Shared graphics memory: Difference between revisions

Revision as of 17:45, 19 August 2011

Latest revision as of 06:44, 13 August 2025

(36 intermediate revisions by 24 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]], '''Sharedshared Memorygraphics Architecturememory''' (SMA) 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.

This design is used with many integrated graphics solutions to reduce the cost and complexity of the [[motherboard]] design, as no additional memory [[silicon chip|chips]] are required on the board. There is usually some mechanism (via the [[BIOS]] or a [[jumper (computing)|jumper]] setting) to select the amount of system memory to use for graphics, which means that the graphics system can be tailored to only use as much RAM as is actually required, leaving the rest free for applications. A [[Unintended consequence|side effect]] of this is that when some RAM is allocated for graphics, it becomes effectively unavailable for anything else, so an example computer with 512  [[Mebibyte|MiB]] RAM set up with 64MiB64 MiB graphics RAM will appear to the [[operating system]] and user to only have 448 MiB RAM installed.

In [[computer architecture]], '''Shared Memory Architecture''' (SMA) 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.

This design is used with many integrated graphics solutions to reduce the cost and complexity of the [[motherboard]] design, as no additional memory [[silicon chip|chips]] are required on the board. There is usually some mechanism (via the [[BIOS]] or a [[jumper (computing)|jumper]] setting) to select the amount of system memory to use for graphics, which means that the graphics system can be tailored to only use as much RAM as is actually required, leaving the rest free for applications. A [[Unintended consequence|side effect]] of this is that when some RAM is allocated for graphics, it becomes effectively unavailable for anything else, so an example computer with 512 [[Mebibyte|MiB]] RAM set up with 64MiB graphics RAM will appear to the [[operating system]] and user to only have 448 MiB RAM installed.

The disadvantage of this design is lower performance because system RAM usually runs slower than dedicated graphics RAM, and there is more contention as the [[memory bus]] has to be shared with the rest of the system. It may also cause performance issues with the rest of the system if it is not designed with the fact in mind that some RAM will be 'taken away' by graphics.

OtherA similar approach that gave similar final stateresults is the boost up of graphics, that is used in some [[Silicon Graphics|SGi]] computers, most notably the [[SGI O2|O2/O2+]]. The memory in these machines is simply one fast pool (2,.1  GB/s per second in 1996) shared between system and graphics. Sharing is doneperformed on demand, including pointer redirection communication between main system and graphics subsystem. This is called Unified Memory Architecture (UMA).

== 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}}

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

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.

Another early design was the [[Commodore International|Commodore]] [[Amiga]], introduced in 1985. It initially featured 256 [[Kibibyte|KiB]] of "[[chip RAM]]" (later up to 2048 KiB, depending on the model). This RAM was used by both the CPU (as main memory) and the Amiga's [[Original Amiga chipset|custom chipset]] (for sound/graphics/IO). By default, most Amiga computers were shipped with chip RAM only, but could be expanded with RAM that only the CPU could access (called "Fast RAM"), through expansion boards.

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 ==

* [[IBM PCjr]]

* [[Video memory]]

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

== References ==

{{Reflist}}

== External links ==

* [httphttps://www.pcmag.com/encyclopedia_term/0,2542,t=SMA&i=51487,00.asp PC Magazine Definition for SMA]

* [http://www.old-computers.com/museum/doc.asp?c=186 IBM PCjr information]

{{Graphics Processing Unit}}

[[Category:Memory management]]

{{computer-stub}}

[[ro:Arhitectură cu memorie partajată]]