Category:Parallel programming - Revision history

Joel Hedlund (NSC) at 08:10, 4 June 2012

2012-06-04T08:10:02Z

Joel Hedlund (NSC) at 07:25, 4 June 2012

2012-06-04T07:25:41Z

Joel Hedlund (NSC) at 07:25, 4 June 2012

2012-06-04T07:25:23Z

Joachim Hein (LUNARC) at 17:00, 24 October 2011

2011-10-24T17:00:05Z

Joachim Hein (LUNARC) at 16:58, 24 October 2011

2011-10-24T16:58:05Z

Joachim Hein (LUNARC) at 16:01, 24 October 2011

2011-10-24T16:01:34Z

Joachim Hein (LUNARC) at 15:14, 24 October 2011

2011-10-24T15:14:15Z

Joachim Hein (LUNARC) at 14:59, 24 October 2011

2011-10-24T14:59:53Z

Joachim Hein (LUNARC) at 08:17, 24 October 2011

2011-10-24T08:17:21Z

Joachim Hein (LUNARC): Created page with "Category:Area of expertise In a parallel program, the computational work to be performed by the application is divided into a number of work packages. These work packages c..."

2011-10-24T08:10:55Z

Created page with "Category:Area of expertise In a parallel program, the computational work to be performed by the application is divided into a number of work packages. These work packages c..."

New page

[[Category:Area of expertise]]

In a parallel program, the computational work to be performed by the application is divided into a number of work packages. These work packages can then be assigned to a number of processing elements (e.g. cores on a modern multi-core processors or GPU) and have them executed independently. This should deliver a faster time to solution, when compared to utilising a single processing element only. By deploying several hundreds or thousands of processing elements, calculations which would otherwise take many years to complete can be completed in month or even weeks.

In a typical parallel program the work packages are however not fully independent. They frequently require access to data generated or modified on other processing elements. This data then needs communicating. When using a distributed memory system communication is typically facilitated by deploying some form of message passing. On a shared memory system (e.g. multi core system) all computational threads have access to a common shared memory space, which allows data communication between the processing elements.

== Experts ==
{{list experts}}

← Older revision		Revision as of 08:10, 4 June 2012
Line 1:		Line 1:
		+	[[Category:Computational science]]
	{{field info		{{field info
	\|description=programming with multiple threads or processes		\|description=programming with multiple threads or processes

@@ Line 11: / Line 11: @@
 {{list general experts}}
 == Software ==
 {{list software for category}}

@@ Line 1: / Line 1: @@
-[[Category:Area of expertise]]
+{{field info
 In a parallel program, the computational work to be performed by the application is divided into a number of work packages.  These work packages can then be assigned to a number of processing elements (e.g. cores on a modern multi-core processors or GPU) and have them executed independently.  This should deliver a faster time to solution, when compared to utilising a single processing element only.  By deploying several hundreds or thousands of processing elements, calculations which would otherwise take many years to complete can be completed in month or even weeks.
@@ Line 5: / Line 8: @@
 In a typical parallel program the work packages are however not fully independent.  They frequently require access to data generated or modified on other processing elements.  This data then needs communicating.  When using a [[distributed memory programming|distributed memory]] system communication is typically facilitated by deploying some form of [[message passing]].  On a shared memory system (e.g. multi core system) one has a choice of using message passing or [[shared memory programming]] techniques. When using shared memory programming one spawns a number of threads, which have access to a common shared memory space.  The threads communicate by writing data to and reading data from this shared space.
-== Experts ==
+== Software ==
-{{list experts}}
+{{list software for category}}

← Older revision		Revision as of 16:01, 24 October 2011
Line 3:		Line 3:
	In a parallel program, the computational work to be performed by the application is divided into a number of work packages. These work packages can then be assigned to a number of processing elements (e.g. cores on a modern multi-core processors or GPU) and have them executed independently. This should deliver a faster time to solution, when compared to utilising a single processing element only. By deploying several hundreds or thousands of processing elements, calculations which would otherwise take many years to complete can be completed in month or even weeks.		In a parallel program, the computational work to be performed by the application is divided into a number of work packages. These work packages can then be assigned to a number of processing elements (e.g. cores on a modern multi-core processors or GPU) and have them executed independently. This should deliver a faster time to solution, when compared to utilising a single processing element only. By deploying several hundreds or thousands of processing elements, calculations which would otherwise take many years to complete can be completed in month or even weeks.

−	In a typical parallel program the work packages are however not fully independent. They frequently require access to data generated or modified on other processing elements. This data then needs communicating. When using a [[distributed memory programming\|distributed memory]] system communication is typically facilitated by deploying some form of [[message passing]]. On a [[shared memory]] system (e.g. multi core system) all computational threads have access to a common shared memory space, which allows data communication between the processing elements.	+	In a typical parallel program the work packages are however not fully independent. They frequently require access to data generated or modified on other processing elements. This data then needs communicating. When using a [[distributed memory programming\|distributed memory]] system communication is typically facilitated by deploying some form of [[message passing]]. On a [[shared memory programming\|shared memory]] system (e.g. multi core system) all computational threads have access to a common shared memory space, which allows data communication between the processing elements.

← Older revision		Revision as of 15:14, 24 October 2011
Line 3:		Line 3:
	In a parallel program, the computational work to be performed by the application is divided into a number of work packages. These work packages can then be assigned to a number of processing elements (e.g. cores on a modern multi-core processors or GPU) and have them executed independently. This should deliver a faster time to solution, when compared to utilising a single processing element only. By deploying several hundreds or thousands of processing elements, calculations which would otherwise take many years to complete can be completed in month or even weeks.		In a parallel program, the computational work to be performed by the application is divided into a number of work packages. These work packages can then be assigned to a number of processing elements (e.g. cores on a modern multi-core processors or GPU) and have them executed independently. This should deliver a faster time to solution, when compared to utilising a single processing element only. By deploying several hundreds or thousands of processing elements, calculations which would otherwise take many years to complete can be completed in month or even weeks.

−	In a typical parallel program the work packages are however not fully independent. They frequently require access to data generated or modified on other processing elements. This data then needs communicating. When using a [[distributed memory]] system communication is typically facilitated by deploying some form of [[message passing]]. On a [[shared memory]] system (e.g. multi core system) all computational threads have access to a common shared memory space, which allows data communication between the processing elements.	+	In a typical parallel program the work packages are however not fully independent. They frequently require access to data generated or modified on other processing elements. This data then needs communicating. When using a [[distributed memory programming\|distributed memory]] system communication is typically facilitated by deploying some form of [[message passing]]. On a [[shared memory]] system (e.g. multi core system) all computational threads have access to a common shared memory space, which allows data communication between the processing elements.

← Older revision		Revision as of 14:59, 24 October 2011
Line 3:		Line 3:
	In a parallel program, the computational work to be performed by the application is divided into a number of work packages. These work packages can then be assigned to a number of processing elements (e.g. cores on a modern multi-core processors or GPU) and have them executed independently. This should deliver a faster time to solution, when compared to utilising a single processing element only. By deploying several hundreds or thousands of processing elements, calculations which would otherwise take many years to complete can be completed in month or even weeks.		In a parallel program, the computational work to be performed by the application is divided into a number of work packages. These work packages can then be assigned to a number of processing elements (e.g. cores on a modern multi-core processors or GPU) and have them executed independently. This should deliver a faster time to solution, when compared to utilising a single processing element only. By deploying several hundreds or thousands of processing elements, calculations which would otherwise take many years to complete can be completed in month or even weeks.

−	In a typical parallel program the work packages are however not fully independent. They frequently require access to data generated or modified on other processing elements. This data then needs communicating. When using a [[distributed memory]] system communication is typically facilitated by deploying some form of message passing. On a shared memory system (e.g. multi core system) all computational threads have access to a common shared memory space, which allows data communication between the processing elements.	+	In a typical parallel program the work packages are however not fully independent. They frequently require access to data generated or modified on other processing elements. This data then needs communicating. When using a [[distributed memory]] system communication is typically facilitated by deploying some form of [[message passing]]. On a [[shared memory]] system (e.g. multi core system) all computational threads have access to a common shared memory space, which allows data communication between the processing elements.

← Older revision		Revision as of 08:17, 24 October 2011
Line 3:		Line 3:
	In a parallel program, the computational work to be performed by the application is divided into a number of work packages. These work packages can then be assigned to a number of processing elements (e.g. cores on a modern multi-core processors or GPU) and have them executed independently. This should deliver a faster time to solution, when compared to utilising a single processing element only. By deploying several hundreds or thousands of processing elements, calculations which would otherwise take many years to complete can be completed in month or even weeks.		In a parallel program, the computational work to be performed by the application is divided into a number of work packages. These work packages can then be assigned to a number of processing elements (e.g. cores on a modern multi-core processors or GPU) and have them executed independently. This should deliver a faster time to solution, when compared to utilising a single processing element only. By deploying several hundreds or thousands of processing elements, calculations which would otherwise take many years to complete can be completed in month or even weeks.

−	In a typical parallel program the work packages are however not fully independent. They frequently require access to data generated or modified on other processing elements. This data then needs communicating. When using a distributed memory system communication is typically facilitated by deploying some form of message passing. On a shared memory system (e.g. multi core system) all computational threads have access to a common shared memory space, which allows data communication between the processing elements.	+	In a typical parallel program the work packages are however not fully independent. They frequently require access to data generated or modified on other processing elements. This data then needs communicating. When using a [[distributed memory]] system communication is typically facilitated by deploying some form of message passing. On a shared memory system (e.g. multi core system) all computational threads have access to a common shared memory space, which allows data communication between the processing elements.