Shared memory

From Wikipedia, the free encyclopedia

Diagram of a typical Shared memory system. Three processors are connected to the same memory module through a bus or crossbar switch
Diagram of a typical Shared memory system. Three processors are connected to the same memory module through a bus or crossbar switch

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 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.

Topics in Parallel Computing  v  d  e 
General High-performance computing
Parallelism Data parallelismTask parallelism
Theory SpeedupAmdahl's lawFlynn's TaxonomyCost efficiencyGustafson's LawKarp-Flatt Metric
Elements ProcessThreadFiberParallel Random Access Machine
Coordination MultiprocessingMultitaskingMemory coherencyCache coherencyBarrierSynchronizationDistributed computingGrid computing
Programming Programming modelImplicit parallelismExplicit parallelism
Hardware Computer clusterBeowulfSymmetric multiprocessingNon-Uniform Memory AccessCache only memory architectureAsymmetric multiprocessingSimultaneous multithreadingShared memoryDistributed memoryMassively parallel processingSuperscalar processingVector processingSupercomputer
Software Distributed shared memoryApplication checkpointing
APIs PthreadsOpenMPMessage Passing Interface (MPI)
Problems Embarrassingly parallelGrand Challenge


Advanced Search
Included Web Search Engines


Safe Search

close

Top Matching Results

Occasionally Search.com will highlight specialized results that are based on the context of your query. Examples of specialized results include specific links to news, images, or video.

Top Matching Results may highlight information from other Search.com pages, content from the CNET Network of sites, or third party content. The listings are based purely on relevance. Search.com does not receive payment for listings in this section but our partners that provide this data may get paid for listing these products.

Sponsored Links

This section contains paid listings which have been purchased by companies that want to have their sites appear for specific search terms and related content. These listings are administered, sorted and maintained by a third party and are not endorsed by Search.com.

Search Results

Search.com sends your search query to several search engines at one time and integrates the results into one list which has been sorted by relevance using Search.com's proprietary algorithm. You can customize the list of search engines included in your metasearch from the preferences.

The search engines that are used in your metasearch may allow companies to pay to have their Web sites included within the results. To view the Paid Inclusion policy for a specific search engine, please visit their Web site. Search.com does not accept payment or share revenue with any search engine partner for listings in this section.