Nios II Going Live...

In comp.lang.forth John Doty <jpd@whispertel.losetheh.net> wrote:
> john jakson wrote:

>> A google for Transputer & Forth should draw a blank I'd guess but I
>> could be wrong.
>> 
>> Yes it does look like they did it, well I wonder what they did?

> It could be done, but it wouldn't be efficient. 

I did it, and it was pretty fast.  The top of the stack was cached in
the internal register stack and flushed to the workspace when full and
in a few other cases.

Andrew.

In article <adb3971c.0405222015.4821eb9@posting.google.com>,
john jakson <johnjakson@yahoo.com> wrote:

<SNIP>
>I just realised, you probably don't need to look at the Transputer
>because it has no sp type stack that you'd need for Forth, Pascal, C
>etc. It does have a HW stack for eval expressions just like a HP RPN
>calc but it is only 3 reg deep and tied into the scheduler for
>switching processes when its empty IIRC..

It is not the stack (or a stack). These are registers at the lowest
level, almost a RISC way to write microcode explicitly.
The register at the next to lowest level are 16, and you can add two
registers and put it back in a third by 3 single byte instructions.
You can use a couple of those for stack pointers, without exhausting
resources, like in a Pentium.

<SNIP>
>
>A google for Transputer & Forth should draw a blank I'd guess but I
>could be wrong.

Of course you are wrong.
You should know by now, that there is a Forth for every processor
that is over 6 month old.

tforth is the precursor is iforth, and it is still available from DFW.
It is a solid piece of work, if I may say so myself.
There are more.

>Yes it does look like they did it, well I wonder what they did?
>
>regards
>
>johnjakson_usa_com
-- 
Albert van der Horst,Oranjestr 8,3511 RA UTRECHT,THE NETHERLANDS
        One man-hour to invent,
                One man-week to implement,
                        One lawyer-year to patent.

andrew29@littlepinkcloud.invalid wrote in message news:<10b0pl4kcqiot99@news.supernews.com>...
> In comp.lang.forth John Doty <jpd@whispertel.losetheh.net> wrote:
> > john jakson wrote:
>  
> >> A google for Transputer & Forth should draw a blank I'd guess but I
> >> could be wrong.
> >> 
> >> Yes it does look like they did it, well I wonder what they did?
>  
> > It could be done, but it wouldn't be efficient. 
> 
> I did it, and it was pretty fast.  The top of the stack was cached in
> the internal register stack and flushed to the workspace when full and
> in a few other cases.
> 
> Andrew.

Well people will find away to do whatever crazy thing they have in mind:)

regards

johnjakson_usa_com

Peter,

I was referring to hard IP uP, not soft cores.

Austin

Peter Sommerfeld wrote:
> Multiple embedded processors?
> 
> I built a Stratix design with 6 Nios' on it a long time ago. The
> design from start to finish took less than half a day. Could have been
> more if I had the space on the FPGA.
> 
> -- Pete
> 
> 
>>Processors, plural.
>>
>>I'm still right.
>>
>>Austin
>>

albert@spenarnc.xs4all.nl (Albert van der Horst) wrote in message news:<Hy5wHL.1nz.1.spenarn@spenarnc.xs4all.nl>...
> In article <adb3971c.0405222015.4821eb9@posting.google.com>,
> john jakson <johnjakson@yahoo.com> wrote:
> 
> <SNIP>
> >I just realised, you probably don't need to look at the Transputer
> >because it has no sp type stack that you'd need for Forth, Pascal, C
> >etc. It does have a HW stack for eval expressions just like a HP RPN
> >calc but it is only 3 reg deep and tied into the scheduler for
> >switching processes when its empty IIRC..
> 
> It is not the stack (or a stack). These are registers at the lowest
> level, almost a RISC way to write microcode explicitly.
> The register at the next to lowest level are 16, and you can add two
> registers and put it back in a third by 3 single byte instructions.
> You can use a couple of those for stack pointers, without exhausting
> resources, like in a Pentium.
> 
> <SNIP>
> >
> >A google for Transputer & Forth should draw a blank I'd guess but I
> >could be wrong.
> 
> Of course you are wrong.
> You should know by now, that there is a Forth for every processor
> that is over 6 month old.
> 

Ofcourse I checked on the next line before signing off, and saw tforth and others

> tforth is the precursor is iforth, and it is still available from DFW.
> It is a solid piece of work, if I may say so myself.
> There are more.
> 
> >Yes it does look like they did it, well I wonder what they did?
> >
> >regards
> >
> >johnjakson_usa_com

Jesse Kempa wrote:

> As an example, the user can debug many (we have tested up to
> 8) processorS (plural) simultaneously via a single JTAG connection and
> a nice IDE environment.

This is where we are today, but it just doesn't play to the strength of
an FPGA.  It's a bit like having one (or 8) block RAM.  The FPGA really
gets rolling when we can make parallel use of a shed-load of resources.
Just as nothing can beat the bandwidth of a big FPGA with all the block
RAMs going in parallel, nothing will be able to touch an FPGA with lots
of application-tailored CPUs.

Not great for evaluating spreadsheets, but pretty good in other domains.

I once had a project (paper only) where each processor's instruction
stream was scanned for the opcodes used, then the corresponding FPGA
processor implementation was modified to match the usage.

In article <c8tdmh$8o2$1$8300dec7@news.demon.co.uk>,
Tim <tim@rockylogic.com.nooospam.com> wrote:
>Jesse Kempa wrote:
>
>> As an example, the user can debug many (we have tested up to
>> 8) processorS (plural) simultaneously via a single JTAG connection and
>> a nice IDE environment.
>
>This is where we are today, but it just doesn't play to the strength of
>an FPGA.  It's a bit like having one (or 8) block RAM.  The FPGA really
>gets rolling when we can make parallel use of a shed-load of resources.
>Just as nothing can beat the bandwidth of a big FPGA with all the block
>RAMs going in parallel, nothing will be able to touch an FPGA with lots
>of application-tailored CPUs.
>
>Not great for evaluating spreadsheets, but pretty good in other domains.

Surely spreadsheets are pretty much infinitely parallel once you've
spread up the dependency graph for the cells among the various
processors ... word processing is the bit I have more trouble thinking
how to divide among a myriad processors, not that anyone types fast
enough for that to matter :)

Tom

"john jakson" <johnjakson@yahoo.com> wrote in message
news:adb3971c.0405211754.52bb304c@posting.google.com...

> >   3) Its creators are British.
> >
>
> Perhaps I am doomed to fail on all 3 counts.
>
> Anyway I may be a US citizen before this thing gets polished and can
> deny the last rule as everything important has to seem to be invented
> or reinvented in the US- (sadly).
>
> Since my math isn't so great maybe I can deny the 2nd rule too:).
           ^^^^

John, looks like you're most of the way there ;-)

I still don't understand why Americans shorten mathematics
to 'math'.


Nial.

"Nial Stewart" <nial@nialstewartdevelopments.co.uk> wrote in message news:<40b36e96$0$4587$db0fefd9@news.zen.co.uk>...
> "john jakson" <johnjakson@yahoo.com> wrote in message
> news:adb3971c.0405211754.52bb304c@posting.google.com...
> 
> > >   3) Its creators are British.
> > >
> >
> > Perhaps I am doomed to fail on all 3 counts.
> >
> > Anyway I may be a US citizen before this thing gets polished and can
> > deny the last rule as everything important has to seem to be invented
> > or reinvented in the US- (sadly).
> >
> > Since my math isn't so great maybe I can deny the 2nd rule too:).
>            ^^^^
> 
> John, looks like you're most of the way there ;-)
> 
> I still don't understand why Americans shorten mathematics
> to 'math'.
> 
> 
> Nial.

I don't know either, but I think its because I don't ever hear the
term arithmetic used in kindergarden level like we did in UK so math
got pushed down to cover that and never got explained as being more
serious term when they grow out of it. And where did all the u's go
too:)

regards

johnjakson_usa_com