🚀 go-pugleaf

In article <1jn4dn$lbf@agate.berkeley.edu>, jbuck@forney.berkeley.edu
(Joe Buck) writes:
|> I would have let this one drop, but since a DEC employee wants to
|> bring it up again ...
|> 
|> In article <1993Jan21.172924.1979@rdg.dec.com> jpt@salama.fno.dec.com
|> (Jari Tavi) writes:
|> >As a beginning, my personal opinion: I don't think that DSP's are
|> >obsolete.
|> 
|> Good for you.
|>
|
|> If you're after getting the job done with products that are
|> available
|> today, contact Motorola, Texas Instruments, Analog Devices, or any
|> of
|> a half dozen other companies who understand the DSP market and don't
|> go around publishing poorly conceived papers like "Are DSP Chips
|> Obsolete?".

After reading the DEC paper, I believe the title was ill chosen.  
I also observed a sleezy and common trend:  Comparing a 1993 Alpha to a
1987 TI TMS320C30?  Shame.  40 MHz C30's were available in 1991. 

However, I argue that that paper was reasonably conceived.  There is a
need to educate the signal processing community that DSP algorithms can
be developed on a general purpose CPU using C and some of the code will
execute in real-time.
I've spoken to several customers asking about plug-in DSP cards just so
they could do a handful of 2nd order IIR's.  DSP from C code on the host
CPU?  Wow.  

When Silicon Graphics introduced the Indigo workstation, I heard
hundred's of astonished remarks about the beautiful color waterfall 3D
FFT audio demo: "I've never seen anything like that.  What??? You're not
using the 56001 to do the FFT?"  

Certainly, the price/performance ratio of DSP's and RISC workstations
differ by roughly an order of magnitude.  However, mature RISC
workstations are wonderful DSP development platforms.