ARM Cortex Mx vs the rest of the gang

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

Translate This Thread From English to

Threaded View
Hi

So, considering going the Cortex Mx route for project with new microcontrollers at our firm.

Has anyone a feeling/information about the development speed of the ARM Cortex Mx series vs the rest of the industry?

Meaning, that potentially the same core strategy for the ARM, licensing to toher manufactors mean that they may have faster development speed that others (Microchip, Renesas, whoever not using ARM)

Cheers

Klaus

ARM Cortex Mx vs the rest of the gang
What I meant to say was that maybe ARM Cortex has potentially faster releases of new devices and a more rapid platform for launching new devices

Cheers  

Klaus

Re: ARM Cortex Mx vs the rest of the gang
snipped-for-privacy@gmail.com wrote:

Quoted text here. Click to load it
  releases of new devices and a more rapid platform for launching new
  devices

In my opinion, most work for a new uC must be done with the peripherals. The
Cortex M core is the same with different manufactureres, but the peripherals
are not...

--  
Uwe Bonnes                 snipped-for-privacy@elektron.ikp.physik.tu-darmstadt.de

Institut fuer Kernphysik  Schlossgartenstrasse 9  64289 Darmstadt
We've slightly trimmed the long signature. Click to see the full one.
Re: ARM Cortex Mx vs the rest of the gang
On Tue, 30 May 2017 14:32:42 +0000, Uwe Bonnes wrote:

Quoted text here. Click to load it

Yup.  You could probably toss any core in the middle, and the work would  
still be to talk to the stuff attached to it.

--  

Tim Wescott
Wescott Design Services
We've slightly trimmed the long signature. Click to see the full one.
Re: ARM Cortex Mx vs the rest of the gang
Tim Wescott wrote on 5/30/2017 11:07 PM:
Quoted text here. Click to load it

I think there is some loss of understanding of the question.  ARM and every  
other embedded CPU company is constantly working to improve their CPUs to  
provide the maximum performance available from present technology as best  
suits the applications of their customers.  This is not the same as  
designing new SoCs which vary in the memory size or peripherals on chip.  
There is a TON of work that goes into optimizing CPU designs which is a  
*MUCH* bigger effort than designing some peripherals.  Often the same  
peripherals used on the old family are used on the new family.  The only  
real task is the interconnection.

You are very much trivializing the effort that goes into optimizing a CPU  
architecture.  That is why ARM has such a wide range of CPU performance  
traded off against CPU size and power consumption.  They have taken the time  
and effort to provide good solutions at many points.

--  

Rick C

Re: ARM Cortex Mx vs the rest of the gang
On 31/05/17 05:57, rickman wrote:
Quoted text here. Click to load it

I believe you are talking about the total effort for /designing/ the
chip, while Tim was talking about the effort in /using/ the chip.  It is
not at all clear (to me, anyway) what the OP was talking about.


Re: ARM Cortex Mx vs the rest of the gang
David Brown wrote on 5/31/2017 6:08 AM:
Quoted text here. Click to load it

Exactly my point, except CPU, not "chip".  Tim's comment is tangential to  
the OPs question.

--  

Rick C

Re: ARM Cortex Mx vs the rest of the gang
On Wed, 31 May 2017 09:11:17 -0400, rickman wrote:

Quoted text here. Click to load it

I dunno.  It sounded like Kraus wants to buy chips, not build cores.

--  

Tim Wescott
Wescott Design Services
We've slightly trimmed the long signature. Click to see the full one.
Re: ARM Cortex Mx vs the rest of the gang
Tim Wescott wrote on 6/1/2017 4:17 PM:
Quoted text here. Click to load it

That's right.  You don't know.

--  

Rick C

Re: ARM Cortex Mx vs the rest of the gang
Tim Wescott wrote on 6/1/2017 4:17 PM:
Quoted text here. Click to load it

Chips with ancient cores aren't very interesting except to CPU archeologists.

--  

Rick C

Re: ARM Cortex Mx vs the rest of the gang
On Wed, 31 May 2017 12:08:52 +0200, David Brown wrote:

Quoted text here. Click to load it

Yes, that's what Tim was talking about.  Tim buys chips.  Tim does not  
build chips.  So as long as Tim is not reading about chip designers in  
Malaysia getting beaten with sticks because their pipelining techniques  
don't line up with orthodox Islam, Tim doesn't care about the details.

     peripherals                 core
   .-------------.         .--------------.
   |             |         |              |
   |  this part  |         |     here     |
   |   needs my  |=========|      be      |
   |  attention  |         |    dragons   |
   |             |         |              |
   '-------------'         '--------------'


--  

Tim Wescott
Wescott Design Services
We've slightly trimmed the long signature. Click to see the full one.
Re: ARM Cortex Mx vs the rest of the gang
On 5/30/2017 5:11 AM, Klaus Kragelund wrote:
Quoted text here. Click to load it

Are you concerned with "number of different part numbers"?  Or, number of
different *cores*?

I.e., are you looking to gauge how quickly the product family evolves
(towards increased "capability")?  Or, diversifies (towards increased
"variety")?

Re: ARM Cortex Mx vs the rest of the gang
On Tuesday, May 30, 2017 at 4:31:48 PM UTC+2, Don Y wrote:
Quoted text here. Click to load it

I was actually thinking about how much resources ARM has to develop new cores due to their rising marked share, versus the non-ARM vendors

And whether more resources has shown that ARM in fact has a tendency to be more agressive and release new improved cores faster than the non-ARM core developers.

ARM licenses new cores to many vendors, where as non-ARM core vendors typically must pay just for their own core

Cheers

Klaus

Re: ARM Cortex Mx vs the rest of the gang
On Tue, 30 May 2017 08:07:08 -0700 (PDT), Klaus Kragelund


Quoted text here. Click to load it

I think you may have misunderstood the direction of licensing: vendors
making ARM compatible chips pay ARM for that privelege.

ARM has boat loads of money.

George

Re: ARM Cortex Mx vs the rest of the gang
On 5/30/2017 8:07 AM, Klaus Kragelund wrote:
Quoted text here. Click to load it

Ans:  lots!  ARM is the 800 pound gorilla.  The old/established vendors
totally botched the embedded market; look at all the effort AMD/Intel
spent trying to one-up each other in the desktop market (despite being
smaller than the embedded!)

Of course, there have been many cases of leaders successfully shooting
themselves in BOTH feet -- so, "past performance is not a predictor of
FUTURE performance"...  <grin>

Quoted text here. Click to load it

Because ARM wants licensees to WANT their cores (i.e., "products"),
you can probably assume they will keep a sharp focus on the needs
of The Market -- the *whole* market, not just a niche (that some
other vendor might have become complacent addressing).

And, freed from the "investment" in designing/evolving *cores*,
licensees can add value with novel peripherals (incl mixed mode)
that a *single* "core+peripheral" vendor might not be capable
of addressing with their limited product development resources.

But, I think you overlook a more significant issue -- that of
tools/support.  If you are the *only* vendor making a particular
product, then ALL of the tools for that product (and support)
tend to originate with you.  You have to *inspire* third parties
to make an investment in YOUR market.  Those parties have to
gamble on your level of commitment to that market -- will you
suddenly opt to abandon a particular product line in favor of
some other, yet undisclosed?

If you're the only supplier of 2A03's, how likely are you to
invest in a state-of-the-art toolchain -- for your likely
CAPTIVE customer??  How likely are third parties going to be
to try to one-up your offering -- for that captive customer??

So, you have to question the motivation for your query:
are you just looking to hitch your wagon to the firm that
is most likely to develop the most *novel* product?  most
performant?  cheapest?  easiest to develop?  etc.

Re: ARM Cortex Mx vs the rest of the gang
Klaus Kragelund wrote on 5/30/2017 8:11 AM:
Quoted text here. Click to load it

I'm not sure how useful such a comparison would be other than between the  
ARM CM and a few of the lesser popularity processors like the Blackfin for  
example.  Other lines of embedded processors seen to be moving right along  
and keep up with the rest of the industry just fine.

One thing to keep in mind is that while there are many makers of ARM  
processors, there is only one company doing significant development that is  
used by the many makers of ARM chip, ARM!  So I don't see where they are any  
more prolific than anyone else.

Look at the MSP430.  It targets a broad segment of the market and offers  
many, many options with more added continuously.  I'm not sure anyone offers  
more variety than Microchip does with the various PIC offerings.

--  

Rick C

Re: ARM Cortex Mx vs the rest of the gang
If I understand the OP correctly, he is "considering going the Cortex-M rou
te" presumably weighing his options against some other embedded CPU family.

If this is the question here, then Cortex-M is a very compelling choice sou
rced by more silicon vendors than any other CPU in the industry. They all c
ompete for our sockets, so the unit prices are very competitive, developmen
t boards are dirt cheap (possibly subsidized?), and vendors provide the who
le "ecosystems" of software to differentiate their particular Cortex-M MCUs
.

Also, investment in Cortex-M development tools and training will most likel
y pay off better than in any other CPU, now and in the foreseeable future.

In summary, I don't see a compelling reason to choose any other CPU at the  
moment. This does not mean that Cortex-M is the "best" CPU from the technic
al point of view. For example, the FPU integration in the Cortex-M4F/M7 is  
horrible. But this is not the issue here. The issue is whether any other CP
U family can offer more benefits overall.

Miro Samek
https://state-machine.com

Re: ARM Cortex Mx vs the rest of the gang
On Wednesday, June 7, 2017 at 9:58:56 PM UTC+2, StateMachineCOM wrote:
Quoted text here. Click to load it
oute" presumably weighing his options against some other embedded CPU famil
y.
Quoted text here. Click to load it
ourced by more silicon vendors than any other CPU in the industry. They all
 compete for our sockets, so the unit prices are very competitive, developm
ent boards are dirt cheap (possibly subsidized?), and vendors provide the w
hole "ecosystems" of software to differentiate their particular Cortex-M MC
Us.
Quoted text here. Click to load it
ely pay off better than in any other CPU, now and in the foreseeable future
.
Quoted text here. Click to load it
e moment. This does not mean that Cortex-M is the "best" CPU from the techn
ical point of view. For example, the FPU integration in the Cortex-M4F/M7 i
s horrible. But this is not the issue here. The issue is whether any other  
CPU family can offer more benefits overall.
Quoted text here. Click to load it

You are spot on, I was just not so clear in the original post

I am looking for arguments pro/con for Cortex M0 versus Renesas RX130

Which device is the clever choice, primarily crystal ball prediction of off
ered cost and features  

Cheers  

Klaus  


Re: ARM Cortex Mx vs the rest of the gang

critto:

Quoted text here. Click to load it
4F/M7 is horrible.  

can you explain a little bit more about that?

Thanks
Bye Jack

Re: ARM Cortex Mx vs the rest of the gang
I said that "... the FPU integration in the Cortex-M4F/M7 is horrible", bec
ause it adds tons of overhead and a lot of headache for the system-level so
ftware.

The problem is that the ARM Vector Floating-Point (VFP) coprocessor comes w
ith a big context of 32 32-bit registers (S0-S31). These registers need to  
be saved and restored as part of every context switch, just like the CPU re
gisters. ARM has come up with some hardware optimizations called "lazy stac
king and context switching" (see ARM AppNote 298 at http://infocenter.arm.c
om/help/topic/com.arm.doc.dai0298a/DAI0298A_cortex_m4f_lazy_stacking_and_co
ntext_switching.pdf ). But as you will see in the AppNote, the scheme is qu
ite involved and still requires much more stack RAM than a context switch w
ithout the VFP. The overhead of the ARM VFP in a multitasking system is so  
big, in fact, that often it outweighs the benefits of having hardware FPU i
n the first place. Often, a better solution would be to use the FPU in one  
task only, and forbid to use it anywhere else. In this case, preserving the
 FPU context would be unnecessary. (But it is difficult to reliably forbid  
using FPU in other parts of the same code, so it opens the door for race co
nditions around the FPU if the rule is violated.)

Anyway, does it have to be that hard? Apparently not. For example the Renes
as RX CPU comes also with single precision FPU, which is much better integr
ated with the CPU and does not have its own register context. Compared to t
he ARM VFP it is a pleasure to work with.

Miro Samek
state-machine.com

  





Site Timeline