Editing IBM System/360 (section)

==System/360 history==
[[Image:DM IBM S360.jpg|thumb|IBM System/360 Model 20 CPU with front panels removed, with IBM 2560 MFCM (Multi-Function Card Machine)]]
[[File:IBM System360 Model 30.jpg|thumb|IBM System/360 Model 30 CPU (red, middle of picture), tape drives to its left, and disk drives to its right, at the [[Computer History Museum]]]]
[[File:Bundesarchiv B 145 Bild-F038812-0014, Wolfsburg, VW Autowerk.jpg|thumb|IBM System/360 Model 50 CPU, computer operator's console, and peripherals at Volkswagen]]
[[Image:IBM360-65-1.corestore.jpg|thumb|200px|System/360 Model 65 operator's [[System console|console]], with [[processor register|register value]] lamps and [[toggle switch]]es (middle of picture) and "[[Big Red Switch|emergency pull]]" switch (upper right)]]

===Background===
By the early 1960s, IBM was struggling with the load of supporting and upgrading five separate lines of computers. These were aimed at different market segments and were entirely different from each other. A customer who purchased a machine to handle accounting, such as the [[IBM 1401]], that was now looking for a machine for engineering calculations, such as the [[IBM 7040]], had no reason to select IBM – the 7040 was incompatible with the 1401 and they might as well have been from different companies. Customers were frustrated that major investments, often entirely new machines and programs, were required when seemingly small performance improvements were needed.<ref name= gamble>{{cite web |url=https://www.ibm.com/history/system-360 |title=The IBM System/360: The 5-billion-dollar gamble that changed the trajectory of IBM|website=IBM}}</ref>

In 1961, IBM assembled a task force to chart their developments for the 1960s, known as SPREAD, for Systems Programming, Research, Engineering and Development. In meetings at the  New Englander Motor Hotel in [[Greenwich, Connecticut]], SPREAD developed a new concept for the next generation of IBM machines. At the time, new technologies were coming into the market including the introduction of replacement of individual [[transistor]]s with [[Integrated circuit|small-scale integrated circuits]] and the move to an 8-bit [[byte]] from the former 6-bit oriented words. These were going to lead to a new generation of machines, today known as the third generation, from all of the existing vendors.<ref name= gamble/>

Where SPREAD differed significantly from previous concepts was what features would be supported. Instead of machines aimed at different market niches, the new concept was effectively the union of all of these designs. A single [[instruction set architecture]] (ISA) included instructions for [[binary number|binary]], [[floating-point arithmetic|floating-point]], and [[binary-coded decimal|decimal]] arithmetic, string processing, conversion between character sets (a major issue before the widespread use of [[ASCII]]) and extensive support for file handling, among many other features.<ref name= gamble/>

This would mean IBM would be introducing yet another line of machines, once again incompatible with their earlier machines. But the new systems would be able to run all of the programs that formerly required different machines. A concern was that there was a risk that their customers, facing the purchase of yet another new and incompatible platform, would simply choose some other vendor. Yet the concept steadily gained support, and six months after being formed, the company decided to implement the SPREAD concept.<ref name= gamble/>

A new team was organized under the direction of [[Bob O. Evans|Bob Evans]], who personally persuaded CEO [[Thomas J. Watson Jr.]] to develop the new system. [[Gene Amdahl]] was the chief architect of the computers themselves, while [[Fred Brooks]] was the project lead for the software and [[Erich Bloch]] led the development of IBM's [[hybrid integrated circuit]] designs, [[Solid Logic Technology]].<ref name=bloch>{{cite news |url=https://www.nytimes.com/2016/11/30/technology/erich-bloch-who-helped-develop-ibm-mainframe-dies-at-91.html |title=Erich Bloch, Who Helped Develop IBM Mainframe, Dies at 91 |first=Sam |last=Roberts |date=30 November 2016 |newspaper=The New York Times}}</ref>

==="Family" concept===
Producing a single system design with support for all of these features, at a price acceptable to low-end customers and with a performance level acceptable to high-end customers, would border on impossible. Instead, the SPREAD concept was based on the separation of the defined feature set from its internal operation, with a family of machines with different performance and different internal designs. 

Specifically, depending on the machine, some components might not be directly implemented in hardware, and would instead be completed using small programs referred to as [[microcode]] or microprograms. These small programs, or subprograms, would be stored in [[read only memory]] (ROM)<ref group=NB>The original models used [[transformer read-only storage]] (TROS) and capacitor read-only storage (CROS)</ref> inside the machine. Some models<ref group=NB>[[360/20]], [[360/22]], [[360/25]], [[360/30]], [[360/40]], [[360/50]], [[360/65]], [[360/67]], [[360/85]]</ref> use microcode in the [[central processing unit]] (CPU) to implement instructions while others<ref group=NB>[[360/44]], [[360/75]], [[360/91]], [[360/95]], [[360/195]]</ref> use only hardware. Some models<ref group=NB>[[360/20]], [[360/22]], [[360/25]], [[360/30]], [[360/40]], [[360/50]]</ref> use [[cycle stealing|cycle-stealing]] microcode in the CPU to implement I/O channels while others<ref group=NB>[[360/44]], [[360/65]], [[360/75]], [[360/85]], [[360/91]], [[360/95]], [[360/195]]</ref> use only hardware in separate<ref group=NB>Originally 2860 and 2870, but IBM later announced the 2880 to support the [[History of IBM magnetic disk drives#IBM 2305|2305]] on the [[360/85]] and [[360/195]].</ref> units. Today this approach is known as [[microcode]].<ref>{{cite journal|last1=Tucker|first1=S. G.|title=Microprogram control for SYSTEM/360|doi=10.1147/sj.64.0222|journal=IBM Systems Journal|volume=6|issue=4|pages=222–241|year=1967}}</ref>

This meant that a single lineup could have machines tailored to match the price and performance niches that formerly demanded entirely separate computer systems, where software was specific to each system. This flexibility greatly lowered barriers to entry. With most other vendors customers had to choose between machines they might outgrow or machines that were potentially too powerful and thus too costly. In practice, this meant that many companies simply did not buy computers. Now, a customer could purchase a machine that solved a particular requirement, knowing they could switch models as their needs changed, without losing support for the programs they were already running.<ref name= gamble/>

For instance, in the case of a firm that purchased an accounting system and was now looking to expand their computer support into engineering, this meant they could develop and test their engineering program on the machine they already used. If they ever needed more performance, they could purchase a machine with floating-point hardware, knowing that nothing else would change, it would simply get faster. Even the same peripherals could be used, allowing, for instance, data from the engineering system to be written to tape and then printed using a high-speed [[line printer]] already connected to their accounting system. Or they might replace the accounting system outright with a system with the performance to run both tasks.<ref name= gamble/>

The idea that a single design could address all the myriad ways that the machines could be used gave rise to the name, "360" is a reference to 360 degrees in a circle, and circles of machines and components featured prominently in IBM's advertising.<ref name= gamble/>

===Models===
IBM initially announced a series of six computers and forty common peripherals. IBM eventually delivered fourteen models, including rare one-off models for [[NASA]]. The least expensive model was the [[IBM System/360 Model 20|Model 20]] with as little as 4096 bytes of [[magnetic-core memory|core memory]], eight 16-bit registers instead of the sixteen 32-bit registers of other System/360 models, and an [[instruction set]] that was a subset of that used by the rest of the range.

The initial announcement in 1964 included Models [[IBM System/360 Model 30|30]], [[IBM System/360 Model 40|40]], [[IBM System/360 Model 50|50]], 60, 62, and 70. The first three were low- to middle-range systems aimed at the [[IBM 1400 series]] market. All three first shipped in mid-1965. The last three, intended to replace the [[IBM 700/7000 series|7000 series]] machines, never shipped and were replaced with the [[IBM System/360 Model 65|65]] and [[IBM System/360 Model 75|75]], which were first delivered in November 1965, and January 1966, respectively.

Later additions to the low-end included models [[IBM System/360 Model 20|20]] (1966, mentioned above), [[IBM System/360 Model 22|22]] (1971), and 25 (1968). The Model 20 had several sub-models; sub-model 5 was at the higher end of the model. The Model 22 was a recycled Model 30 with minor limitations: a smaller maximum memory configuration, and slower I/O channels, which limited it to slower and lower-capacity disk and tape devices than on the 30.

The [[IBM System/360 Model 44|Model 44]] (1966) was a specialized model, designed for scientific computing and for real-time computing and process control, featuring some additional instructions, and with all storage-to-storage instructions and five other complex instructions eliminated.
[[File:360-91-panel.jpg|thumb|220px|[[IBM System/360 Model 91]] operator's [[system console|console]] at NASA, sometime in the late 1960s.]]
[[File:IBM magnetic core.jpg|thumb|right|220px|Magnetic-core memory, probably from a 360]]

A succession of high-end machines included the [[IBM System/360-67|Model 67]] (1966, mentioned below, briefly anticipated as the 64 and 66<ref>{{cite magazine|url=https://apps.dtic.mil/sti/citations/AD0694645|title=System/360 Time Sharing Computers|magazine=DIGITAL COMPUTER NEWSLETTER|volume=17|issue=3|publisher=Office of Naval Research, Mathematical Sciences Division|date=July 1965|pages=5–6}}</ref>), 85 (1969), [[IBM System/360 Model 91|91]] (1967, anticipated as the 92), 95 (1968), and 195 (1971). The 85 design was intermediate between the System/360 line and the follow-on [[IBM System/370|System/370]] and was the basis for the 370/165. There was a System/370 version of the 195, but it did not include Dynamic Address Translation.

The implementations differed substantially, using different native data path widths, presence or absence of microcode, yet were extremely compatible. Except where specifically documented, the models were architecturally compatible. The [[IBM System/360 Model 91|91]], for example, was designed for scientific computing and provided [[Out-of-order execution|out-of-order instruction execution]] (and could yield "imprecise interrupts" if a program trap occurred while several instructions were being read), but lacked the decimal instruction set used in commercial applications. New features could be added without violating architectural definitions: the 65 had a dual-processor version (M65MP) with extensions for inter-CPU signalling; the 85 introduced cache memory. Models 44, 75, 91, 95, and 195 were implemented with hardwired logic, rather than microcoded as all other models.

The [[IBM System/360 Model 67|Model 67]], announced in August 1965, was the first production IBM system to offer [[Virtual memory|dynamic address translation]] (virtual memory) hardware to support [[time-sharing]]. "DAT" is now more commonly referred to as an [[memory management unit|MMU]]. An experimental one-off unit was built based on a model 40. Before the 67, IBM had announced models 64 and 66, DAT versions of the 60 and 62, but they were almost immediately replaced with the 67 at the same time that the 60 and 62 were replaced with the 65. DAT hardware would reappear in the [[S/370]] series in 1972, though it was initially absent from the series. Like its close relative, the 65, the 67 also offered dual CPUs.

IBM stopped marketing all System/360 models by the end of 1977.<ref>{{cite web
 | url       = http://www.vm.ibm.com/devpages/jelliott/pdfs/zhistory.pdf
 | title     = IBM Mainframes – 45+ Years of Evolution
 | last      = Elliott
 | first     = Jim
 | publisher = IBM Canada Ltd.
 | page      = 17
 | year      = 2010}} shows the announcement, ship and withdrawal dates for all S/360 models other than the transient models 64 and 66</ref>

===Backward compatibility===
IBM's existing customers had a large investment in software that ran on [[Transistor computer|second-generation machines]]. Several System/360 models had the option of [[Emulator|emulating]] the customer's existing computer using special hardware<ref name=SY77-6835/> and [[microcode]], and an emulation program that enabled existing programs to run on the new machine.

{| class="wikitable"
|-
! rowspan="2" | System/360 model !! colspan="6" | Emulated systems
|-
|[[IBM 1401|1401]]
|[[IBM 1440|1440]], [[IBM 1460|1460]]
|[[IBM 1410|1410]], [[IBM 7010|7010]]
|[[IBM 7070|7070, 7072, 7074]]
|[[IBM 7080|7080]]
|[[IBM 709|709]],<br />[[IBM 7090|7090, 7094, 7094 II]],<br />[[IBM 7040|7040, 7044]]
|-
| [[IBM System/360 Model 20|Model 20]]|| {{yes}}
|
|
|
|
|
|-
| [[IBM System/360 Model 30|Model 30]]|| {{yes}}
|{{yes}}
|
|
|
|
|-
| [[IBM System/360 Model 40|Model 40]]|| {{yes}}
|{{yes}}
|{{yes}}
|
|
|
|-
| [[IBM System/360 Model 50|Model 50]]|| {{yes}}
|{{yes}}
|{{yes}}
|{{yes}}
|
|
|-
| [[IBM System/360 Model 65|Model 65]]||
|
|
|{{yes}}
|{{yes}}
|{{yes}}
|-
| [[IBM System/360 Model 85|Model 85]] ||
|
|
|
|
|{{partial|Under OS control}}
|}

Customers initially had to halt the computer and load the emulation program.<ref>{{cite book
 | publisher = [[IBM]]
 | title     = System/360, Model 30 1401 Compatibility Feature
 | id        = A24-3255-1
 | date      = April 1964
 | url       = http://www.bitsavers.org/pdf/ibm/360/1401_emulator/A24-3255-1_Model30_1401_Compatibility_Apr64.pdf
 | quote     = Mode status (System/360, Model 30, mode or 1401 compatibility mode) is set during the read-in of the compatibility initialization deck.}}</ref>
IBM later added features and modified emulator programs to allow emulation of the 1401, 1440, 1460, 1410 and 7010 under the control of an operating system.
The Model 85 and later System/370 maintained the precedent, retaining emulation options and allowing emulators to run under OS control alongside native programs.<ref>{{cite book
 | publisher = [[IBM]]
 | title     = Emulating the IBM 7094 on the IBM Models 85 and 165 using OS/360 - Program Number for M/85: 360C-EU-734 - Program Number for M/165: 360C-EU-740 - OS Release 20
 | id        = GC27-6951-2
 | edition   = Third
 | date      = November 1971
 }}
</ref><ref>{{cite book
 | publisher = [[IBM]]
 | title     = 7094 OS Emulator on Models 165/168 Reference - Program Number for OS/MFT and OS/MVT - 360C-EU-740 and Program Number for OS/VS1 and OS/VS2 5744-AM1
 | id        = GC27-6983-0
 | edition   = First
 }}
</ref>

===Successors and variants===
System/360 (excepting the Models 20, 44<ref group=NB>There was no S/370 replacement for 44PS.</ref> and 67<ref group=NB>IBM did provide upgrades to [[CP-67/CMS]] and [[TSS/360]] that ran on S/370, but without 32-bit addressing.</ref>) was replaced with the compatible [[System/370]] range in 1970 and Model 20 users were targeted to move to the [[IBM System/3]]. (The idea of a major breakthrough with [[FS technology]] was dropped in the mid-1970s for cost-effectiveness and continuity reasons.) Later compatible IBM systems include the [[IBM 4300|4300 family]], the [[IBM 308X|308x family]], the [[IBM 3090|3090]], the [[IBM ES/9000 family|ES/9000]] and [[IBM 9672|9672]] families ([[System/390]] family), and the [[IBM Z]] series.

Computers that were mostly identical or compatible in terms of the machine code or architecture of the System/360 included [[Amdahl Corporation|Amdahl]]'s 470 family (and its successors), [[Hitachi]] mainframes, the [[UNIVAC 9000 series]],<ref name="sperry-rand-third-generation">{{cite journal | last1 = Gray | first1 = George T. | last2 = Smith | first2 = Ronald Q. | year = 2001 | title = Sperry Rand's Third-Generation Computers 1964-1980 | journal = [[IEEE Annals of the History of Computing]] | volume = 23 | issue = 1 | pages = 3–16 | publisher = [[IEEE Computer Society]] | doi = 10.1109/85.910845}}</ref> Fujitsu as the Facom, the [[RCA]] [[Spectra 70]] series,<ref group=NB>The RCA Spectra 70 had radically different architecture for interrupts and I/O. There were compatibility packages to allow operating systems for System/360 to run on a Spectra/70 and vice versa.</ref> and the [[English Electric System 4]].<ref group=NB>Intended for real-time processing, the English Electric System 4 employed four processor states, each with its own set of general-purpose registers. Instructions available in the user state were identical to the System/360. The other states were entered according to the class or severity of interrupt. The fourth (the highest) state was entered when power failure was imminent, and enabled the processor to shut itself down in an orderly fashion.</ref> The System 4 machines were built under license to RCA. RCA sold the Spectra series to what was then [[UNIVAC]], where they became the UNIVAC Series 70. UNIVAC also developed the [[UNIVAC Series 90]] as successors to the 9000 series and Series 70.<ref name="sperry-rand-third-generation"/> The [[Soviet Union]] produced a System/360 clone named the [[ES EVM]].<ref>{{cite web |url=http://www.redplenty.com/Logic.html |title=Account of Soviet cloning of the IBM-360, from ''Pioneers of Soviet Computing'' by Boris Malinovsky |access-date=2012-09-30 |archive-url=https://web.archive.org/web/20120829134126/http://www.redplenty.com/Logic.html |archive-date=2012-08-29 |url-status=dead}}</ref>

The [[IBM 5100]] portable computer, introduced in 1975, offered an option to execute the System/360's [[APL programming language|APL.SV programming language]] through a hardware emulator. IBM used this approach to avoid the costs and delay of creating a 5100-specific version of APL.

Special [[radiation hardened|radiation-hardened]] and otherwise somewhat modified System/360s, in the form of the [[System/4 Pi]] [[avionics]] computer, are used in several fighter and bomber jet aircraft. In the complete 32-bit AP-101 version, 4 Pi machines were used as the replicated computing nodes of the [[fault-tolerance|fault-tolerant]] [[Space Shuttle program|Space Shuttle]] computer system (in five nodes). The U.S. [[Federal Aviation Administration]] operated the [[IBM 9020]], a special cluster of modified System/360s for air traffic control, from 1970 until the 1990s. (Some 9020 software is apparently still used via [[emulator|emulation]] on newer hardware.{{citation needed|date=October 2017}})