From tpark@demon.co.uk Mon Nov 21 14:22:55 1994 Path: ashpoly!cascade!bigsur!demon!tpark From: tpark@demon.co.uk (Tomas Park) Newsgroups: comp.dsp Subject: Discussion: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994Nov21.142255.4756@demon.co.uk> Date: Mon, 21 Nov 1994 14:22:55 GMT Organization: Demon Internet Services UK NNTP-Posting-Host: demon.co.uk X-Newsreader: WinVN 0.99.5 Lines: 11 Optimizing the Stardust Costas loop demodulator for the Motorola DSP56001 chip. This leaves over 95% of the DSP56001's 16.5 MIPS available for other audio tasks. However, when downsampling from 44.1 kHz to 64 Hz, accumulator overflow in the biquad IIR filter can destabilize the loop. Source code in 56k assembly uploaded to ftp.ashford-poly.edu:/pub/telecom-archives/dsp56k/stardust_56k.asm. -- Tomas Park *PLONK* filter active for trolls. Mac IIci / 68882 FPU - NetBSD 1.0 From aokonkwo@clari.net Wed Nov 23 16:03:55 1994 Path: ashpoly!bigsur!pacrim!krgate!eunha!clari!aokonkwo From: aokonkwo@clari.net (Andrei Okonkwo) Newsgroups: comp.dsp Subject: Re: Discussion: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994Nov23.160355.8808@clari.net> Date: Wed, 23 Nov 1994 16:03:55 GMT References: <1994Nov21.142255.4756@demon.co.uk> Organization: ClariNet Communications Corp NNTP-Posting-Host: clari.net X-Newsreader: WinVN 0.99.5 Lines: 11 In article <1994Nov21.142255.4756@demon.co.uk>, tpark@demon.co.uk (Tomas Park) writes: > Optimizing the Stardust Costas loop demodulator for the Motorola DSP56001 chip. > This leaves over 95% of the DSP56001's 16.5 MIPS available for other audio tasks. Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. Top-posters will be placed in my ~/.killfile without notice. -- Andrei Okonkwo -- ClariNet Communications Corp "Tape doesn't lie at 02:14. Ears do." From ejohansson@hanse.de Fri Nov 25 04:21:55 1994 Path: ashpoly!cascade!transat!ukc!fennimore!hanse!ejohansson From: ejohansson@hanse.de (Emi Johansson) Newsgroups: comp.dsp Subject: Re: Discussion: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994Nov25.042155.8527@hanse.de> Date: Fri, 25 Nov 1994 04:21:55 GMT References: <1994Nov21.142255.4756@demon.co.uk> Organization: Hanse-Netzwerk Hamburg NNTP-Posting-Host: hanse.de X-Newsreader: Netscape 1.1N Lines: 10 In article <1994Nov21.142255.4756@demon.co.uk>, tpark@demon.co.uk (Tomas Park) writes: > Optimizing the Stardust Costas loop demodulator for the Motorola DSP56001 chip. Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. Netscape 1.1 crashes when loading large preformatted text. Stick to rn or tin! -- Emi Johansson -- Hanse-Netzwerk Hamburg "The carrier frequency does not drift by accident." From hsilva@rwth-aachen.de Fri Nov 25 07:49:55 1994 Path: ashpoly!bigsur!pacrim!jpgate!kamome!rwth-aachen!hsilva From: hsilva@rwth-aachen.de (Hana Silva) Newsgroups: comp.dsp Subject: Re: Discussion: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994Nov25.074955.9885@rwth-aachen.de> Date: Fri, 25 Nov 1994 07:49:55 GMT References: <1994Nov21.142255.4756@demon.co.uk> Organization: RWTH Aachen Informatik NNTP-Posting-Host: rwth-aachen.de X-Newsreader: NewsWatcher 2.0b24 Lines: 8 In article <1994Nov21.142255.4756@demon.co.uk>, tpark@demon.co.uk (Tomas Park) writes: > Optimizing the Stardust Costas loop demodulator for the Motorola DSP56001 chip. Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. -- Hana Silva -- RWTH Aachen Informatik "Row 14. No joke."