement suggestions Bug reports Documentation error reports Order status, license renewals, passcodes Sales, pricing, and general information 508-647-7000 (Phone) 508-647-7001 (Fax) The MathWorks, Inc. 3 Apple Hill Drive Natick, MA 01760-2098 For contact information about worldwide offices, see the MathWorks Web site. Parallel Computing ToolboxTM Release Notes © COPYRIGHT 2006­2010 by The MathWorks, Inc. The software described in this document is furnished under a license agreement. The software may be used or copied only under the terms of the license agreement. [. . . ] · Compiled Parallel Computing Toolbox applications do not support Simulink software. For a list of other unsupported products, see the Web page http://www. mathworks. com/products/ineligible_programs/. · When workers are running a task from compiled code, they can execute only compiled code and toolbox code. They cannot execute functions contained in the current directory. Batch and MATLAB pool jobs attempt to change the worker working directory to the client working directory. When noncompiled files in the current directory conflict with compiled versions (for example, files with different extensions), an error is thrown. spmd Construct A new single program multiple data (spmd) language construct allows enhanced interleaving of serial and parallel programming, with interlab communication. The general form of an spmd statement is: spmd <statements> end The block of code represented by <statements> executes in parallel on workers in the MATLAB pool. Data on the labs is available for access from the client via Composite objects. For more information, see the spmd reference page and "Using Distributed Arrays, spmd, and Composites". Compatibility Considerations Because spmd is a new keyword, it will conflict with any user-defined functions or variables of the same name. If you have any code with functions or variables named spmd, you must rename them. 17 Parallel Computing ToolboxTM Release Notes Composite Objects Composite objects provide direct access from the client (desktop) program to data that is stored on labs in the MATLAB pool. The data of variables assigned inside an spmd block is available via Composites in the client. When a MATLAB pool is open, you can also create Composites directly from the client using the Composite function. See also "Using Distributed Arrays, spmd, and Composites". Configuration Validation The Configurations Manager is enhanced with the capability for validating configurations. Open the Configurations Manager on the MATLAB Desktop by clicking Parallel > Manage Configurations. For more information, see "Validating Configurations". Rerunning Failed Tasks When using a job manager, if a task does not complete due to certain system failures, it can attempt to rerun up to a specified number of times. New properties of a task object to control reruns and access information about rerun attempts are: · MaximumNumberOfRetries · AttemptedNumberOfRetries · FailedAttemptInformation Enhanced Job Control with Generic Scheduler Interface The generic scheduler interface now allows you to cancel and destroy jobs and tasks and to investigate the state of a job. The following new properties of the generic scheduler object facilitate these features: · GetJobStateFcn · DestroyJobFcn · DestroyTaskFcn · CancelJobFcn 18 Version 4. 0 (R2008b) Parallel Computing ToolboxTM Software · CancelTaskFcn New toolbox functions to accommodate this ability are: · getJobSchedulerData · setJobSchedulerData For more information on this new functionality, see "Managing Jobs". Changed Function Names for Codistributed Arrays What was known in previous releases as distributed arrays are henceforth called codistributed arrays. Some functions related to constructing and accessing codistributed arrays have changed names in this release. Compatibility Considerations The following table summarizes the changes in function names relating to codistributed arrays. The first three functions behave exactly the same with no change in operation, arguments, etc. The isa function takes the argument 'codistributed' in addition to the array in question. Old Function Name distributed distributor dcolon isdistributed New Function Name codistributed codistributor codcolon isa(X, 'codistributed') Determining if a MATLAB Pool is Open The function matlabpool now allows you to discover if a pool of workers is already open. The form of the command is: matlabpool size For more information about this option and others, see the matlabpool reference page. 19 Parallel Computing ToolboxTM Release Notes Version 3. 3 (R2008a) Parallel Computing Toolbox Software This table summarizes what is new in Version 3. 3 (R2008a): New Features and Changes Yes Details below Version Compatibility Considerations Yes -- Details labeled as Compatibility Considerations, below. [. . . ] This ensures that the set of random numbers generated for each task or lab within a job is unique, even when you have more than 82 tasks or labs. Compatibility Considerations In the previous version of the distributed computing products, the rand function could by default generate the same set of numbers for some tasks or labs when these exceeded 82 for a job. Single-Threaded Computations on Workers Despite the ability in MATLAB software to perform multithreaded computations on multiple-CPU machines, the workers and labs running distributed and parallel jobs perform only single-threaded computations, so that multiprocessor cluster machines can better accommodate multiple workers or labs. 31 Parallel Computing ToolboxTM Release Notes Version 3. 0 (R2006b) Distributed Computing Toolbox Software This table summarizes what is new in Version 3. 0 (R2006b): New Features and Changes Yes Details below Version Compatibility Considerations Yes -- Details labeled as Compatibility Considerations, below. Fixed Bugs and Known Problems Bug Reports Includes fixes Related Documentation at Web Site No New features and changes introduced in this version are · "Support for Windows Compute Cluster Server (CCS)" on page 32 · "Windows 64 Support" on page 33 · "Parallel Job Enhancements" on page 33 · "Distributed Arrays" on page 33 · "Interactive Parallel Mode (pmode)" on page 34 · "Moved MDCE Control Scripts" on page 34 · "rand Seeding Unique for Each Task or Lab" on page 35 · "Task ID Property Now Same as labindex" on page 36 Support for Windows Compute Cluster Server (CCS) Distributed Computing Toolbox software and MATLAB® Distributed Computing EngineTM software now let you program jobs and run them on a Windows Compute Cluster Server. For information about programming in the toolbox to use Windows Compute Cluster Server (CCS) as your scheduler, see the findResource reference page, and see also "Find a Windows HPC Server Scheduler". 32 Version 3. 0 (R2006b) Distributed Computing ToolboxTM Software Windows 64 Support The distributed computing products now support Windows 64 (Win64) for both MATLAB client and MATLAB worker machines. Parallel Job Enhancements Parallel Jobs Support Any Scheduler Support for parallel jobs now extends to any type of scheduler. In previous releases, only the MathWorks job manager and mpiexec scheduler object supported parallel jobs. [. . . ]