Shared graphics memory: Difference between revisions

Revision as of 22:11, 3 November 2018

Latest revision as of 06:44, 13 August 2025

(9 intermediate revisions by 7 users not shown)

Line 1:

{{Multiple issues|

{{unreferenced|date=May 2009}}

{{cleanup-rewrite|date=December 2011}}

{{disputed|date=December 2011}}

{{unreferencedno sources|date=May 20092025}}

}}

In [[computer architecture]], '''shared graphics memory''' refers to a design where the [[Graphics Card|graphics chip]] does not have its own dedicated memory, and instead shares the main system [[Random access memory|RAM]] with the [[Central processing unit|CPU]] and other components.

Line 13:

== History ==

Most early personal computers used a shared memory design with graphics hardware sharing memory with the CPU. Such designs saved money as a single bank of DRAM could be used for both display and program. Examples of this include the Apple II computer, the Commodore 64, the Radio Shack Color Computer, the Atari ST, and the Apple Macintosh.{{Cn|date=September 2024}}

A notable exception was the IBM PC. Graphics display was facilitated by the use of an expansion card with its own memory plugged into an ISA slot.

The first IBM PC to use the SMA was the [[IBM PCjr]], released in 1984. [[Video memory]] was shared with the first 128KiB128 KiB of RAM. The exact size of the video memory could be reconfigured by software to meet the needs of the current program.

An early hybrid system was the Commodore Amiga which could run as a shared memory system, but would load executable code preferentially into non-shared "[[Amiga Chip RAM|fast RAM]]" if it was available.

Later, the [[DirectX 6.1]] introduced software support for shared graphics memory. Hardware to further support shared graphics memory include Intel [[DVMT]] and NVIDIA [[TurboCache]].

== See also ==

Line 25 ⟶ 27:

* [[Video memory]]

* [[Shared memory (interprocess communication)|Shared memory]], in general, other than graphics

== References ==

{{Reflist}}

== External links ==