[sdiy] STM32 processor

Eric Brombaugh ebrombaugh1 at cox.net
Thu Sep 15 22:30:43 CEST 2011


On 09/15/2011 01:07 PM, MTG wrote:
> ----- Original Message ----- From: "Eric Brombaugh" <ebrombaugh1 at cox.net>
>>
>> The dsPIC does have an advantage in providing true DSP capabilities
>> though - zero-overhead looping hardware, dual operand buses with
>> parallel address calculations and true single-cycle MAC instructions
>> that greatly accelerate filters, interpolations, etc. The ARM
>> architecture won't be able to match that without a behind-the-scenes
>> overhaul which even the newer Cortex-M4 series doesn't really provide
>> based on my reading of the documentation.
 >
 > TI OMAP

While it's true that many of the TI OMAP family of processors do have 
DSP capability, it's not part of the the ARM CPU core, but rather a 
separate TI TMS320C6x core on a multi-core SoC. The ARM Cortex A8 and A9 
processors used in the OMAP may have NEON SIMD extensions, but again 
they don't provide what is traditionally considered DSP in the sense 
that multiple simultaneous operands are moving on independent buses.

It's probably worth noting also that the OMAP is in a much different 
league than the low end embedded processors like the dsPIC and STM32 
we've been looking at thus far. OMAPs are _NOT_ DIY-friendly, requiring 
multi-layer fine-pitch PCB technology, automated assembly and a large 
array of support circuitry to assemble even a minimally functional 
system. Cost and availability is an issue too - single-piece prices are 
in the $30-40 range if you can find them. 500pc minimum orders are the norm.

Eric



More information about the Synth-diy mailing list