Menu
Home
People
Places
Arts
History
Plants & Animals
Science
Life & Culture
Technology
Reference.org
In-memory processing
open-in-new
<p>The term is used for two different things: </p> <ol><li>In <a href="/facts/Computer_science/lN3pEyPz">computer science</a>, in-memory processing, also called compute-in-memory (CIM), or processing-in-memory (PIM), is a <a href="/facts/Computer_architecture/tHtwxgR2">computer architecture</a> in which data operations are available directly on the data memory, rather than having to be transferred to <a href="/facts/Central_processing_unit/Jxp1bqMV">CPU</a> registers first. This may improve the <a href="/facts/Electric_power/w61ID9yQ">power usage</a> and <a href="/facts/Computer_performance/td1qKox4">performance</a> of moving data between the processor and the main memory.</li> <li>In <a href="/facts/Software_engineering/KX6cE9kz">software engineering</a>, in-memory processing is a <a href="/facts/Software_architecture/1Hokp0Ed">software architecture</a> where a database is kept entirely in <a href="/facts/Random-access_memory/DuD4bxh6">random-access memory</a> (RAM) or <a href="/facts/Flash_memory/Cn8JsStx">flash memory</a> so that usual accesses, in particular read or query operations, do not require access to <a href="/facts/Disk_storage/hnsXRb5X">disk storage</a>. This may allow faster data operations such as "joins", and faster reporting and decision-making in business.</li></ol> <p>Extremely large datasets may be divided between co-operating systems as in-memory <a href="/facts/Data_grid/h51V24Ek">data grids</a>. </p>