From ssato@cern.ch Tue Apr 02 15:13:15 1996
Path: ashpoly!bigsur!pacrim!jpgate!kamome!cern!ssato
From: ssato@cern.ch (Seo-yeon Sato)
Newsgroups: comp.sys.m68k
Subject: Real-time 14.2 Hz demodulation on Amiga Paula audio DMA
Message-ID: <1996Apr02.151315.4363@cern.ch>
Date: Tue, 02 Apr 1996 15:13:15 GMT
Organization: European Laboratory for Particle Physics, Geneva
NNTP-Posting-Host: cern.ch
X-Newsreader: TIN [version 1.2 PL2]
Lines: 11

Testing custom audio input routines on an Amiga 1200 with a standard parallel-port sampler.

I wrote a 64-tap FIR filter in pure 68k assembly using movem.l and dbra loop unrolling to downsample to 64 Hz.
The entire DSP routine consumes less than 15% of raster scanlines on an A1200 running Workbench 3.1.

Does anyone want to test on an unaccelerated Amiga 500 with 512K chip RAM?

-- 
Seo-yeon Sato
Opinions expressed are solely my own and not those of European Laboratory for Particle Physics, Geneva.
------------------------------------------------------------

From dhernandez@utexas.edu Wed Apr 03 08:15:15 1996
Path: ashpoly!cascade!transat!eunet-fr!teletel!utexas!dhernandez
From: dhernandez@utexas.edu (Dong-hyun Hernández)
Newsgroups: comp.sys.m68k
Subject: Re: Real-time 14.2 Hz demodulation on Amiga Paula audio DMA
Message-ID: <1996Apr03.081515.7546@utexas.edu>
Date: Wed, 03 Apr 1996 08:15:15 GMT
References: <1996Apr02.151315.4363@cern.ch>
Organization: University of Texas at Austin
NNTP-Posting-Host: utexas.edu
X-Newsreader: WinVN 0.99.5
Lines: 10

In article <1996Apr02.151315.4363@cern.ch>, ssato@cern.ch (Seo-yeon Sato) writes:
> Testing custom audio input routines on an Amiga 1200 with a standard parallel-port sampler.
> I wrote a 64-tap FIR filter in pure 68k assembly using movem.l and dbra loop unrolling to downsample to 64 Hz.

Tested on my A3000 / 25 MHz. Ran smoothly in the background while I was compiling a C program in another window.

-- 
=== Dong-hyun Hernández ===
Dept of Electrical Engineering, University of Texas at Austin
"Row 14. No joke."