Sieve C++ Parallel Programming System: Difference between revisions

Revision as of 19:47, 17 May 2018

Latest revision as of 23:06, 18 November 2024

(6 intermediate revisions by 5 users not shown)

Line 8:

* Only functions annotated with sieve or immediate can be called.

Delaying side-effects removes many small dependencies which would usually impede automatic parallelization. Reads and writes can be safely reordered by the compiler as to allow better use of various data movement mechanisms, such as [[Direct Memory Access]](DMA). In addition, [[alias analysis]] and [[dataflow analysis]] can be simplified [http://www.cl.cam.ac.uk/~al407/research/papers/eupar07.pdf]{{Dead link|date=November 2024 |bot=InternetArchiveBot |fix-attempted=yes }}. The compiler can then split up code within the sieve block much easier, to exploit parallelism.

==Memory Configuration==

This separation of scopes also means the Sieve System can be used in non-uniform memory architectures. Multi-core CPUs such as the [[Cell microprocessor]] used in the [[PlayStation 3]] are of this type, in which the fast cores have local memories that must be utilized to exploit performance inherent in the system. It is also able to work on shared memory systems, like x86, meaning it can run on various architectures. Sieve blocks can also be nested [httphttps://www.cs.cmu.edu/~damp/finalPapers/lindley.pdf] for systems with a hierarchy of different memories and processing elements.

==Parallelization and Scalability==

The sieve compiler can split code within a sieve block into chunks either implicitly or explicitly though a 'splithere' statement. For instance, the following example shows parallelizing a loop:

<sourcesyntaxhighlight lang="cpp">

sieve

{

Line 24:

}

}

</syntaxhighlight>

</source>

The compiler will implicitly add a splitpoint above the for loop construct body, as an entry point. Similarly one will be added after as an exit point.

In the Sieve System, only local variables to the sieve block scope may have dependencies. However, these dependencies must not cross splitpoints; they will generate compiler warnings {{Citation needed|date=May 2009}}. In order to parallelize this loop, a special 'Iterator' class may be used in place of a standard integer looping counter. It is safe for parallelization, and the programmer is free to create new Iterator classes at will [https://web.archive.org/web/20080723192430/http://codeplaysoftware.typepad.com/codeplay/2007/05/loop_carried_de.html]{{dead link|date=May 2018 |bot=InternetArchiveBot |fix-attempted=yes }}. In addition to these Iterator classes, the programmer is free to implement classes called 'Accumulators' which are used to carry out reduction operations.

The way the Iterator classes are implemented opens up various means for scalability. The Sieve Parallel Runtime employs dynamic [[speculative execution]] when executing on a target platform. This can yield very good speedups, however running on a single core machine can incur overheads [https://web.archive.org/web/20070827225352/http://www.codeplay.com/technology/sievebenchmarks.html].

==Determinism==

Determinism is an unusual feature of the Sieve System. If executing a parallel Sieve program on a multi core machine yields a bug, the bug will not disappear when run on a single core to aid [[debugging]][https://web.archive.org/web/20070321082311/http://www.codeplay.com/downloads_public/sievepaper-2columns-normal.pdf][http://www.cl.cam.ac.uk/~al407/research/papers/eupar07.pdf]{{Dead link|date=November 2024 |bot=InternetArchiveBot |fix-attempted=yes }}. This has the advantage of eliminating [[race conditions]], one of the most common bugs in [[concurrent programming]]. The removal of the need to consider [[concurrency control]] structures within a sieve block can speed up development time and results in safer code.

==Supported Systems==

The system is designed for hierarchical based systems with homogeneous or heterogeneous CPU cores which have local memories, connected via DMA engines or similar memory transfer models.

Sieve has been shown [https://web.archive.org/web/20070827225352/http://www.codeplay.com/technology/sievebenchmarks.html] successfully operating on multi-core x86 systems, the [[Ageia]] [[PhysX]] [[Physics Processing Unit]], and the IBM [[Cell microprocessor]]. [[ANSI C]] is generated if a compiler [[code generation (compiler)|code generator]] is not available for a certain target platform. This allows for autoparallelization using existing C compilation toolkits [http://mgrid.feis.herts.ac.uk/wp-content/scott.ppt]{{dead link|date=May 2018 |bot=InternetArchiveBot |fix-attempted=yes }}.

==See also==

Line 48:

==References==

*[http://www.cl.cam.ac.uk/~al407/research/papers/hppc07.pdf Auto-parallelisation of Sieve C++ Programs]{{Dead link|date=November 2024 |bot=InternetArchiveBot |fix-attempted=yes }} Alastair Donaldson, Anton Lokhmotov, Colin Riley, Andrew Cook. In Proceedings of the Euro-Par Workshop Highly Parallel Processing on a Chip (HPPC'07), Rennes, France, August 2007. Lecture Notes in Computer Science 4854, 2007.

*[http://www.cl.cam.ac.uk/~al407/research/papers/eupar07.pdf Delayed Side-effects Ease Multi-core Programming]{{Dead link|date=November 2024 |bot=InternetArchiveBot |fix-attempted=yes }} Anton Lokhmotov, Alan Mycroft, Andrew Richards. In Proceedings of the 13th International Euro-Par Conference, Rennes, France, August 2007. Lecture Notes in Computer Science 4641, 641-650, 2007.

*[httphttps://www.cs.cmu.edu/~damp/finalPapers/lindley.pdf Implementing deterministic declarative concurrency using sieves] S. Lindley. In proceedings of DAMP 2007: Workshop on Declarative Aspects of Multicore Programming Nice, France, January 2007.

*[https://web.archive.org/web/20070321082311/http://www.codeplay.com/downloads_public/sievepaper-2columns-normal.pdf The Codeplay Sieve C++ Parallel Programming System] A. Richards. White paper, 2006.

*[http://mgrid.feis.herts.ac.uk/wp-content/scott.ppt Codeplay Sieve C++ System Presentation]{{dead link|date=May 2018 |bot=InternetArchiveBot |fix-attempted=yes }} Scott McKenzie, presented at [https://web.archive.org/web/20070217065730/http://mgrid.feis.herts.ac.uk/ MicroGrid 2006].