A parallel programming model is a concept that enables the expression of parallel programs which can be compiled and executed. The value of a programming model is usually judged on its generality: how well a range of different problems can be expressed and how well they execute on a range of different architectures. The implementation of a programming model can take several forms such as libraries invoked from traditional sequential languages, language extensions, or complete new execution models.

Consensus on a particular programming model is important as it enables software expressed within it to be transportable between different architectures. The von Neumann model has facilitated this with sequential architectures as it provides an efficient bridge between hardware and software, meaning that high-level languages can be efficiently compiled to it and it can be efficiently implemented in hardware^[1].

Main classifications and paradigms

Classifications of parallel programming models can be divided broadly into two areas: process interaction and problem decomposition.

Process interaction

Process interaction relates to the mechanisms by which parallel processes are able to communicate with each other. The most common forms of interaction are shared memory and message passing, but it can also be implicit.

Shared memory

In a shared memory model, parallel tasks share a global address space which they read and write to asynchronously. This requires protection mechanisms such as locks, semaphores and monitors to control concurrent access. Shared memory can be emulated on distributed-memory systems but non-uniform memory access (NUMA) times can come in to play.

Message passing

In a message passing model, parallel tasks exchange data through passing messages to one another. These communications can be asynchronous or synchronous. The Communicating Sequential Processes (CSP) formalisation of message-passing employed communication channels to 'connect' processes, and led to a number of important languages such as Joyce, occam and Erlang.

Implicit

In an implicit model, no process interaction is visible to the programmer, instead the compiler and/or runtime is responsible for performing it. This is most common with domain-specific languages where the concurrency within a problem can be more prescribed.

Problem decomposition

Any parallel program is composed of simultaneously executing processes, problem decomposition relates to the way in which these processes are formulated. This classification may also be referred to as algorithmic skeletons or parallel programming paradigms.

Task parallelism

A task-parallel model focuses on processes, or threads of execution. These processes will often be behaviourally distinct, which emphasises the need for communication. Task parallelism is a natural way to express message-passing communication. It is usually classified as MIMD/MPMD or MISD.

Data parallelism

A data-parallel model focuses on performing operations on a data set which is usually regularly structured in an array. A set of tasks will operate on this data, but independently on separate partitions. In a shared memory system, the data will be accessible to all, but in a distributed-memory system it will divided between memories and worked on locally. Data parallelism is usually classified as SIMD/SPMD.

Example parallel programming models

• Algorithmic Skeletons
• Components
• Distributed Objects
• Remote Method Invocation
• Workflows
• Parallel Random Access Machine
• Stream processing
• Bulk synchronous parallelism

See also

• List of concurrent and parallel programming languages
• Bridging model
• Concurrency
• Automatic parallelization
• Degree of parallelism
• Partitioned global address space

References

Further reading

• H. Shan and J. Pal Singh. A comparison of MPI, SHMEM, and Cache-Coherent Shared Address Space Programming Models on a Tightly-Coupled Multiprocessor. International Journal of Parallel Programming, 29(3), 2001.
• H. Shan and J. Pal Singh. Comparison of Three Programming Models for Adaptive Applications on the Origin 2000. Journal of Parallel and Distributed Computing, 62:241–266, 2002.
• About structured parallel programming: Davide Pasetto and Marco Vanneschi. Machine independent Analytical models for cost evaluation of template--based programs, University of Pisa, 1996
• J. Darlinton, M. Ghanem, H. W. To (1993), "Structured Parallel Programming", In Programming Models for Massively Parallel Computers. IEEE Computer Society Press. 1993, http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.37.4610 

External links

• Developing Parallel Programs — A Discussion of Popular Models (Oracle White Paper September 2010)
• Designing and Building Parallel Programs (Section 1.3, 'A Parallel Programming Model')
• Introduction to Parallel Computing (Section 'Parallel Programming Models')

Parallel computing General Cloud computing High-performance computing Cluster computing Distributed computing Grid computing Levels Bit Instruction Data Task Threads Superthreading Hyperthreading Theory Amdahl's law Gustafson's law Cost efficiency Karp–Flatt metric slowdown speedup Elements Process Thread Fiber PRAM Instruction window Coordination Multiprocessing Multithreading (computer architecture) Memory coherency Cache coherency Cache invalidation Barrier Synchronization Application checkpointing Programming Models Implicit parallelism Explicit parallelism Concurrency Flynn's taxonomy SISD SIMD MISD MIMD SPMD Thread (computer science) Non-blocking algorithm Hardware Multiprocessor Symmetric Asymmetric Memory NUMA COMA distributed shared distributed shared SMT MPP Superscalar Vector processor Supercomputer Beowulf APIs Ateji PX POSIX Threads OpenMP OpenHMPP OpenACC PVM MPI UPC Intel Threading Building Blocks Boost.Thread Global Arrays Charm++ Cilk Co-array Fortran OpenCL CUDA Dryad Problems Embarrassingly parallel Grand Challenge Software lockout Scalability Race conditions Deadlock Livelock Deterministic algorithm Parallel slowdown Category Commons