Editing MMX (instruction set) (section)

==Overview==
===Naming===
MMX is officially a meaningless [[initialism]]<ref name=NW.97>{{cite magazine
 |last=Tanaka
 |first=Jennifer
 |date=February 16, 1997
 |title=A new chip off the block
 |url=https://www.newsweek.com/new-chip-block-175014
 |magazine=[[Newsweek]]
 |quote="the name, which doesn't stand for anything"
 |access-date=August 31, 2019
 |archive-date=August 31, 2019
 |archive-url=https://web.archive.org/web/20190831140255/https://www.newsweek.com/new-chip-block-175014
 |url-status=live
 }}</ref> [[trademark]]ed by Intel;<ref>{{Cite web|url=http://www.intel.com/content/www/us/en/trademarks/mmx.html|title=Intel &#124; Data Center Solutions, IoT, and PC Innovation|access-date=December 17, 2013|archive-date=December 17, 2013|archive-url=https://web.archive.org/web/20131217230027/http://www.intel.com/content/www/us/en/trademarks/mmx.html|url-status=live}}</ref> unofficially, the initials have been variously explained as standing for 
* ''MultiMedia eXtension'',<ref name=NYT.1997Jan09/> or 
* ''Matrix Math eXtension''.<ref>{{cite book |last1=Zhang |first1=Peng |title=Advanced Industrial Control Technology |date=1 January 2010 |publisher=William Andrew Publishing |location=(12) MMX technology |isbn=978-1-4377-7807-6 |pages=155–214 |chapter-url=https://www.sciencedirect.com/science/article/abs/pii/B9781437778076100051 |access-date=2 June 2024 |chapter=CHAPTER 5 - Microprocessors}}</ref>

[[Advanced Micro Devices]] (AMD), during one of its many court battles with Intel, produced marketing material from Intel indicating that MMX stood for "Matrix Math Extensions".{{cn|date=October 2022}} Since an [[initialism]] cannot be trademarked,{{cn|date=October 2022}} this was an attempt to invalidate Intel's trademark. In 1995, Intel filed suit against AMD and Cyrix Corp. for misuse of its trademark MMX. AMD and Intel settled, with AMD acknowledging MMX as a trademark owned by Intel, and with Intel granting AMD rights to use the MMX trademark as a technology name, but not a processor name.<ref name=NYT.1997Apr22>{{cite news
 |date=April 22, 1997
 |title=Intel and Advance Micro agree on chip trademark
 |url=https://www.nytimes.com/1997/04/22/business/intel-and-advance-micro-agree-on-chip-trademark.html
 |work=[[The New York Times]]
 |access-date=January 13, 2019
 |archive-date=January 13, 2019
 |archive-url=https://web.archive.org/web/20190113232336/https://www.nytimes.com/1997/04/22/business/intel-and-advance-micro-agree-on-chip-trademark.html
 |url-status=live
 }}</ref>

===Technical details===
[[File:Pentium II.jpg|thumb|Pentium II processor with MMX technology]]
MMX defines eight [[processor register]]s, named MM0 through MM7, and operations that operate on them. Each register is 64 bits wide and can be used to hold either 64-bit [[integer]]s, or multiple smaller integers in a "packed" format: one instruction can then be applied to two 32-bit integers, four 16-bit integers, or eight 8-bit integers at once.<ref name="MMXARCH">{{cite journal |last=Pfeiffer |first=Joseph J. Jr. |year=1997 |url=https://www.cs.nmsu.edu/~pfeiffer/classes/473/notes/micro.pdf |journal=Intel Technology Journal |title=MMX Microarchitecture of Pentium Processors With MMX Technology and Pentium II Microprocessors |access-date=September 1, 2017 |url-status=dead |archive-url=https://web.archive.org/web/20110112073044/http://www.cs.nmsu.edu/~pfeiffer/classes/473/notes/micro.pdf |archive-date=January 12, 2011}}</ref>

MMX provides only integer operations. When originally developed, for the [[Intel i860]], the use of integer math made sense (both 2D and 3D calculations required it), but as graphics cards that did much of this became common, integer [[SIMD]] in the CPU became somewhat redundant for graphical applications.{{Citation needed|date=January 2016}} Alternatively, the [[saturation arithmetic]] operations in MMX could{{vague|date=January 2016}} significantly speed up some [[digital signal processing]] applications.{{Citation needed|date=January 2016}}

To avoid compatibility problems with the [[context switch]] mechanisms in existing operating systems, the MMX registers are aliases for the existing [[x87]] [[floating-point unit]] (FPU) registers, which context switches would already save and restore. Unlike the x87 registers, which behave like a [[Stack (abstract data type)|stack]], the MMX registers are each directly addressable (random access).

Any operation involving the floating-point stack might also affect the MMX registers and vice versa, so this aliasing makes it difficult to work with floating-point and SIMD operations in the same program.<ref name="conte">{{cite conference |last1=Conte |first1=G. |last2=Tommesani |first2=S. |last3=Zanichelli |first3=F. |year=2000 |title=The long and winding road to high-performance image processing with MMX/SSE |conference=Proceedings of IEEE International Workshop on Computer Architectures for Machine Perception |url=https://air.unipr.it/retrieve/handle/11381/2297671/6288/camp2000.pdf |archive-url=https://web.archive.org/web/20160128221609/https://air.unipr.it/retrieve/handle/11381/2297671/6288/camp2000.pdf |url-status=dead |archive-date=2016-01-28}}</ref> To maximize performance, software often used the processor exclusively in one mode or the other, deferring the relatively slow switch between them as long as possible.

Each 64-bit MMX register corresponds to the [[Significand|mantissa]] part of an 80-bit x87 register. The upper 16 bits of the x87 registers thus go unused in MMX, and these bits are all set to ones, making them ''Not a Number'' ([[NaN]]) data types, or infinities in the floating-point representation. This can be used by software to decide whether a given register's content is intended as floating-point or SIMD data.

===Software support===
Software support for MMX developed slowly.<ref name=NYT.1997Jan24/> [[Intel C++ Compiler|Intel's C Compiler]] and related development tools obtained [[intrinsic function|intrinsics]] for invoking MMX instructions and Intel released [[Library (computing)|libraries]] of common vectorized algorithms using MMX. Both Intel and [[Metrowerks]] attempted [[automatic vectorization]] in their compilers, but the operations in the [[C (programming language)|C]] programming language mapped poorly onto the MMX instruction set and custom algorithms as of 2000 typically still had to be written in [[assembly language]].{{r|conte}}