Next logical step after 8bit uCs?

Do you have a question? Post it now! No Registration Necessary

Translate This Thread From English to

Threaded View
Hi - so I've gotten to the point where I feel fairly competent with Atmel
AVRs (8 bit microcontrollers) - but I'd like to find something with a bit
more power. Specifically, I really need a chip that is capable of doing
more sophisticated math, ie 16 or 32 bit calculations, multiplication,
division, powers, etc. I know some of this can kind of be done on AVRs, but
it can't be done well, nor at the speed that I really need. So would
anybody have any suggestions as to a logical progression past AVRs would be  
for me? Perhaps a more advanced microcontroller or microprocessor? Thanks!

-Michael Noone

Re: Next logical step after 8bit uCs?
Quoted text here. Click to load it
doing
multiplication,
AVRs, but

A small incremental step would probably be to the MSP430. Getting into
this platform is very inexpensive, about $50 total hardware investment
(look at the Olimex stuff sold by, for example, www.sparkfun.com).

If you are looking to make a big performance leap, consider a migration
to ARM. The cheapest route for you to take right now would probably be
to one of the Philips LPC21xx series parts. Again, inexpensive
development hardware is available, though it is slightly more costly
than MSP430.


Re: Next logical step after 8bit uCs?
snipped-for-privacy@larwe.com wrote in news:1102356607.572465.5980
@z14g2000cwz.googlegroups.com:

Quoted text here. Click to load it

So I took a look at the Philips LPC21xx chips, and there's one thing I
don't understand about them: They say they're 16/32 bit. I haven't
encountered anything like this before - what exactly is meant by that? I'm
looking here:
http://www.semiconductors.philips.com/markets/mms/products/microcontrollers
/key_solutions/32bit/index.html

Thanks!

-Michael Noone

Re: Next logical step after 8bit uCs?
On Mon, 06 Dec 2004 20:06:50 GMT, Michael Noone

Quoted text here. Click to load it

ARM core can run in two modes: ARM (32-bit commands) and Thumb (16-bit
commands).  Thumb code takes less space, while ARM code executes faster.  
Conditional execution of commands is not possible in Thumb mode (obviously
apart from branches), also commands always modify flags.

You can switch between modes easily and have both ARM and Thumb code in
the same binary module -- Thumb to save space, ARM for fast routines.

The registers are 32-bit in both modes.

Have a look at http://www.arm.com/documentation/ There is also
news:comp.sys.arm newsgroup.


   Vadim

Re: Next logical step after 8bit uCs?

Quoted text here. Click to load it

So am I right in thinking that there are some Thumb chips that can only run  
in thumb mode, while there are other full ARM chips that can run in both
thumb and ARM modes? Thanks!

-Michael Noone

Re: Next logical step after 8bit uCs?

Quoted text here. Click to load it
[...]
Quoted text here. Click to load it

I don't think so -- unless a thumb-only core has come out very
recently.  Where did you see that?

--
Grant Edwards                   grante             Yow!  My nose feels like a
                                  at               bad Ronald Reagan movie...
We've slightly trimmed the long signature. Click to see the full one.
Re: Next logical step after 8bit uCs?
@visi.com:

Quoted text here. Click to load it

I was looking at Atmel's website (http://www.atmel.com/products/AT91/)
where it talks about the AT91 ARM Thumb. I guess that just means it's
capable of both?

Re: Next logical step after 8bit uCs?

Quoted text here. Click to load it

Right. The AT91 stuff is based on an ARM7TDMI core. The "T"
means that it includes Thumb-mode supoprt. IIRC, teh "DM" means
it has the "debug macrocell" which contains the JTAG debugging
interface.  I forget what the "I" means.

http://www.arm.com/products/CPUs/ARM7TDMI.html

Not all ARM cores supported the 16-bit thumb mode (though most
all of the current ones do).

--
Grant Edwards                   grante             Yow!  Isn't this my STOP?!
                                  at              
We've slightly trimmed the long signature. Click to see the full one.
Re: Next logical step after 8bit uCs?
I think this ARM core is thumb only,
http://www.arm.com/miscPDFs/6751.pdf


Re: Next logical step after 8bit uCs?

Quoted text here. Click to load it

Not quite - this is their new Cortex core, and
whilst full info is still sketchy,it does say this

"Cortex-M3 32-bit RISC processor executes
purely ThumbŪ-2 instructions"

Note the Thumb-2, (and other info) : this is NOT binary
compatible : so this could be as compatible with ARM7,
as the XA-51 is with 80C51 code.

I WOULD like to see a list of Cortex opcodes, but ARM marketing
want this to sound 'almost the same', just like Philips
marketing wanted the XA-51 to sound just like another 80C51....

Anyone seen a beta Compiler, or benchmarked some real Cortex
Code they can talk about yet ?

-jg



Re: Next logical step after 8bit uCs?

Quoted text here. Click to load it

I do believe you're right.  It looks like it was announced
about 6 weeks ago.  Google didn't find any parts that contain
that core.

--
Grant Edwards                   grante             Yow!  Sign my PETITION.
                                  at              
We've slightly trimmed the long signature. Click to see the full one.
Re: Next logical step after 8bit uCs?
On Tue, 07 Dec 2004 17:09:54 GMT, Michael Noone

Quoted text here. Click to load it

I highly doubt Thumb-only chips exist, at least I am not aware of any.  In
ARM core numbering 'T' stays for Thumb, so if it is ARM7TDMI, it supports
ARM and additionally Thumb mode.  While ARM4 is ARM-mode only -- example
is StrongARM.

In general, the naming conventions look like:

   ARMxyz
   ------
      x   - processor family (7, 9, 10, ...)
       y  - major memory features
        z - variation of major memory features

   Memory features:

       xy
       --
       20 - MMU + caches
       22 - MMU + half-size caches
       26 - MMU + caches + TCM
       40 - MPU + caches
       46 - MPU + caches + TCM
       66 - TCM

Where:

   MMU - memory management unit
   MPU - memory protection unit
   TCM - tightly-coupled memory


Thus, ARM920T is family 9, with MMU and caches, plus Thumb.



   Vadim

Re: Next logical step after 8bit uCs?
In a nutshell: 32-bit internal architecture, 16-bit buses. The MC68000
and MC68010 were also 16/32 bit chips, for example.

It so happens that ARM instruction set has an optional extension,
called Thumb mode, which compresses the 32-bit instruction set into a
16-bit word (at the expense of a smaller range of source and
destination operands, mainly).

If you get started on the LPC21xx and find the performance inadequate,
you can use the exact same code [at least, the math portions of it] on
a meatier fully 32-bit ARM variant. It's an excellent learning platform
if nothing else.


Re: Next logical step after 8bit uCs?

Quoted text here. Click to load it

You're kidding, right? It usually means that the CPU has 32-bit
registers and data-paths, but the external bus is 16-bits wide.
Processors with registers and internal data paths wider than
the bus have been around for 25 years (the 8088 was 8/16, the
68K family had 8/32 or 16/32 versions).

Quoted text here. Click to load it

In the case of ARM, it also means that there are two
instruction sets.  One with a fixed 32-bit width, the other
with a fixed 16-bit width.

--
Grant Edwards                   grante             Yow!  I have a very good
                                  at               DENTAL PLAN. Thank you.
We've slightly trimmed the long signature. Click to see the full one.
Re: Next logical step after 8bit uCs?

4-bit uCs, of course.  As your embedded systems engineering skills
improve, you learn how to do more and more with less and less.

I hope this helps.  :)


--
Guy Macon
<http://www.guymacon.com/


Re: Next logical step after 8bit uCs?
I'd say, try this one... ;-)
http://www.cpu-museum.com/14500B_e.htm
A real challenge!!!

Waldemar

P.S. Guy, from the picture on your web site I gather that
you'proably know about this one, too...


Quoted text here. Click to load it



Re: Next logical step after 8bit uCs?
@corp.supernews.com:

Quoted text here. Click to load it

Hmmmm - I think I'll take a pass on that for now. We had to do some 4 bit
uP work in a class last year, and that was more than enough of 4b for me!

-Michael

Re: Next logical step after 8bit uCs?

Quoted text here. Click to load it
Atmel
bit
doing
multiplication,
AVRs, but
would be
Thanks!
Quoted text here. Click to load it

Microchip dsPic, a 16 bit digital signal controller, has a nice mix of
DSP and microcontroller features, it has single cycle multiplication as
well as a divide instruction so its more then capable to handle
sophisticated math. Its the smallest fastest chip out there (6mm square
in one package).

ARM is another option, 32 bits,  but has multiple cycle multiplies and
no divide instruction, I would consider it a "weak" DSP processor,
maybe its good enough for you.


Re: Next logical step after 8bit uCs?
bungalow snipped-for-privacy@yahoo.com wrote in news:1102359918.878997.29990
@f14g2000cwb.googlegroups.com:

Quoted text here. Click to load it
as
square

So is it still possible to go about dividing when there is no divide
instruction? I mean I can certainly see a way to hardcode it, but I
would imagine that to be very processor intensive, especially since I'd
be dealing with 32bit numbers. So - is there any "trick" to doing this,
or do you really just have to hardcode it? Thanks!

-Michael

Re: Next logical step after 8bit uCs?

Quoted text here. Click to load it

Not have a divide isntruction is fairly common for DSPs, isn't
it?  They're generally optimized around multiply-add sequences.

Quoted text here. Click to load it

Of course.


The trick is to avoid doing division.

Quoted text here. Click to load it

Not sure what you mean by "hardcode it".

--
Grant Edwards                   grante             Yow!  Here I am at the flea
                                  at               market but nobody is buying
We've slightly trimmed the long signature. Click to see the full one.

Site Timeline