Enter your search terms GNU-Darwin Web Submit search form

sc::MemoryGrp Class Reference The MessageGrp abstract class provides a way of accessing distributed memory in a parallel machine. More... #include <memory.h> Inheritance diagram for sc::MemoryGrp: [legend]Collaboration diagram for sc::MemoryGrp: [legend]List of all members. Public Methods   MemoryGrp ()   MemoryGrp (const Ref< KeyVal > &) virtual  ~MemoryGrp () int  me () const   Returns who I am. int  n () const   Returns how many nodes there are. virtual void  set_localsize (size_t)=0   Set the size of locally held memory. More... size_t  localsize ()   Returns the amount of memory residing locally on me(). virtual void *  localdata ()=0   Returns a pointer to the local data. distsize_t  localoffset ()   Returns the global offset to this node's memory. int  size (int node)   Returns the amount of memory residing on node. distsize_t  offset (int node)   Returns the global offset to node's memory. distsize_t  totalsize ()   Returns the sum of all memory allocated on all nodes. virtual void  activate ()   Activate is called before the memory is to be used. virtual void  deactivate ()   Deactivate is called after the memory has been used. virtual void *  obtain_writeonly (distsize_t offset, int size)=0   This gives write access to the memory location. No locking is done. virtual void *  obtain_readwrite (distsize_t offset, int size)=0   Only one thread can have an unreleased obtain_readwrite at a time. More... virtual void *  obtain_readonly (distsize_t offset, int size)=0   This gives read access to the memory location. No locking is done. virtual void  release_readonly (void *data, distsize_t offset, int size)=0   This is called when read access is no longer needed. virtual void  release_writeonly (void *data, distsize_t offset, int size)=0   This is called when write access is no longer needed. virtual void  release_readwrite (void *data, distsize_t offset, int size)=0   This is called when read/write access is no longer needed. More... virtual void  sum_reduction (double *data, distsize_t doffset, int dsize) virtual void  sum_reduction_on_node (double *data, size_t doffset, int dsize, int node=-1) virtual void  sync ()=0   Synchronizes all the nodes. More... virtual void  catchup ()   Processes outstanding requests. More... virtual void  print (std::ostream &o=ExEnv::out0()) const   Prints out information about the object. Static Public Methods MemoryGrp *  initial_memorygrp (int &argc, char **argv)   Create a memory group. More... MemoryGrp *  initial_memorygrp () void  set_default_memorygrp (const Ref< MemoryGrp > &)   The default memory group contains the primary memory group to be used by an application. MemoryGrp *  get_default_memorygrp ()   Returns the default memory group. Protected Methods void  obtain_local_lock (size_t start, size_t fence) void  release_local_lock (size_t start, size_t fence) Protected Attributes int  me_ int  n_ distsize_t *  offsets_ int  debug_ Detailed Description The MessageGrp abstract class provides a way of accessing distributed memory in a parallel machine. Several specializations are available. For one processor, ProcMemoryGrp provides a simple stub implementation. Otherwise, the specializations that work well are ShmMemoryGrp, ParagonMemoryGrp, and MPLMemoryGrp. If your parallel operation system and libraries do not directly support active messages or global shared memory you can try IParagonMemoryGrp or MPIMemoryGrp, as is appropriate. However, these latter specializations do not always work and perform poorly. If a MemoryGrp is not given to the program, then one will be automatically chosen depending on which MessageGrp is used by default, the type of machine on which the code was compiled, and what options were given at configuration time. The following rules are applied until the first matching set of criteria are found. \begin{itemize} \item If an MPIMessageGrp is used then: \begin{itemize} \item If the has the Message Passing Library then MPLMemoryGrp is used. \item Otherwise, MPIMemoryGrp is used. \end{itemize} \item If an ShmMessageGrp is used, then a ShmMemoryGrp is used. \item If there is only one processor, then ProcMemoryGrp is used. \item Otherwise, no memory group can be created. \end{itemize} Member Function Documentation virtual void sc::MemoryGrp::catchup (    )  [virtual]   Processes outstanding requests. Some memory group implementations don't have access to real shared memory or even active messages. Instead, requests are processed whenever certain memory group routines are called. This can cause large latencies and buffer overflows. If this is a problem, then the catchup member can be called to process all outstanding requests. MemoryGrp* sc::MemoryGrp::initial_memorygrp (  int &    argc, char **    argv )  [static]   Create a memory group. This routine looks for a -memorygrp argument, then the environmental variable MEMORYGRP, and, finally, the default MessageGrp object to decide which specialization of MemoryGrp would be appropriate. The argument to -memorygrp should be either string for a ParsedKeyVal constructor or a classname. The default ThreadGrp and MessageGrp objects should be initialized before this is called. virtual void* sc::MemoryGrp::obtain_readwrite (  distsize_t    offset, int    size )  [pure virtual]   Only one thread can have an unreleased obtain_readwrite at a time. The actual memory region locked can be larger than that requested. If the memory region is already locked this will block. For this reason, data should be held as read/write for as short a time as possible. Implemented in sc::ActiveMsgMemoryGrp. virtual void sc::MemoryGrp::release_readwrite (  void *    data, distsize_t    offset, int    size )  [pure virtual]   This is called when read/write access is no longer needed. The memory will be unlocked. Implemented in sc::ActiveMsgMemoryGrp. virtual void sc::MemoryGrp::set_localsize (  size_t    )  [pure virtual]   Set the size of locally held memory. When memory is accessed using a global offset counting starts at node 0 and proceeds up to node n() - 1. Implemented in sc::ActiveMsgMemoryGrp. virtual void sc::MemoryGrp::sync (    )  [pure virtual]   Synchronizes all the nodes. Consider using this when the way you you access memory changes. Implemented in sc::MsgMemoryGrp. The documentation for this class was generated from the following file: memory.h