In computer science, partitioned global address space (PGAS) is a parallel programming model paradigm. PGAS is typified by communication operations involving a global memory

address space In computing, an address space defines a range of discrete addresses, each of which may correspond to a network host, peripheral device, disk sector, a memory cell or other logical or physical entity. For software programs to save and retrieve s ...

abstraction that is logically partitioned, where a portion is local to each process, thread, or

processing element This glossary of computer hardware terms is a list of definitions of terms and concepts related to computer hardware, i.e. the physical and structural components of computers, architectural issues, and peripheral devices. A ...

. The novelty of PGAS is that the portions of the shared memory space may have an affinity for a particular process, thereby exploiting locality of reference in order to improve performance. A PGAS memory model is featured in various parallel programming languages and libraries, including:

Coarray Fortran Coarray Fortran (CAF), formerly known as F--, started as an extension of Fortran 95/2003 for parallel processing created by Robert Numrich and John Reid in the 1990s. The Fortran 2008 standard (ISO/IEC 1539-1:2010) now includes coarrays (spel ...

Unified Parallel C Unified Parallel C (UPC) is an extension of the C programming language designed for high-performance computing on large-scale parallel machines, including those with a common global address space ( SMP and NUMA) and those with distributed memory ...

Split-C

Fortress A fortification is a military construction or building designed for the defense of territories in warfare, and is also used to establish rule in a region during peacetime. The term is derived from Latin ''fortis'' ("strong") and ''facere'' ...

Chapel A chapel is a Christian place of prayer and worship that is usually relatively small. The term has several meanings. Firstly, smaller spaces inside a church that have their own altar are often called chapels; the Lady chapel is a common type ...

, X10
UPC++Coarray C++

Global Arrays Global Arrays, or GA, is the library developed by scientists at Pacific Northwest National Laboratory for parallel computing. GA provides a friendly API for shared-memory programming on distributed-memory computers for multidimensional arrays. Th ...

DASH
and SHMEM. The PGAS paradigm is now an integrated part of the Fortran language, as of Fortran 2008 which standardized coarrays. The various languages and libraries offering a PGAS memory model differ widely in other details, such as the base programming language and the mechanisms used to express parallelism. Many PGAS systems combine the advantages of a SPMD programming style for distributed memory systems (as employed by

MPI MPI or Mpi may refer to: Science and technology Biology and medicine * Magnetic particle imaging, an emerging non-invasive tomographic technique * Myocardial perfusion imaging, a nuclear medicine procedure that illustrates the function of the hear ...

) with the data referencing semantics of shared memory systems. In contrast to message passing, PGAS programming models frequently offer one-sided communication operations such as Remote Memory Access (RMA), whereby one processing element may directly access memory with affinity to a different (potentially remote) process, without explicit semantic involvement by the passive target process. PGAS offers more efficiency and scalability than traditional shared-memory approaches with a flat address space, because hardware-specific

data locality In computer science, locality of reference, also known as the principle of locality, is the tendency of a processor to access the same set of memory locations repetitively over a short period of time. There are two basic types of reference localit ...

can be explicitly exposed in the semantic partitioning of the address space. A variant of the PGAS paradigm, asynchronous partitioned global address space (APGAS) augments the programming model with facilities for both local and remote asynchronous task creation. Two programming languages that use this model are

and X10.

Examples

now an integrated part of the language as of Fortran 2008 *

an explicitly parallel SPMD dialect of the ISO

C programming language ''The C Programming Language'' (sometimes termed ''K&R'', after its authors' initials) is a computer programming book written by Brian Kernighan and Dennis Ritchie, the latter of whom originally designed and implemented the language, as well a ...

a parallel language originally developed by

Cray Cray Inc., a subsidiary of Hewlett Packard Enterprise, is an American supercomputer manufacturer headquartered in Seattle, Washington. It also manufactures systems for data storage and analytics. Several Cray supercomputer systems are listed i ...

under the DARPA HPCS project
UPC++
A

C++ C, or c, is the third letter in the Latin alphabet, used in the modern English alphabet, the alphabets of other western European languages and others worldwide. Its name in English is ''cee'' (pronounced ), plural ''cees''. History "C" ...

template library that provides PGAS communication operations designed to support high-performance computing on

exascale Exascale computing refers to computing systems capable of calculating at least "1018 IEEE 754 Double Precision (64-bit) operations (multiplications and/or additions) per second ( exaFLOPS)"; it is a measure of supercomputer performance. Exascale ...

supercomputers, including Remote Memory Access (RMA) and Remote Procedure Call (RPC)
Coarray C++
a

library developed by Cray, providing a close analog to Fortran coarray functionality *

a library supporting parallel scientific computing on distributed arrays
DASH
a

template library for distributed data structures with support for hierarchical locality * SHMEM a family of libraries supporting parallel scientific computing on distributed arrays * X10 a parallel language developed by IBM under the DARPA HPCS project *

a parallel language developed by Sun Microsystems under the DARPA HPCS project
Titanium
an explicitly parallel dialect of Java developed at UC Berkeley to support scientific high-performance computing on large-scale multiprocessors
Split-C
a parallel extension of the

that supports efficient access to a global address space * The Adapteva Epiphany architecture is a manycore

network on a chip A network on a chip or network-on-chip (NoC or )This article uses the convention that "NoC" is pronounced . Therefore, it uses the convention "a" for the indefinite article corresponding to NoC ("a NoC"). Other sources may pronounce it as a ...

processor with

scratchpad memory Scratchpad memory (SPM), also known as scratchpad, scratchpad RAM or local store in computer terminology, is a high-speed internal memory used for temporary storage of calculations, data, and other work in progress. In reference to a microproces ...

addressable between cores.

External links

*
An Introduction to the Partitioned Global Address Space Model

Programming in the Partitioned Global Address Space Model
(2003)
GASNet Communication System
- provides a software infrastructure for PGAS languages over high-performance networksBonachea D, Hargrove
GASNet-EX: A High-Performance, Portable Communication Library for Exascale
Proceedings of Languages and Compilers for Parallel Computing (LCPC'18). Oct 2018. https://doi.org/10.25344/S4QP4W

References

{{Parallel Computing

Programming model A programming model is an execution model coupled to an API or a particular pattern of code. In this style, there are actually two execution models in play: the execution model of the base programming language and the execution model of the prog ...

Programming paradigms

Examples

See also

External links

References