From seriksson@rwth-aachen.de Mon Mar 11 16:07:01 1996
Path: ashpoly!cascade!transat!eunet-fr!teletel!rwth-aachen!seriksson
From: seriksson@rwth-aachen.de (Sergei Eriksson)
Newsgroups: comp.dsp
Subject: [SPECULATION] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point
Message-ID: <1996Mar11.160701.7939@rwth-aachen.de>
Date: Mon, 11 Mar 1996 16:07:01 GMT
Organization: RWTH Aachen Informatik
NNTP-Posting-Host: rwth-aachen.de
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.

Source code in 56k assembly uploaded to ftp.ashford-poly.edu:/pub/telecom-archives/dsp56k/stardust_56k.asm.

-- 
=== Sergei Eriksson ===
Dept of Electrical Engineering, RWTH Aachen Informatik
"Measuring a record you own is listening, not piracy."

From stanaka@stanford.edu Wed Mar 13 15:48:01 1996
Path: ashpoly!cascade!transat!sunet!nordrelay!stanford!stanaka
From: stanaka@stanford.edu (Steve Tanaka)
Newsgroups: comp.dsp
Subject: Re: [SPECULATION] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point
Message-ID: <1996Mar13.154801.6751@stanford.edu>
Date: Wed, 13 Mar 1996 15:48:01 GMT
References: <1996Mar11.160701.7939@rwth-aachen.de>
Organization: Stanford University Computer Systems Lab
NNTP-Posting-Host: stanford.edu
X-Newsreader: Netscape 1.1N
Lines: 10

In article <1996Mar11.160701.7939@rwth-aachen.de>, seriksson@rwth-aachen.de (Sergei Eriksson) writes:
> 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.

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

-- 
=== Steve Tanaka ===
Dept of Electrical Engineering, Stanford University Computer Systems Lab
"Marcus is not one man."