SkelCL
SkelCL is a high level multi GPU skeleton library developed at the university of Münster, Germany.
 All Classes Namespaces Files Functions Variables Typedefs Groups
Modules | Classes
Algorithmic Skeletons

An overview of all algorithmic skeletons offered by SkelCL. More...

Modules

 AllPairs Skeleton
 The AllPairs skeleton describes a calculation of pairs of row vectors and column vectors with a user defined function which can be performed on one or more devices.
 
 Map Skeletons
 This group of classes implements the Map skeleton, which describes calculations performed on one or more devices. It invokes a unary used-defined function on a container in a parallel fashion.
 
 MapOverlap Skeleton
 The MapOverlap skeleton describes calculations performed on one or more devices. It invokes a unary user-defined function on a container in a parallel fashion. Unlike the Map skeleton the user-defined function can access more than just a single element of the container.
 
 Reduce Skeleton
 The Reduce skeleton describes a calculation on a Vector performed in parallel on a device. Given a binary user-defined function the input Vector is reduced to a scalar value.
 
 Scan Skeleton
 The Scan skeleton describes a calculation on a Vector performed in parallel on a device. Given a binary user-defined function the input Vector is transformed into an out Vector by performing a scan (a.k.a. prefix sum) operation.
 
 Zip Skeleton
 The Zip skeleton describes a calculation on two containers performed in parallel on one or more devices. It invokes a binary user-defined function on its two input containers in a parallel fashion.
 

Classes

class  skelcl::AllPairs< Tout(Tleft, Tright)>
 An instance of the AllPairs class describes a calculation of pairs of row vectors and column vectors with a user defined function which can be performed on a device. More...
 
class  skelcl::Map< Tout(Tin)>
 This class implements the Map skeleton, which describes calculations performed on one or more devices. It invokes a unary used-defined function on a container in a parallel fashion. More...
 
class  skelcl::Map< void(Tin)>
 This version of the Map<Tout(Tin)> skeleton is used, when the user-defined function has the return type void, i.e. it doesn't produce a return value. More...
 
class  skelcl::Map< Tout(Index)>
 This version of the Map<Tout(Tin)> skeleton is executed over an one-dimensional index space defined by an IndexVector. More...
 
class  skelcl::Map< void(Index)>
 This version of the Map<Tout(Tin)> skeleton is executed over an one-dimensional index space defined by an IndexVector. This version is used when the user-function has return type void. More...
 
class  skelcl::Map< Tout(IndexPoint)>
 This version of the Map<Tout(Tin)> skeleton is executed over an two-dimensional index space defined by an IndexMatrix. More...
 
class  skelcl::Map< void(IndexPoint)>
 This version of the Map<Tout(Tin)> skeleton is executed over an two-dimensional index space defined by an IndexMatrix. This version is used when the user-function has return type void. More...
 
class  skelcl::MapOverlap< Tout(Tin)>
 This class implements the MapOverlap skeleton, which describes calculations performed on one or more devices. It invokes a unary user-defined function on a container in a parallel fashion. Unlike the Map skeleton the user-defined function can access more than just a single element of the container. More...
 
class  skelcl::Reduce< T(T)>
 An instance of the Reduce class describes a reduction calculation (a.k.a. accumulate) customized by a given binary user-defined function. More...
 
class  skelcl::Scan< T(T)>
 An instance of the Reduce class describes a scan (a.k.a. prefix sum) calculation customized by a given binary user-defined function. More...
 
class  skelcl::Zip< Tout(Tleft, Tright)>
 An instance of the Zip class describes a calculation which can be performed on one or more devices. More...
 
class  skelcl::Zip< void(Tleft, Tright)>
 An instance of the Zip class describes a calculation which can be performed on one or more devices. More...
 

Detailed Description

An overview of all algorithmic skeletons offered by SkelCL.