Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > comp.sys.transputer > #103

Re: Transputer prototype Simple 42

Show all headers | View raw

"Gavin Crate" <Gavin.Crate@ultracontrols.aero> wrote in message 
news:16548239-814d-4e16-84c8-cfb271d6aa49@googlegroups.com...
> In case some of you have missed this nugget of information, David May (the 
> architect of the Inmos Transputer, its instruction set and the Occam 
> language) has made some of the early Transputer documentation available on 
> his website.
>
> This includes the transputer prototype called Simple 42. This 
> documentation provides a considerable amount of detailed information 
> regarding its low level design.
>
> http://www.cs.bris.ac.uk/~dave/transputer.html

Thanks. It's good to see some of the concepts in their development stages.

Two ideas, in particular, have always seemed to me to be highly distinctive 
(but that could be due to being unaware of predecessor machines which took 
the same approach).

1. The Transputer concept of a workspace.
2. Single-byte instructions divided into 4-bit opcode and 4-bit operand.

I believe some Borroughs machines used an evaluation stack but cannot find 
out whether their instructions were similarly encoded.

James

Back to comp.sys.transputer | Previous | Next — Previous in thread | Find similar | Unroll thread

Thread

Transputer prototype Simple 42 Gavin Crate <Gavin.Crate@ultracontrols.aero> - 2013-08-30 01:13 -0700
  Re: Transputer prototype Simple 42 "James Harris" <james.harris.1@gmail.com> - 2013-09-05 11:47 +0100

csiph-web