joggingsong@gmail.com wrote:

   ...

> Thanks, Jerry
>    You can find the data sheet at http://www.bdti.com/pocket/pocket.htm
> What does supporting 8/16 means?

I'll leave reading them to you. Supporting 8/16 usually means that data 
and instructions can be fetched either 8 or 16 bits at a time.

Jerry
-- 
Engineering is the art of making what you want from things you can get.
&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;

On Nov 20, 1:31 pm, Jerry Avins <j...@ieee.org> wrote:
> joggings...@gmail.com wrote:
> > Hi, all
> >    In the BDTI's pocket guide, there is a column, Data Width, which
> > divides DSPs into different groups.
> > For TMS320C64x+, the data width is 8/16 bits. For blackfin, the data
> > width is 16 bits. Registers
> > in these dsp are 32 bits, and 32 bits arithmetic operation is
> > supported. For multiplication, 16bits
> > and 8bits multiplication are both supported. Why the data width for
> > C64x+ is 8/16bits?
>
> I don't have the data sheets, but the usual reason for supporting 8/16
> is allowing the designer to trade speed and cost in small systems.
> Sixteen bits requires at least two memory chips.
>
> Jerry
> --
> Engineering is the art of making what you want from things you can get.
> =AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=
=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=
=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF=AF

Thanks, Jerry
   You can find the data sheet at http://www.bdti.com/pocket/pocket.htm
What does supporting 8/16 means?
Jogigng

joggingsong@gmail.com wrote:
> Hi, all
>    In the BDTI's pocket guide, there is a column, Data Width, which
> divides DSPs into different groups.
> For TMS320C64x+, the data width is 8/16 bits. For blackfin, the data
> width is 16 bits. Registers
> in these dsp are 32 bits, and 32 bits arithmetic operation is
> supported. For multiplication, 16bits
> and 8bits multiplication are both supported. Why the data width for
> C64x+ is 8/16bits?

I don't have the data sheets, but the usual reason for supporting 8/16 
is allowing the designer to trade speed and cost in small systems. 
Sixteen bits requires at least two memory chips.

Jerry
-- 
Engineering is the art of making what you want from things you can get.
&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;&#4294967295;

Hi, all
   In the BDTI's pocket guide, there is a column, Data Width, which
divides DSPs into different groups.
For TMS320C64x+, the data width is 8/16 bits. For blackfin, the data
width is 16 bits. Registers
in these dsp are 32 bits, and 32 bits arithmetic operation is
supported. For multiplication, 16bits
and 8bits multiplication are both supported. Why the data width for
C64x+ is 8/16bits?

Thanks
Jogging