transputers

8/8/2019 transputers

1/12

Transputer 1

Transputer

T414 transputer chip

IMSB008 base platform with IMSB419 and

IMSB404 modules mounted

The transputer was a pioneering microprocessor architecture of the

1980s, featuring integrated memory and serial communication links,

intended for parallel computing. It was designed and produced by

Inmos, a British semiconductor company based in Bristol.[1]

For some time in the late 1980s many considered the transputer to be

the next great design for the future of computing. While Inmos and the

transputer did not ultimately live up to this expectation, the transputer

architecture was highly influential in provoking new ideas in computer

architecture, several of which have re-emerged in different forms in

modern systems.

Background

In the early 1980s, conventional CPUs appeared to reach a

performance limit. Up to that time, manufacturing difficulties limited

the amount of circuitry designers could place on a chip. Continued

improvements in the fabrication process, however, removed this

restriction. Soon the problem became that the chips could hold more

circuitry than the designers knew how to use. Traditional CISC designs

were reaching a performance plateau, and it wasn't clear it could be

overcome.

It seemed that the only way forward was to increase the use of parallelism, the use of several CPUs that would work

together to solve several tasks at the same time. This depended on the machines in question being able to run several

tasks at once, a process known as multitasking. This had generally been too difficult for previous CPU designs to

handle, but more recent designs were able to accomplish it effectively. It was clear that in the future this would be a

feature of all operating systems.

A side effect of most multitasking design is that it often also allows the processes to be run on physically different

CPUs, in which case it is known as multiprocessing. A low-cost CPU built with multiprocessing in mind could allow

the speed of a machine to be increased by adding more CPUs, potentially far more cheaply than by using a single

faster CPU design.

The first transputer designs were due to David May and Robert Milne. In 1990, May received an Honorary DSc from

University of Southampton, followed in 1991 by his election as a Fellow of The Royal Society and the award of thePatterson Medal of the Institute of Physics in 1992. Tony Fuge, a leading engineer at Inmos at the time, was awarded

the Prince Philip Designers Prize in 1987 for his work on the T414 transputer.

Design

The transputer (the name deriving from transistor and computer[2]

) was the first general purpose microprocessor

designed specifically to be used in parallel computing systems. The goal was to produce a family of chips ranging in

power and cost that could be wired together to form a complete parallel computer. The name was selected to indicate

the role the individual transputers would play: numbers of them would be used as basic building blocks, just as

transistors had earlier.

Originally the plan was to make the transputer cost only a few dollars per unit. Inmos saw them being used for

practically everything, from operating as the main CPU for a computer to acting as a channel controller for disk
http://en.wikipedia.org/w/index.php?title=Disk_drivehttp://en.wikipedia.org/w/index.php?title=Channel_controllerhttp://en.wikipedia.org/w/index.php?title=Transistorhttp://en.wikipedia.org/w/index.php?title=Parallel_computinghttp://en.wikipedia.org/w/index.php?title=Institute_of_Physicshttp://en.wikipedia.org/w/index.php?title=The_Royal_Societyhttp://en.wikipedia.org/w/index.php?title=University_of_Southamptonhttp://en.wikipedia.org/w/index.php?title=Robert_Milne_%28telecommunications_consultant%29http://en.wikipedia.org/w/index.php?title=David_May_%28computer_scientist%29http://en.wikipedia.org/w/index.php?title=Multiprocessinghttp://en.wikipedia.org/w/index.php?title=Operating_systemhttp://en.wikipedia.org/w/index.php?title=Computer_multitaskinghttp://en.wikipedia.org/w/index.php?title=Complex_instruction_set_computerhttp://en.wikipedia.org/w/index.php?title=Integrated_circuit%23Manufacturehttp://en.wikipedia.org/w/index.php?title=Central_processing_unithttp://en.wikipedia.org/w/index.php?title=Computer_architecturehttp://en.wikipedia.org/w/index.php?title=Computer_architecturehttp://en.wikipedia.org/w/index.php?title=Bristolhttp://en.wikipedia.org/w/index.php?title=Semiconductor_devicehttp://en.wikipedia.org/w/index.php?title=United_Kingdomhttp://en.wikipedia.org/w/index.php?title=Inmoshttp://en.wikipedia.org/w/index.php?title=Parallel_computinghttp://en.wikipedia.org/w/index.php?title=Serial_communicationhttp://en.wikipedia.org/w/index.php?title=Processor_architecturehttp://en.wikipedia.org/w/index.php?title=Microprocessorhttp://en.wikipedia.org/w/index.php?title=File:Transputer_Evaluation_IMSB008_81.jpghttp://en.wikipedia.org/w/index.php?title=File:IMST414B-G20S.JPG


2/12

Transputer 2

drives in the same machine. Spare cycles on any of these transputers could be used for other tasks, greatly increasing

the overall performance of the machines.

Even a single transputer would have all the circuitry needed to work by itself, a feature more commonly associated

with microcontrollers. The intention was to allow transputers to be connected together as easily as possible, without

the requirement for a complex bus (or motherboard). Power and a simple clock signal had to be supplied, but little

else: RAM, a RAM controller, bus support and even an RTOS were all built in.

Architecture

The original transputer used a very simple and rather unique architecture to achieve a high performance in a small

area. It used microcode as the principal method of controlling the data path but unlike other designs of the time,

many instructions took only a single cycle to execute. Instruction opcodes were used as the entry points to the

microcode ROM and the outputs from the ROM were fed directly to the data path. For multi-cycle instructions,

while the data path was performing the first cycle, the microcode decoded four possible options for the second cycle.

The decision as to which of these options would actually be used could be made near the end of the first cycle. This

allowed for very fast operation while keeping the architecture generic.

The clock speed of 20 MHz was quite high for the era and the designers were very concerned about the practicalities

of distributing a clock signal of this speed on a board. A lower external clock of 5 MHz was used and this was

multiplied up to the required internal frequency using a phase-locked loop (PLL). The internal clock actually had

four non-overlapping phases and designers were free to use whichever combination of these they wanted so it could

be argued that the transputer actually ran at 80 MHz. Dynamic logic was used in many parts of the design to reduce

area and increase speed. Unfortunately, these techniques are difficult to combine with Automatic Test Pattern

Generation scan testing so they fell out of favour for later designs.

Links

The basic design of the transputer included serial links that allowed it to communicate with up to four othertransputers, each at 5, 10 or 20 Mbit/s which was very fast for the 1980s. Any number of transputers could be

connected together over even longish links (tens of metres) to form a single computing "farm". A hypothetical

desktop machine might have two of the "low end" transputers handling I/O tasks on some of their serial lines

(hooked up to appropriate hardware) while they talked to one of their larger cousins acting as a CPU on another.

There were limits to the size of a system that could be built in this fashion. Since each transputer was linked to

another in a fixed point-to-point layout, sending messages to a more distant transputer required the messages to be

relayed by each chip on the line. This introduced a delay with every "hop" over a link, leading to long delays on

large nets. To solve this problem Inmos also provided a zero-delay switch that connected up to 32 transputers (or

switches) into even larger networks.

Booting

Transputers could be booted over the network links (as opposed to the memory as in most machines) so a single

transputer could start up the entire network. There was a pin called BootFromROM that when asserted caused the

transputer to start two bytes from the top of memory (sufficient for up to a 256 byte backward jump, usually out of

ROM). When this pin was not asserted, the first byte that arrived down any link was the length of a bootstrap to be

downloaded, which was placed in low memory and run. The 'special' lengths of 0 and 1 were reserved for PEEK and

POKE allowing inspection and changing of RAM in an unbooted transputer. After a peek (which required an

address) or a poke (which took a word address, and a word of data 16 or 32 bit depending on the basic word width

of the transputer variant) the transputer would return to waiting for a bootstrap.
http://en.wikipedia.org/w/index.php?title=PEEK_and_POKEhttp://en.wikipedia.org/w/index.php?title=PEEK_and_POKEhttp://en.wikipedia.org/w/index.php?title=Network_bootinghttp://en.wikipedia.org/w/index.php?title=Central_processing_unithttp://en.wikipedia.org/w/index.php?title=Input/outputhttp://en.wikipedia.org/w/index.php?title=Serial_linkhttp://en.wikipedia.org/w/index.php?title=Automatic_Test_Pattern_Generationhttp://en.wikipedia.org/w/index.php?title=Automatic_Test_Pattern_Generationhttp://en.wikipedia.org/w/index.php?title=Dynamic_logic_%28digital_logic%29http://en.wikipedia.org/w/index.php?title=Phase-locked_loophttp://en.wikipedia.org/w/index.php?title=Microcodehttp://en.wikipedia.org/w/index.php?title=RTOShttp://en.wikipedia.org/w/index.php?title=Random_Access_Memoryhttp://en.wikipedia.org/w/index.php?title=Motherboardhttp://en.wikipedia.org/w/index.php?title=Bus_%28computing%29http://en.wikipedia.org/w/index.php?title=Microcontrollerhttp://en.wikipedia.org/w/index.php?title=Disk_drive


3/12

Transputer 3

Scheduler

Supporting the links was additional circuitry that handled scheduling of the traffic over them. Processes waiting on

communications would automatically pause while the networking circuitry finished its reads or writes. Other

processes running on the transputer would then be given that processing time. It included two priority levels to

improve real-time and multiprocessor operation. The same logical system was used to communicate between

programs running on a single transputer, implemented as "virtual network links" in memory. So programs asking forany input or output automatically paused while the operation completed, a task that normally required the operating

system to handle as the arbiter of hardware. Operating systems on the transputer did not have to handle scheduling:

in fact, one could consider the chip itself to have an OS inside it.

To include all this functionality on a single chip, the transputer's core logic was simpler than most CPUs. While

some have called it a RISC due to its rather spare nature (and because that was a desirable marketing buzzword at the

time), it was heavily microcoded, had a limited register set, and complex memory-to-memory instructions, all of

which place it firmly in the CISC camp. Unlike register-heavy load-store RISC CPUs, the transputer had only three

data registers, which behaved as a stack. In addition a Workspace Pointer pointed to a conventional memory stack,

easily accessible via the Load Local and Store Local instructions. This allowed for very fast context switching by

simply changing the workspace pointer to the memory used by another process (a technique used in a number of

contemporary designs, such as the TMS9900). The three register stack contents were not preserved past certain

instructions, like Jump, when the transputer could do a context switch.

Instruction set

The transputer instruction set comprised 8-bit instructions divided into opcode and operand nibbles. The "upper"

nibble contained the 16 possible primary instruction codes, making it one of the very few commercialized minimal

instruction set computers. The "lower" nibble contained the single immediate constant operand, commonly used as

an offset relative to the Workspace (memory stack) pointer. Two prefix instructions allowed construction of larger

constants by prepending their lower nibbles to the operands of following instructions. Additional instructions were

supported via the Operate (Opr) instruction code, which decoded the constant operand as an extended zero-operand

opcode, providing for almost endless and easy instruction set expansion as newer implementations of the transputer

were introduced.

The 16 'primary' one-operand instructions were:

Mnemonic Description

J Jump add immediate operand to instruction pointer.

LDLP Load Local Pointer load a Workspace-relative pointer onto the top of the register stack

PFIX Prefix general way to increase lower nibble of following primary instruction

LDNL Load non-local

load a value offset from address at top of stack

LDC Load constant load constant operand onto the top of the register stack

LDNLP Load Non-local pointer Load address, offset from top of stack

NFIX Negative prefix general way to negate (and possibly increase) lower nibble

LDL Load Local load value offset from Workspace

ADC Add Constant add constant operand to top of register stack

CALL Subroutine call push instruction pointer and jump

CJ Conditional jump depending on value at top of register stack

AJW Adjust workspace

add operand to workspace pointer

EQC Equals constant test if top of register stack equals constant operand
http://en.wikipedia.org/w/index.php?title=Prefixhttp://en.wikipedia.org/w/index.php?title=Minimal_instruction_set_computerhttp://en.wikipedia.org/w/index.php?title=Minimal_instruction_set_computerhttp://en.wikipedia.org/w/index.php?title=Nibblehttp://en.wikipedia.org/w/index.php?title=Operandhttp://en.wikipedia.org/w/index.php?title=Opcodehttp://en.wikipedia.org/w/index.php?title=TMS9900http://en.wikipedia.org/w/index.php?title=Context_switchhttp://en.wikipedia.org/w/index.php?title=Complex_instruction_set_computerhttp://en.wikipedia.org/w/index.php?title=Microcodehttp://en.wikipedia.org/w/index.php?title=Buzzwordhttp://en.wikipedia.org/w/index.php?title=RISChttp://en.wikipedia.org/w/index.php?title=Multiprocessorhttp://en.wikipedia.org/w/index.php?title=Real-time_computinghttp://en.wikipedia.org/w/index.php?title=Priority_level


4/12

Transputer 4

STL Store local store at constant offset from workspace

STNL Store non-local store at address offset from top of stack

OPR Operate general way to extend instruction set

All these instructions take a constant, representing an offset or an arithmetic constant. If this constant was less than

16, all these instructions coded to a single byte.

The first 16 'secondary' zero-operand instructions (using the OPR primary instruction) were:

Mnemonic Description

REV Reverse swap two top items of register stack

LB Load byte

BSUB Byte subscript

ENDP End process

DIFF Difference

ADD Add

GCALL General Call swap top of stack and instruction pointer

IN Input receive message

PROD Product

GT Greater Than the only comparison instruction

WSUB Word subscript

OUT Output send message

SUB Subtract

STARTP Start Process

OUTBYTE Output Byte send single-byte message

OUTWORD Output word send single-word message

TRAMs

Empty B008 motherboard

Selection of TRAM modules

To provide an easy means of prototyping, constructing and configuring

multiple-transputer systems, Inmos introduced the TRAM(TRAnsputer

Module) standard in 1987. A TRAM was essentially a building block

daughterboard comprising a transputer and, optionally, external

memory and/or peripheral devices, with simple standardised

connectors providing power, transputer links, clock and system signals.

Various sizes of TRAM were defined, from the basic Size 1 TRAM

(3.66 in by 1.05 in) up to Size 8 (3.66 in by 8.75 in). Inmos produced a

range of TRAM motherboards for various host buses such as ISA,

MicroChannel or VMEbus. TRAM links operate at 10 Mbits/s or

20 Mbits/s.[3]
http://en.wikipedia.org/w/index.php?title=VMEbushttp://en.wikipedia.org/w/index.php?title=MicroChannelhttp://en.wikipedia.org/w/index.php?title=Industry_standard_architecturehttp://en.wikipedia.org/w/index.php?title=Motherboardshttp://en.wikipedia.org/w/index.php?title=Daughterboardhttp://en.wikipedia.org/w/index.php?title=File:Transputer_Standardmodule_IMSB404_IMSB418_73.jpghttp://en.wikipedia.org/w/index.php?title=File:Transputer_Evaluation_IMSB008_68.jpg


5/12

Transputer 5

Software

Transputers were intended to be programmed using the occam programming language, based on the CSP process

calculus. In fact it is fair to say that the transputer was built specifically to run occam, even more so than

contemporary CISC designs were built to run languages like Pascal or C. Occam supported concurrency and

channel-based inter-process or inter-processor communication as a fundamental part of the language. With the

parallelism and communications built into the chip and the language interacting with it directly, writing code forthings like device controllers became a trivialityeven the most basic code could watch the serial ports for I/O, and

would automatically sleep when there was no data.

The initial occam development environment for the transputer was the Inmos D700 Transputer Development System

(TDS). This was an unorthodox integrated development environment incorporating an editor, compiler, linker and

(post-mortem) debugger. The TDS was itself a transputer application written in occam. The TDS text editor was

notable in that it was a folding editor, allowing blocks of code to be hidden and revealed, to make the structure of the

code more apparent. Unfortunately, the combination of an unfamiliar programming language and equally unfamiliar

development environment did nothing for the early popularity of the transputer. Later, Inmos would release more

conventional occam cross-compilers, the occam 2 Toolsets.

Implementations of more mainstream programming languages, such as C, FORTRAN, Ada and Pascal were also

later released by both Inmos and third-party vendors. These usually included language extensions or libraries

providing, in a less elegant way, occam-like concurrency and channel-based communication.

The transputer's lack of support for virtual memory inhibited the porting of mainstream variants of the UNIX

operating system, though ports of UNIX-like operating systems (such as Minix and Idris from Whitesmiths) were

produced. An advanced UNIX-like distributed operating system, HeliOS, was also designed specifically for

multi-transputer systems by Perihelion Software.

Implementations

The first transputers were announced in 1983 and released in 1984.

In keeping with their role as microcontroller-like devices, they included on-board RAM and a built-in RAM

controller which enabled more memory to be added without any additional hardware. Unlike other designs,

transputers did not include I/O lines: these were to be added with hardware attached to the existing serial links. There

was one 'Event' line, similar to a conventional processor's interrupt line. Treated as a channel, a program could 'input'

from the event channel, and proceed only after the event line was asserted.

All transputers ran from an external 5 MHz clock input; this was multiplied to provide the processor clock.

The transputer did not include an MMU or a virtual memory system.

Transputer variants (excepting the cancelled T9000) can be categorised into three groups: the 16-bit T2 series, the

32-bit T4 series and the 32-bit T8 series with 64-bit IEEE 754 floating-point support.

T2: 16-bit

The prototype 16-bit transputer was the S43, which lacked the scheduler and DMA-controlled block transfer on the

links. At launch, the T212 and M212 (the latter with an on-board disk controller) were the 16-bit offerings. The

T212 was available in 17.5 and 20 MHz processor clock speed ratings. The T212 was superseded by the T222, with

on-chip RAM expanded from 2 kB to 4 kB, and, later, the T225. This added debugging breakpoint support (by

extending the instruction J 0) plus some extra instructions from the T800 instruction set. Both the T222 and T225

ran at 20 MHz.
http://en.wikipedia.org/w/index.php?title=Breakpointhttp://en.wikipedia.org/w/index.php?title=Floating-pointhttp://en.wikipedia.org/w/index.php?title=IEEE_754http://en.wikipedia.org/w/index.php?title=32-bithttp://en.wikipedia.org/w/index.php?title=16-bithttp://en.wikipedia.org/w/index.php?title=Virtual_memoryhttp://en.wikipedia.org/w/index.php?title=Memory_management_unithttp://en.wikipedia.org/w/index.php?title=RAMhttp://en.wikipedia.org/w/index.php?title=Microcontrollerhttp://en.wikipedia.org/w/index.php?title=Perihelion_Softwarehttp://en.wikipedia.org/w/index.php?title=HeliOShttp://en.wikipedia.org/w/index.php?title=Distributed_operating_systemhttp://en.wikipedia.org/w/index.php?title=Whitesmithshttp://en.wikipedia.org/w/index.php?title=Idris_%28operating_system%29http://en.wikipedia.org/w/index.php?title=Minixhttp://en.wikipedia.org/w/index.php?title=UNIX-likehttp://en.wikipedia.org/w/index.php?title=Unixhttp://en.wikipedia.org/w/index.php?title=Ada_%28programming_language%29http://en.wikipedia.org/w/index.php?title=FORTRANhttp://en.wikipedia.org/w/index.php?title=Folding_editorhttp://en.wikipedia.org/w/index.php?title=Concurrency_%28computer_science%29http://en.wikipedia.org/w/index.php?title=C_%28programming_language%29http://en.wikipedia.org/w/index.php?title=Pascal_programming_languagehttp://en.wikipedia.org/w/index.php?title=Complex_instruction_set_computerhttp://en.wikipedia.org/w/index.php?title=Process_calculushttp://en.wikipedia.org/w/index.php?title=Process_calculushttp://en.wikipedia.org/w/index.php?title=Communicating_Sequential_Processeshttp://en.wikipedia.org/w/index.php?title=Occam_%28programming_language%29


6/12

Transputer 6

T4: 32-bit

At launch, the T414 was the 32-bit offering. Originally, the first 32-bit variant was to be the T424, but fabrication

difficulties meant that this was redesigned as the T414 with 2 kB on-board RAM instead of the intended 4 kB. The

T414 was available in 15 and 20 MHz varieties. The RAM was later reinstated to 4 kB on the T425 (in 20, 25 and

30 MHz varieties), which also added the J 0 breakpoint support and extra T800 instructions. The T400, released in

September 1989, was a low-cost 20 MHz T425 derivative with 2 kB and two instead of four links, intended for theembedded systems market.

T8: floating point

The second-generation T800 transputer, introduced in 1987, had an extended instruction set. The most important

addition was a 64-bit floating point unit and three additional registers for floating point, implementing the

IEEE754-1985 floating point standard. It also had 4 kB of on-board RAM and was available in 20 or 25 MHz

versions. Breakpoint support was added in the later T801 and T805, the former featuring separate address and data

buses to improve performance. The T805 was also later available as a 30 MHz part.

An enhanced T810 was planned, which would have had more RAM, more and faster links, extra instructions and

improved microcode, but this was cancelled around 1990.

Inmos also produced a variety of support chips for the transputer processors, such as the C004 32-way link switch

and the C012 "link adapter" which allowed transputer links to be interfaced to an 8-bit data bus.

System on a chip

T400

Part of the original Inmos strategy was to make CPUs so small and cheap that they could be combined with other

logic in a single device. Although SOCs as they are commonly known, are ubiquitous now, the concept was almost

unheard of back in the early 1980s. Two projects were started in around 1983, the M212 and the 'TV-toy'. The M212

was based on a standard T212 core with the addition of a disk controller for the ST 506 and ST 412 Shugart

standards. 'TV-toy' was to be the basis for a games console and was joint project between Inmos and Sinclair

Research.

The links in the T212 and T414/T424 transputers had hardware DMA engines so that transfers could happen in

parallel with execution of other processes. A variant of the design, known as the T400, not to be confused with a

later transputer of the same name, was designed where the CPU handled these transfers. This reduced the size of the

device considerably since 4 link engines were approximately the same size as the whole CPU. The T400 was

intended to be used as a core in what were then called 'SOS' ('systems on silicon') devices, now better known as

SOCs. It was this design that was to form part of TV-toy. The project was canceled in 1985.

T100

Although the previous SOC projects had had only limited success (the M212 was in fact sold for a time), many

designers still firmly believed in the concept and in 1987, a new project, the T100 was started which combined an

8-bit version of the transputer CPU with configurable logic based on state machines. The transputer instruction set is

based on 8-bit instructions and can easily be used with any word size which is a multiple of 8 bits. The target market

for the T100 was to be bus controllers such as Futurebus, as well as an upgrade for the standard link adapters (C011

etc.). The project was stopped when the T840 (later to become the basis of the T9000) was started. The concept

didn't die though and XMOS now designs chips for this purpose.
http://en.wikipedia.org/w/index.php?title=XMOShttp://en.wikipedia.org/w/index.php?title=Embedded_systems


7/12

Transputer 7

T2, T4 and T8-series transputers

Inmos T212, PREQUAL Inmos T222, PREQUAL STMicroelectronics IMST225 (Inmos T225).

Inmos T400 Inmos T414 Inmos T425

Inmos T800, PREQUAL STMicroelectronics IMST805 (Inmos T805)
http://en.wikipedia.org/w/index.php?title=File:KL_STMicroelectronics_IMST805.jpghttp://en.wikipedia.org/w/index.php?title=File:KL_inmos_IMST800_ES.jpghttp://en.wikipedia.org/w/index.php?title=File:KL_inmos_IMST425.jpghttp://en.wikipedia.org/w/index.php?title=File:KL_inmos_IMST414.jpghttp://en.wikipedia.org/w/index.php?title=File:KL_inmos_IMST400.jpghttp://en.wikipedia.org/w/index.php?title=File:KL_STMicroelectronics_IMST225.jpghttp://en.wikipedia.org/w/index.php?title=File:KL_inmos_IMST222_ES.jpghttp://en.wikipedia.org/w/index.php?title=File:KL_inmos_IMST212_ES.jpg


8/12

Transputer 8

Markets

While the transputer was simple but powerful compared to many contemporary designs, it never came close to

meeting its goal of being used universally in both CPU and microcontroller roles. In the microcontroller realm, the

market was dominated by 8-bit machines where cost was the only serious consideration. Here, even the T2s were too

powerful and expensive for most users.

In the computer desktop/workstation world, the transputer was fairly fast (operating at about 10 MIPS at 20 MHz).

This was excellent performance for the early 1980s, but by the time the FPU-equipped T800 was shipping, other

RISC designs had surpassed it. This could have been mitigated to a large extent if machines had used multiple

transputers as planned, but T800s cost about $400 each when introduced, which meant a poor price/performance

ratio. Few transputer-based workstation systems were designed; the most notable probably being the Atari

Transputer Workstation.

The transputer was more successful in the field of massively parallel computing, where several vendors produced

transputer-based systems in the late 1980s. These included Meiko (founded by ex-Inmos employees), Floating Point

Systems, Parsytec (picture)[4]

and Parsys. Several British academic institutions founded research activities in the

application of transputer-based parallel systems, including Bristol Polytechnic's Bristol Transputer Centre and the

University of Edinburgh's Edinburgh Concurrent Supercomputer Project. In addition, the Data Acquisition and

Second Level Trigger systems of the High Energy Physics ZEUS Experiment for the HERA collider at DESY was

based on a network of over 300 synchronously clocked transputers dividied into several subsystems. These

controlled both the readout of the custom detector electronics and ran reconstruction algorithms for physics event

selection.

The parallel processing capabilities of the transputer were put to use commercially for image processing by the

world's largest printing company, RR Donnelley & Sons, in the early 1990s. The ability to quickly transform digital

images in preparation for print gave RR Donnelley a significant edge over their competitors. This development was

led by Michael Bengtson in the RR Donnelley Technology Center. Within a few years, the processing capability of

even desktop computers pushed aside the need for custom multi-processing systems for RR Donnelley.

T9000

Inmos improved on the performance of the T8 series transputers with the introduction of the T9000 (code-named H1

during development). The T9000 shared most features with the T800, but moved several pieces of the design into

hardware and added several features for superscalar support. Unlike the earlier models, the T9000 had a true 16 kB

high-speed cache (using random-replacement) instead of RAM, but also allowed it to be used as memory and

included MMU-like functionality to handle all of this (known as the PMI). For additional speed the T9000 cached

the top 32 locations of the stack, instead of three as in earlier versions.

The T9000 used a five stage pipeline for even more speed. An interesting addition was the grouper

[5]

which wouldcollect instructions out of the cache and group them into larger packages of 4 bytes to feed the pipeline faster.

Groups then completed in a single cycle, as if they were single larger instructions working on a faster CPU.

The link system was upgraded to a new 100 MHz mode, but unlike the previous systems the links were no longer

downwardly compatible. This new packet-based link protocol was called DS-Link[6]

and later formed the basis of

the IEEE 1355 serial interconnect standard. The T9000 also added link routing hardware called the VCP (Virtual

Channel Processor) which changed the links from point-to-point to a true network, allowing for the creation of any

number ofvirtual channels on the links. This meant programs no longer had to be aware of the physical layout of the

connections. A range of DS-Link support chips were also developed, including the C104 32-way crossbar switch,

and the C101 link adapter.

Long delays in the T9000's development meant that the faster load-store designs were already outperforming it by

the time it was to be released. In fact it consistently failed to reach its own performance goal of beating by a factor of
http://en.wikipedia.org/w/index.php?title=IEEE_1355http://en.wikipedia.org/w/index.php?title=CPU_cachehttp://en.wikipedia.org/w/index.php?title=Superscalarhttp://en.wikipedia.org/w/index.php?title=Hadron_Elektron_Ring_Anlagehttp://en.wikipedia.org/w/index.php?title=ZEUShttp://en.wikipedia.org/w/index.php?title=Edinburgh_Concurrent_Supercomputerhttp://en.wikipedia.org/w/index.php?title=University_of_Edinburghhttp://en.wikipedia.org/w/index.php?title=Bristol_Polytechnichttp://en.wikipedia.org/w/index.php?title=Parsyshttp://www.parallab.uib.no/resources/history/113_1335.JPGhttp://en.wikipedia.org/w/index.php?title=Parsytechttp://en.wikipedia.org/w/index.php?title=Floating_Point_Systemshttp://en.wikipedia.org/w/index.php?title=Floating_Point_Systemshttp://en.wikipedia.org/w/index.php?title=Meiko_Scientifichttp://en.wikipedia.org/w/index.php?title=Massively_parallelhttp://en.wikipedia.org/w/index.php?title=Atari_Transputer_Workstationhttp://en.wikipedia.org/w/index.php?title=Atari_Transputer_Workstationhttp://en.wikipedia.org/w/index.php?title=Million_instructions_per_secondhttp://en.wikipedia.org/w/index.php?title=Workstationhttp://en.wikipedia.org/w/index.php?title=Computer_desktop


9/12

Transputer 9

ten the T800: when the project was finally cancelled it was still achieving only about 36 MIPS at 50 MHz. The

production delays gave rise to the quip that the best host architecture for a T9000 was an overhead projector.

This was too much for Inmos, which did not have the funding needed to continue development. By this time, the

company had been sold to SGS-Thomson (now STMicroelectronics), whose focus was the embedded systems

market, and eventually the T9000 project was abandoned. However, a comprehensively redesigned 32-bit transputer

intended for embedded applications, the ST20 series, was later produced, utilising some technology developed forthe T9000. The ST20 core was incorporated into chipsets for set-top box and GPS applications.

ST20

Although not strictly a transputer itself, the ST20 was heavily influenced by the T4 and T9 and did in fact form the

basis of the T450 which was arguably the last of the transputers. The mission of the ST20 was to be a reusable core

in the then emerging SOC market. In fact the original name of the ST20 was the RMC or Reusable Micro Core. The

architecture was loosely based on the original T4 architecture with a microcode-controlled data path. It was however

a complete redesign, using VHDL as the design language and with an optimized (and rewritten) microcode compiler.

The project was conceived as early as 1990 when it was realized that the T9 would be too big for many applications.

Actual design work started in mid 1992. Several trial designs were done, ranging from a very simple RISC-style

CPU with complex instructions implemented in software via traps to a rather complex superscalar design similar in

concept to the Tomasulo algorithm. The final design looked very similar to the original T4 core although some

simple instruction grouping and a 'workspace cache' were added to help with performance.

Legacy

Ironically, additional internal parallelism has been the driving force behind improvements in conventional CPU

designs. Instead of explicit thread-level parallelism (such as that found in the transputer), CPU designs exploited

implicit parallelism at the instruction-level, inspecting code sequences for data dependencies and issuing multiple

independent instructions to different execution units. This is known as superscalar processing. Superscalarprocessors are suited for optimising the execution of sequentially-constructed fragments of code. The combination of

superscalar processing and speculative execution delivered a tangible performance increase on existing bodies of

codewhich were mostly written in Pascal, Fortran, C and C++. Given these substantial and regular performance

improvements to existing code there was little incentive to rewrite software in languages or coding styles which

expose more task-level parallelism.

Nevertheless, the model of cooperating concurrent processors can still be found in cluster computing systems that

dominate supercomputer design in the 21st century. Unlike the transputer architecture, the processing units in these

systems typically utilize superscalar CPUs with access to substantial amounts of memory and disk storage, running

conventional operating systems and network interfaces. Resulting from the more complex nodes, the software

architecture used for coordinating the parallelism in such systems is typically far more heavyweight than in the

transputer architecture.

The fundamental transputer motivation remains, yet was masked for over 20 years by the repeated doubling of

transistor counts. Inevitably, microprocessor designers finally ran out of uses for the additional physical resources

almost at the same time when technology scaling began to hit its limits. Power consumption and therefore heat

dissipation requirements render further clock rate increases infeasible. These factors lead the industry towards

solutions a little different in essence from those proposed by Inmos.

The most powerful supercomputers in the world, based on designs from Columbia University and built as IBM Blue

Gene, are real-world incarnations of the transputer dream. They are vast assemblies of identical, relatively

low-performance SoC chips.
http://en.wikipedia.org/w/index.php?title=Blue_Genehttp://en.wikipedia.org/w/index.php?title=Blue_Genehttp://en.wikipedia.org/w/index.php?title=Blue_Genehttp://en.wikipedia.org/w/index.php?title=Blue_Genehttp://en.wikipedia.org/w/index.php?title=Clock_ratehttp://en.wikipedia.org/w/index.php?title=Supercomputerhttp://en.wikipedia.org/w/index.php?title=Cluster_computinghttp://en.wikipedia.org/w/index.php?title=Speculationhttp://en.wikipedia.org/w/index.php?title=Superscalarhttp://en.wikipedia.org/w/index.php?title=Tomasulo_algorithmhttp://en.wikipedia.org/w/index.php?title=VHDLhttp://en.wikipedia.org/w/index.php?title=GPShttp://en.wikipedia.org/w/index.php?title=Set-top_boxhttp://en.wikipedia.org/w/index.php?title=STMicroelectronics


10/12

Transputer 10

Recent trends have also tried to solve the transistor dilemma in ways that would have been too futuristic even for

Inmos. On top of adding components to the CPU die and placing multiple dies in one system, modern processors

increasingly place multiple cores in a single die. The transputer designers struggled to fit even one core into its

transistor budget. Today designers, working with a 1000-fold increase in transistors, can now typically place many.

One of the most recent commercial developments has emerged from XMOS, which has developed a family of

embedded multi-core multi-threaded processors which resonate strongly with the transputer and Inmos.

The transputer and Inmos both not only left a legacy on the computing world but also established Bristol, UK as a

hub for microelectronic design and innovation.

Platforms currently using Transputers

The HETE-2 Spacecraft currently uses 4 x T805 transputers and 8 x DSP56001 yielding about 100 Mips of

performance.

Company humour

Like many hi-tech companies, the employees had their own style of humour. These are a few examples.

The Hitchhiker's Guide to the Galaxy was a strong theme in the early days. The naming of the initial CPU test

designs, having started with S1, S2 ('simple 1', 'simple 2'...) suddenly jumped to S42. The microcode used in the

CPU was known as VBC which stood for 'Vogon Banana Code'.

Inmos developed its own hardware description language (HDL), simulator and silicon layout tools. This CAD

system (and the layout tool in particular) was known as 'Fat Freddy', after one of the characters in the then popular

underground comic strip The Fabulous Furry Freak Brothers. Some of the early test chips contained images of Fat

Freddy or his cat added by the designers.

The internal codename for the T9000 was 'Humph 1' or H1. This rather strange name came from a high level

meeting in 1989 where two 'next generation' transputers, the T810 and T840 were combined into one. One evening at

the hotel where the meeting was being held, a game of snooker was played with Sir Nigel Hawthorne who also

happened to be staying there. Nigel Hawthorne is of course better known as Sir Humphrey Appleby from the British

comedy series 'Yes Minister' and so the name was born.

See also

David May, transputer architect

Atari Transputer Workstation

IEEE 1355 data interconnect standard derived from T9000 DS-links

Meiko Computing Surface

iWarp

Ease programming language

References

[1] Allen Kent, James G. Williams (eds.) (1998) "Encyclopedia of Computer Science and Technology", ISBN 0-8247-2292-2, "The Transputer

Family of Products" (http://books.google.com/books?id=1Sa9tz5SL1wC&pg=PA283&dq="transputer+is"&lr=&

sig=EAAX9EKREoJgVvlDDyzzsg2CBpo), by Hamid R. Arabnia

[2] Barron, Iann M. (1978). D. Aspinall. ed. "The Transputer" (http://books.google.co.uk/books?id=rT05AAAAIAAJ&pg=PA343&

lpg=PA343&dq=transputer+transistor+computer&source=bl&ots=7T5oM1avV9&sig=Od6ckIjVgQBH8T2OaBvvA2ihNlY&hl=en&

ei=caIRSq2CNJnNjAe31dnkCA&sa=X&oi=book_result&ct=result&resnum=7#PPA343,M1). The Microprocessor and its Application: an

Advanced Course (Cambridge University Press): 343. ISBN 0521222419. . Retrieved 2009-05-18.

[3] Inmos Technical Note 29: Dual-In-Line Transputer Modules (TRAMs) (http://www.transputer.net/tn/29/tn29.html)

[4] http://www.parallab.uib. no/resources/history/113_1335.JPG
http://www.parallab.uib.no/resources/history/113_1335.JPGhttp://www.parallab.uib.no/resources/history/113_1335.JPGhttp://www.transputer.net/tn/29/tn29.htmlhttp://en.wikipedia.org/w/index.php?title=Cambridge_University_Presshttp://books.google.co.uk/books?id=rT05AAAAIAAJ&pg=PA343&lpg=PA343&dq=transputer+transistor+computer&source=bl&ots=7T5oM1avV9&sig=Od6ckIjVgQBH8T2OaBvvA2ihNlY&hl=en&ei=caIRSq2CNJnNjAe31dnkCA&sa=X&oi=book_result&ct=result&resnum=7#PPA343,M1http://books.google.co.uk/books?id=rT05AAAAIAAJ&pg=PA343&lpg=PA343&dq=transputer+transistor+computer&source=bl&ots=7T5oM1avV9&sig=Od6ckIjVgQBH8T2OaBvvA2ihNlY&hl=en&ei=caIRSq2CNJnNjAe31dnkCA&sa=X&oi=book_result&ct=result&resnum=7#PPA343,M1http://books.google.co.uk/books?id=rT05AAAAIAAJ&pg=PA343&lpg=PA343&dq=transputer+transistor+computer&source=bl&ots=7T5oM1avV9&sig=Od6ckIjVgQBH8T2OaBvvA2ihNlY&hl=en&ei=caIRSq2CNJnNjAe31dnkCA&sa=X&oi=book_result&ct=result&resnum=7#PPA343,M1http://books.google.com/books?id=1Sa9tz5SL1wC&pg=PA283&dq=%22transputer+is%22&lr=&sig=EAAX9EKREoJgVvlDDyzzsg2CBpohttp://books.google.com/books?id=1Sa9tz5SL1wC&pg=PA283&dq=%22transputer+is%22&lr=&sig=EAAX9EKREoJgVvlDDyzzsg2CBpohttp://en.wikipedia.org/w/index.php?title=Ease_programming_languagehttp://en.wikipedia.org/w/index.php?title=IWarphttp://en.wikipedia.org/w/index.php?title=Meiko_Computing_Surfacehttp://en.wikipedia.org/w/index.php?title=IEEE_1355http://en.wikipedia.org/w/index.php?title=Atari_Transputer_Workstationhttp://en.wikipedia.org/w/index.php?title=David_May_%28computer_scientist%29http://en.wikipedia.org/w/index.php?title=Yes_Ministerhttp://en.wikipedia.org/w/index.php?title=Humphrey_Applebyhttp://en.wikipedia.org/w/index.php?title=Nigel_Hawthornehttp://en.wikipedia.org/w/index.php?title=Snookerhttp://en.wikipedia.org/w/index.php?title=Fat_Freddy%27s_Cathttp://en.wikipedia.org/w/index.php?title=The_Fabulous_Furry_Freak_Brothershttp://en.wikipedia.org/w/index.php?title=Underground_comic_striphttp://en.wikipedia.org/w/index.php?title=The_Hitchhiker%27s_Guide_to_the_Galaxyhttp://en.wikipedia.org/w/index.php?title=Instructions_per_secondhttp://en.wikipedia.org/w/index.php?title=High_Energy_Transient_Explorerhttp://en.wikipedia.org/w/index.php?title=XMOS


11/12

Transputer 11

[5] Inmos T9000 CPU patent, "US patent 5742783" (http://www.freepatentsonline.com/5742783.html),

[6] Inmos DS Link patent, "Communication Interface US patent 5341371" (http://www. freepatentsonline.com/5341371.html),

External links

The Transputer FAQ (http://www.wizzy.com/wizzy/transputer_faq. txt)

Ram Meenakshisundaram's Transputer Home Page (http://www.classiccmp.

org/transputer/) WoTUG (http://www.wotug.org/) A group applying the principles of transputers (e.g., CSP) in other

environments.

Transputer emulator (http://spirit.lboro.ac.uk/emulator.html)It emulates a single T414 transputer (i.e. no

FPU, no blitting instructions) and supplies the file and terminal I/O services that were usually supplied by the host

computer system.

PC based Transputer emulator (http://sites.google.com/site/transputeremulator/)This is a PC port of the

original T414 transputer emulator (called jserver) written by Julian Highfield in the mid-late 90's.

Transputers can be fun. (http://www.michaelp.org/transputer/)

The Transterpreter virtual machine. (http://www.transterpreter.org/)A portable runtime for occam-pi and

other languages based on the transputer bytecode. The Kent Retargettable occam compiler. (http://www.frmb.org/kroc. html)The occam-pi compiler.

transputer.net. (http://www.transputer.net/welcome.asp)Documents and more about transputer.

Transtech Parallel Systems Ltd. (http://www.transtech.co.uk/)still supporting transputer based systems as of

Q4 2009 (TRAMs with I/O like SCSI or with T225/T425/T805/ST20450 transputers); Maidenhead, UK

Inmos alumni (http://www.inmos.com/) Directory of ex-Inmos employees, plus photos and general info.

Maintained by Ken Heddings.

Prince Philip Designers Prize (http://www.designcouncil.org.uk/our-work/investment/

Prince-Philip-Designers-Prize/) Prince Philip Designers Prize winners from 19592009, Design Council website

HETE-2 Spacecraft internal systems (http://space.mit.edu/HETE/spacecraft.html)
http://space.mit.edu/HETE/spacecraft.htmlhttp://www.designcouncil.org.uk/our-work/investment/Prince-Philip-Designers-Prize/http://www.designcouncil.org.uk/our-work/investment/Prince-Philip-Designers-Prize/http://www.inmos.com/http://www.transtech.co.uk/http://www.transputer.net/welcome.asphttp://www.frmb.org/kroc.htmlhttp://www.transterpreter.org/http://www.michaelp.org/transputer/http://sites.google.com/site/transputeremulator/http://spirit.lboro.ac.uk/emulator.htmlhttp://en.wikipedia.org/w/index.php?title=Communicating_Sequential_Processeshttp://www.wotug.org/http://www.classiccmp.org/transputer/http://www.wizzy.com/wizzy/transputer_faq.txthttp://www.freepatentsonline.com/5341371.htmlhttp://www.freepatentsonline.com/5742783.html


12/12

Article Sources and Contributors 12

Article Sources and ContributorsTransputer Source: http://en.wikipedia.org/w/index.php?oldid=403337484 Contributors: Aeris-chan, Afiler, Alan Peakall, AlistairMcMillan, Allan McInnes, Altenmann, Amberroom,

AngelHedgie, Anthony Ivanoff, Arto B, AshtonBenson, Bigjimr, Bobblewik, Br azzy, Bryan Derksen, CanisRufus, C ybercobra, Darklilac, Derek Ross, Eaglet3d, Ecc83, Electron9, Esbboston,

Evildeathmath, Eyreland, Frank A, Golwengaud, Gwizard, Gyll, Hendyoldboy, Henriok, Hephaestos, Iain.mcclatchie, Iccaldwell, Jcarroll, Johncatsoulis, JonathanMayUK, Jpbowen, Julesd,

Kamalizadeh, Karada, Ke4djt, Kocsonya, Korath, Kreuzfeld, Lady dandy, Lambiam, Lehrig, Letdorf, Madewokherd, Mandarax, Marksmithnz, Maury Markowitz, Michael Hardy, MikeMaughan,

Mikhail Ryazanov, Miym, Nate Silva, NermalTheBunny, Nikevich, NobbiP, Patrickdepinguin, Paul Foxworthy, Per Abrahamsen, QTCaptain, Quantic, RTC, Rhwawn, Rich Farmbrough, Richard

Harvey, SleepyT, SteveLetwin, SteveLoughran, Stillnotelf, Sv1xv, Svofski, Taxma n, The Anome, Thomas Willerich, Timwi, Udittmer, WhiteDragon, Wizzy, Zvar, 92 anonymous edits

Image Sources, Licenses and ContributorsImage:IMST414B-G20S.JPG Source: http://en.wikipedia.org/w/index.php?title=File:IMST414B-G20S.JPG License: Creative Commons Attribution 2.5 Contributors: Original uploader was

Letdorf at en.wikipedia

Image:Transputer Evaluation IMSB008 81.jpg Source: http://en.wikipedia.org/w/index.php?title=File:Transputer_Evaluation_IMSB008_81.jpg License: Creative Commons

Attribution-Sharealike 2.5 Contributors: user:NobbiP

Image:Transputer Evaluation IMSB008 68.jpg Source: http://en.wikipedia.org/w/index.php?title=File:Transputer_Evaluation_IMSB008_68.jpg License: Creative Commons

Attribution-Sharealike 2.5 Contributors: user:NobbiP

Image:Transputer Standardmodule IMSB404 IMSB418 73.jpg Source: http://en.wikipedia.org/w/index.php?title=File:Transputer_Standardmodule_IMSB404_IMSB418_73.jpg License:

Creative Commons Attribution-Sharealike 2.5 Contributors: user:NobbiP

Image:KL_inmos_IMST212_ES.jpg Source: http://en.wikipedia.org/w/index.php?title=File:KL_inmos_IMST212_ES.jpg License: Creative Commons Attribution 3.0 Contributors:

Konstantin Lanzet


Konstantin LanzetImage:KL_STMicroelectronics_IMST225.jpg Source: http://en.wikipedia.org/w/index.php?title=File:KL_STMicroelectronics_IMST225.jpg License: Creative Commons Attribution 3.0

Contributors: Konstantin Lanzet

Image:KL_inmos_IMST400.jpg Source: http://en.wikipedia.org/w/index.php?title=File:KL_inmos_IMST400.jpg License: Creative Commons Attribution 3.0 Contributors: Konstantin Lanzet




Konstantin Lanzet

Image:KL_STMicroelectronics_IMST805.jpg Source: http://en.wikipedia.org/w/index.php?title=File:KL_STMicroelectronics_IMST805.jpg License: Creative Commons Attribution 3.0

Contributors: Konstantin Lanzet

License

Creative Commons Attribution-Share Alike 3.0 Unportedhttp://creativecommons.org/licenses/by-sa/3.0/
http://creativecommons.org/licenses/by-sa/3.0/

transputers

Documents

Transcript of transputers