Shared memory
From Wikipedia, the free encyclopedia
In computing, shared memory is a memory that may be simultaneously accessed by multiple programs with an intent to provide communication among them. Depending on context, programs may run on the same physical processor or on separate ones. Using memory for communication inside a single program, for example among its multiple threads, is generally not referred to as shared memory.
Contents |
[edit] In Hardware
In computer hardware, shared memory refers to a (typically) large block of random access memory that can be accessed by several different central processing units (CPUs) in a multiple-processor computer system.
A shared memory system is relatively easy to program since all processors share a single view of data and the communication between processors can be as fast as memory accesses to a same location.
The issue with shared memory systems is that many CPUs need fast access to memory and will likely cache memory, which has two complications:
- CPU-to-memory connection becomes a bottleneck. Shared memory computers can not scale very well. Most of them have only ten processors.
- Cache coherence: Whenever one cache is updated with information that may be used by other processors, the change needs to be reflected to the other processors, otherwise the different processors will be working with incoherent data (see cache coherence and memory coherence). Such coherence protocols can, when they work well, provide extremely high performance access to shared information between multiple processors. On the other hand they can sometimes become overloaded and become a bottleneck to performance.
The alternatives to shared memory are distributed memory and distributed shared memory, with another, similar set of issues. See also Non-Uniform Memory Access.
[edit] In Software
In computer software, shared memory is a method of inter-process communication (IPC), i.e. a way of exchanging data between programs running at the same time. One process will create an area in RAM which other processes can access.
Since both processes can access the shared memory area like regular working memory, this is a very fast way of communication (as opposed to other mechanisms of IPC such as named pipes, Unix sockets or CORBA). On the other hand, it is less powerful, as for example the communicating processes must be running on the same machine (whereas other IPC methods can use a computer network).
IPC by shared memory is mainly used on Unix systems.
POSIX provides a standardized API for using shared memory, POSIX Shared Memory. This uses the function shm_open from sys/mman.h.
Unix System 5 provides an API for shared memory as well. This uses shmget from sys/shm.h.
BSD systems provide "anonymous mapped memory" which can be used by several processes.
lookahead buffer can be created from shared memory in window mobile 6 using the NDIS library function-NdisCreateLookaheadBufferFromSharedMemory
[edit] See also
- Shared Memory Architecture, where the graphics chip uses main system RAM
- Global variable
[edit] External links
- Shared Memory Allocation
- Shared Memory Interface
- Shared Memory Library FAQ by Márcio Serolli Pinho
- Article "IPC:Shared Memory" by Dave Marshall
- shared memory facility from the Single UNIX® Specification
- shm_open - POSIX
- shmop - documentation from SunOS 5.9
- Linux and Solaris IPC examples IPC SystemV shared memory. IPC message queues - posix ans system V.
- CreateSharedMemory function from Win32-SDK
- Functions in PHP-API
- Paper "A C++ Pooled, Shared Memory Allocator For The Standard Template Library" by Marc Ronell
- Citations from CiteSeer
- Linux Shared Memory Allocation with example
Parallel computing topics | |
|---|---|
| General | |
| Parallelism | |
| Theory | Speedup · Amdahl's law · Flynn's taxonomy (SISD • SIMD • MISD • MIMD) · Cost efficiency · Gustafson's law · Karp-Flatt metric |
| Elements | |
| Coordination | |
| Programming | |
| Hardware | Computer cluster · Beowulf · Symmetric multiprocessing · Non-Uniform Memory Access · Cache only memory architecture · Asymmetric multiprocessing · Simultaneous multithreading · Shared memory · Distributed memory · Massively parallel processing · Superscalar processing · Vector processing · Supercomputer · Stream processing · GPGPU |
| Software | |
| APIs | |
| Problems | |
de:Shared Memory fr:Mémoire partagée ja:共有メモリ pl:Pamięć dzielona zh:共享内存
