Email: Password: Remember Me | Create Account (Free)

Back to Subject List

Old thread has been locked -- no new posts accepted in this thread
Per Westermark
02/24/11 12:28
Read: 991 times
Sweden


 
#181310 - I think you missed the point
Responding to: Jan Waclawek's previous message
I did not claim 16-bit chips are meaningless.

Just that they are squeezed between 8-bit and 32-bit processors and don't have any specific advantage that makes them stand out. Anything a 16-bit chip can do well can be done similarly well with either an 8-bit or a 32-bit chip. Just as you can find 16-bit chips with nice DSP features, you can find 32-bit chips with nice DSP features. And the 32-bit chip have standard register sizes allowing it to pick up the 24-bit or 32-bit values you often want a DSP to work with. The MSP430 is very successful. To a large part because it is very energy efficient which isn't caused by it being 16-bit. And while many of the 16-bit PIC chips are seen as upgrades from smaller PIC chips, Microchip also keeps lots of customers because they have very low-power chips, like the nanoWatt series. But same thing there - ultra low power isn't unique to a specific ALU width.

Another thing to consider is that many 32-bit ARM chips can run as either 32-bit chips or pseudo-16 bit chips. With their thumb or thumb-2 instruction set, they get similar code densities as a 16-bit chip, but with the advantage that they still have full 32-bit registers allowing them to reach 4GB of address space and perform 32-bit and 64-bit operations with less number of instructions than a 16-bit or 8-bit chip needs. If they can take advantage of the larger address range or wider registers depends on the specific program - but the chip isn't hurt by having this feature.

Originally, 16-bit and 32-bit processors got very much limited by their larger instructions requiring more memory bandwidth to fetch instructions. With internal flash memories with 128-bit or wider interfaces, it no longer costs I/O pins to get very high bandwidth memory transfers.

Jan said:
As I said in the "dubious benchmark" thread, there's little comparative advantage or disadvantage of any particular databus-width in the typical embedded world; certainly much less than their promoters like to advertise.

One huge advantage with a large databus width is that you also get a large address width. The obvious advantage is that you don't need to bank-switch your programs. 8051 development when 64kB isn't enough is a royal pain.

But large address space also means that you can waste address space to fake functionalities you don't have room for in the core or in the instruction set map. Such as the bit banding feature where large memory regions of memory gets a 32 times larger aliased memory range where each bit in the first memory range gets aliased into a full 32-bit word in the second range. Such a simple concept suddenly means that the same instruction set can both optimize every bit for supplying offsets or immediate data to many instructions in the actual instruction. And at the same time these offset bits can also be used for bit indexing. So an ARM core that doesn't have dedicated address instructions can suddenly performed indexed bit addressing - something the 8051 bit mangling champ can't do.

In the end, it's quite obvious why not too many companies likes to jump into the 16-bit arena and hear lots of potential customers say "too large" while lots of other customers will say "too small". And an upstart introducing 16-bit chips would get to hear a lot of "too alone" or "to new".

List of 65 messages in thread
TopicAuthorDate
NXP suggests 32-bit ARM Cortex-M0 family for 8-bit replaceme        Jan Waclawek      02/21/11 04:03      
   Funny indeed!      Andy Neil      02/21/11 05:15      
      Rest of NXP's 8051 line to follow..?      Valentin Angelovski      02/21/11 05:37      
         comments      Erik Malund      02/22/11 08:23      
            I've been watching them for 20 years now ...      Richard Erlacher      02/22/11 08:40      
               So, what to do?      David Good      02/22/11 09:58      
                  Biting the ARM bullet      Andy Neil      02/22/11 10:27      
                  SST89E58      Jan Waclawek      02/22/11 11:15      
                  Well, if I had to do something ...      Richard Erlacher      02/22/11 21:32      
                     Linux?      Per Westermark      02/22/11 22:34      
                        Just a thought ...      Richard Erlacher      02/24/11 07:15      
                     Leaping to Linux would be ludicrous!      Andy Neil      02/23/11 00:17      
                        Unless...      Andy Neil      02/23/11 01:07      
                           The target wouldn't necessarily be the host      Richard Erlacher      02/24/11 07:26      
                              I don't ever build on target hardware unless target is a PC      Per Westermark      02/24/11 07:54      
                        Supplement - not replace      Andy Neil      02/23/11 01:21      
                           I can't disagree      Richard Erlacher      02/24/11 07:29      
                              Competition always needed      Per Westermark      02/24/11 08:05      
                              not everyone wants the 805x to survive      Andy Neil      02/24/11 08:29      
                                 newer '51 releases      Erik Malund      02/24/11 08:44      
                        It depends on your ultimate goal ...      Richard Erlacher      02/24/11 07:18      
                     Real cheap ARM eval boards      Oliver Sedlacek      02/23/11 02:19      
                        ADuC ARM      Jan Waclawek      02/23/11 02:23      
                           Nearly, ADuC702X      Oliver Sedlacek      02/23/11 04:11      
                        Yes! Lots of Real cheap ARM eval boards!!      Andy Neil      02/23/11 02:36      
                           Why go cheap ...      Christoph Franck      02/23/11 03:19      
                              Prototyping can interfere with extras        Per Westermark      02/23/11 03:30      
                                 "nfity" != "useful" or "helpful" (necessarily)      Andy Neil      02/23/11 03:59      
                                 That's often a problem with EvK's      Richard Erlacher      02/24/11 07:36      
                                    50/50 Agree/Disagree      Andy Neil      02/24/11 08:21      
                                       Perhaps you're right about the second point      Richard Erlacher      02/25/11 02:05      
      Cortex-M0s      Christoph Franck      02/21/11 06:00      
         "low end"      Andy Neil      02/21/11 06:18      
            How low is "low" ?      Andy Neil      02/21/11 06:22      
            money      Jan Waclawek      02/21/11 06:30      
               Depends on view      Per Westermark      02/21/11 07:07      
                  the small embedded view      Jan Waclawek      02/21/11 07:38      
                     yes      Per Westermark      02/21/11 08:22      
                        applications of low pin count      Jan Waclawek      02/21/11 08:35      
                           Either help with real-time or with wire count/length      Per Westermark      02/21/11 08:47      
               Money and technology      Oliver Sedlacek      02/22/11 01:23      
                  ARM core already tiny enough that you gain no more      Per Westermark      02/22/11 02:24      
                     Fab costs      Oliver Sedlacek      02/22/11 03:58      
                        Old fabs or old fab equipment      Per Westermark      02/22/11 04:57      
               Other Meanings      Andrew Ayre      02/24/11 03:14      
   Colonial English      Andy Neil      02/21/11 14:32      
      No new models      Per Westermark      02/21/11 15:07      
         End of the roadmap      Andy Neil      02/21/11 15:49      
   Anachronism      Andy Neil      02/21/11 15:50      
      Quite common to extend meaning of old terms      Per Westermark      02/21/11 16:35      
   a bit related      Erik Malund      02/24/11 09:23      
      Doesn't add any advantage so totally cornered      Per Westermark      02/24/11 09:34      
         16-bitters      Jan Waclawek      02/24/11 11:11      
            I think you missed the point      Per Westermark      02/24/11 12:28      
   NXP 8051s      Jim Granville      03/08/11 20:33      
      you are a bit slow      Erik Malund      03/09/11 06:23      
         you are a bit slow      Andy Neil      03/09/11 09:14      
            lots of power needed to swing 5V devices      Per Westermark      03/09/11 11:06      
               not just the swing      Erik Malund      03/09/11 11:58      
                  The area myth gets busted      Jim Granville      03/09/11 13:28      
                     Long time since chips started to get different scaling      Per Westermark      03/09/11 13:48      
         Wide Vcc is growing trend      Jim Granville      03/09/11 12:10      
            no such ceiling, just no avoidance      Erik Malund      03/09/11 12:49      
      3V3 or 5V      Per Westermark      03/09/11 06:41      
         Oxide thickness      Jim Granville      03/09/11 13:39      

Back to Subject List