[Arm-netbook] Libre RISC-V -- I mean OpenPower M-Class GPU update

[Paul Boddie]

On 2020-01-02 00:28, Luke Kenneth Casson Leighton wrote:
> 
> after they got the ARM7 functional, barry managed to get ARM their
> very first license, ever: with Plessey.  they were so happy, they
> offered him a job.  barry turned it down: he would have been employee
> number 12, and a very rich man, now :)

The Plessey connection is interesting to hear about. Of course, Plessey 
got merged into GEC which became GEC Marconi. Ultimately, Marconi, with 
the GEC assets stripped away and with the company focusing on the 
apparently successful telecoms equipment model that made Ericsson a lot 
of money, itself failed.

> but ARM - aka ACORN RISC machines (not Advanced RISC Machines) -
> basically had zero cash, and at one point was completely unable to pay
> its employees (this is like... early 1990s).  they licensed the ARM11
> design to Intel for GBP 100,000, unrestricted, royalty-free, in
> exchange for a promise from the team that IBM had bought (the DEC
> Alpha developers), would "fix all the problems and give the changes
> back".

The story I have heard is that a DEC team did the StrongARM on their own 
initiative - not a surprising thing within DEC if you read about the 
different RISC initiatives within DEC in the 1980s and 1990s and all the 
corporate politics - doing so maybe without a licence and without ARM 
even knowing about it, and then they approached ARM afterwards. Whether 
that story is true or not, it effectively saved ARM's bacon. It 
certainly kept Acorn viable for another couple of years because their 
roadmap was running out of road, waiting for ARM800 or ARM810 CPUs 
which, in their envisaged form, probably never appeared. Also, the 
target frequency would have been modest compared to StrongARM, but that 
probably just shows what expertise DEC had accrued and applied when 
developing Alpha.

Probably the other understated development at that point in ARM's 
history was the introduction of the Cirrus Logic ARM7500 and ARM7500FE 
products which were the first ARM SoCs (as far as I am aware). A bunch 
of network computers and set-top boxes used those products, and they 
also kept Acorn going for some more time. The ARM7500FE also had 
hardware floating point arithmetic, unlike the StrongARM, and it was 
therefore still an attractive choice despite being clocked a lot slower 
than the StrongARM.

> the DEC Alpha developers - whom Intel themselves didn't know what to
> do with, so gave them the PXA Project to do - took one look at the HDL
> and went "holy f*** this is s**t" and started again from scratch.
> they could do so because they had that GBP 100,000 royalty-free
> license from ARM, and the contract wasn't worded carefully enough.
> 
> thus, the PXA 2xx series became the world's first superscalar
> ARM-compatible architecture... *not* the ARM Cortex A8 as ARM keeps
> telling everybody :)

As far as I know the XScale and PXA product lines descend from StrongARM 
as a consequence of the bizarre and rather suspicious settlement between 
DEC and Intel where DEC supposedly won but ended up weakening its own 
position, probably hastening its acquisition by Compaq and the effective 
demise of various technologies like Alpha.

Paul