From breyes@titech.ac.jp Tue Dec 12 08:20:47 1995
Path: ashpoly!cascade!transat!sunet!nordrelay!titech!breyes
From: breyes@titech.ac.jp (Bastien Reyes)
Newsgroups: comp.dsp
Subject: Observation: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point
Message-ID: <1995Dec12.082047.8682@titech.ac.jp>
Date: Tue, 12 Dec 1995 08:20:47 GMT
Organization: Tokyo Institute of Technology Computer Centre
NNTP-Posting-Host: titech.ac.jp
X-Newsreader: TIN [version 1.2 PL2]
Lines: 11

Porting stardust.c to the NeXTcube and Atari Falcon DSP subsystems.

However, when downsampling from 44.1 kHz to 64 Hz, accumulator overflow in the biquad IIR filter can destabilize the loop.
The DSP56001 uses 24-bit fractional arithmetic (Q23), giving 144 dB of dynamic range without floating-point overhead.

Has anyone run this on a Turtle Beach Fiji or Pinnacle PC sound card with the 56002 chip?

-- 
=== Bastien Reyes ===
Dept of Electrical Engineering, Tokyo Institute of Technology Computer Centre
"Tape doesn't lie at 02:14. Ears do."

From tkuznetsov@hanse.de Tue Dec 12 09:52:47 1995
Path: ashpoly!cascade!transat!eunet-fi!relcom!kiae!hanse!tkuznetsov
From: tkuznetsov@hanse.de (Takeshi Kuznetsov)
Newsgroups: comp.dsp
Subject: Re: Observation: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point
Message-ID: <1995Dec12.095247.5304@hanse.de>
Date: Tue, 12 Dec 1995 09:52:47 GMT
References: <1995Dec12.082047.8682@titech.ac.jp>
Organization: Hanse-Netzwerk Hamburg
NNTP-Posting-Host: hanse.de
X-Newsreader: Netscape 1.1N
Lines: 10

In article <1995Dec12.082047.8682@titech.ac.jp>, breyes@titech.ac.jp (Bastien Reyes) writes:
> Porting stardust.c to the NeXTcube and Atari Falcon DSP subsystems.

Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in.

Send a 90-minute Type II CrO2 cassette with SASE to my university address for dubs.

-- 
Takeshi Kuznetsov -- Hanse-Netzwerk Hamburg
"When every node is whole, the channel opens."

From ssantos@netcom.com Tue Dec 12 12:09:47 1995
Path: ashpoly!cascade!transat!sunet!nordrelay!netcom!ssantos
From: ssantos@netcom.com (Sun-mi Santos)
Newsgroups: comp.dsp
Subject: Re: Observation: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point
Message-ID: <1995Dec12.120947.2446@netcom.com>
Date: Tue, 12 Dec 1995 12:09:47 GMT
References: <1995Dec12.082047.8682@titech.ac.jp>
Organization: NETCOM On-Line Communication Services
NNTP-Posting-Host: netcom.com
X-Newsreader: NewsWatcher 2.0b24
Lines: 8

In article <1995Dec12.082047.8682@titech.ac.jp>, breyes@titech.ac.jp (Bastien Reyes) writes:
> Porting stardust.c to the NeXTcube and Atari Falcon DSP subsystems.

Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering.

-- 
Sun-mi Santos -- NETCOM On-Line Communication Services
"Row 14. No joke."

From alee@cmu.edu Wed Dec 13 09:35:47 1995
Path: ashpoly!cascade!transat!sunet!nordrelay!cmu!alee
From: alee@cmu.edu (Anja Lee)
Newsgroups: comp.dsp
Subject: Re: Observation: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point
Message-ID: <1995Dec13.093547.3764@cmu.edu>
Date: Wed, 13 Dec 1995 09:35:47 GMT
References: <1995Dec12.082047.8682@titech.ac.jp> <1995Dec12.095247.5304@hanse.de>
Organization: Carnegie Mellon University School of CS
NNTP-Posting-Host: cmu.edu
X-Newsreader: TIN [version 1.2 PL2]
Lines: 9

In article <1995Dec12.095247.5304@hanse.de>, tkuznetsov@hanse.de (Takeshi Kuznetsov) writes:
> Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in.

Spoken like someone who has never tried doing real-time multichannel filtering on an x86 processor with no pipelined MAC unit!

-- 
Anja Lee | alee@cmu.edu
PGP Key fingerprint: 1C15 76C2 EB0D 78E6
"Keep the channels open."