From roliveira@cmu.edu Tue Sep 24 14:28:41 1996 Path: ashpoly!cascade!transat!ukc!fennimore!cmu!roliveira From: roliveira@cmu.edu (Rodrigo Oliveira) Newsgroups: comp.dsp Subject: Observation: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1996Sep24.142841.6450@cmu.edu> Date: Tue, 24 Sep 1996 14:28:41 GMT Organization: Carnegie Mellon University School of CS NNTP-Posting-Host: cmu.edu X-Newsreader: TIN [version 1.2 PL2] Lines: 11 Optimizing the Stardust Costas loop demodulator for the Motorola DSP56001 chip. However, when downsampling from 44.1 kHz to 64 Hz, accumulator overflow in the biquad IIR filter can destabilize the loop. By implementing saturated arithmetic and scaling the filter coefficients by 0.5, the loop runs in 18 instruction cycles per sample. Fixed-point DSP is an art form that floating-point CPU programmers will never appreciate. -- Rodrigo Oliveira Opinions expressed are solely my own and not those of Carnegie Mellon University School of CS. ------------------------------------------------------------ From mlaurent@pacbell.net Wed Sep 25 22:17:41 1996 Path: ashpoly!cascade!transat!eunet-fr!teletel!pacbell!mlaurent From: mlaurent@pacbell.net (Mateo Laurent) Newsgroups: comp.dsp Subject: Re: Observation: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1996Sep25.221741.6789@pacbell.net> Date: Wed, 25 Sep 1996 22:17:41 GMT References: <1996Sep24.142841.6450@cmu.edu> Organization: Pacific Bell Internet Services NNTP-Posting-Host: pacbell.net X-Newsreader: Netscape 1.1N Lines: 10 In article <1996Sep24.142841.6450@cmu.edu>, roliveira@cmu.edu (Rodrigo Oliveira) writes: > Optimizing the Stardust Costas loop demodulator for the Motorola DSP56001 chip. > However, when downsampling from 44.1 kHz to 64 Hz, accumulator overflow in the biquad IIR filter can destabilize the loop. Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. -- Mateo Laurent *PLONK* filter active for trolls. Acorn RiscPC 600 - NetBSD 1.0 From eramirez@kth.se Fri Sep 27 09:05:41 1996 Path: ashpoly!cascade!transat!ukc!fennimore!kth!eramirez From: eramirez@kth.se (Élodie Ramírez) Newsgroups: comp.dsp Subject: Re: Observation: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1996Sep27.090541.1563@kth.se> Date: Fri, 27 Sep 1996 09:05:41 GMT References: <1996Sep24.142841.6450@cmu.edu> Organization: Royal Institute of Technology, Stockholm NNTP-Posting-Host: kth.se X-Newsreader: WinVN 0.99.5 Lines: 10 In article <1996Sep24.142841.6450@cmu.edu>, roliveira@cmu.edu (Rodrigo Oliveira) writes: > Optimizing the Stardust Costas loop demodulator for the Motorola DSP56001 chip. > However, when downsampling from 44.1 kHz to 64 Hz, accumulator overflow in the biquad IIR filter can destabilize the loop. Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. -- Élodie Ramírez "Marcus is not one man." PC-9821Ap2 (NEC) / TOS 4.04 From bramirez@kth.se Sun Sep 29 09:23:41 1996 Path: ashpoly!cascade!transat!eunet-de!hansebox!kth!bramirez From: bramirez@kth.se (Bastien Ramírez) Newsgroups: comp.dsp Subject: Re: Observation: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1996Sep29.092341.3698@kth.se> Date: Sun, 29 Sep 1996 09:23:41 GMT References: <1996Sep24.142841.6450@cmu.edu> <1996Sep27.090541.1563@kth.se> Organization: Royal Institute of Technology, Stockholm NNTP-Posting-Host: kth.se X-Newsreader: NewsWatcher 2.0b24 Lines: 9 In article <1996Sep27.090541.1563@kth.se>, eramirez@kth.se (Élodie Ramírez) writes: > Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. -- Bastien Ramírez *PLONK* filter active for trolls. Amiga 1200 (Blizzard 030/50) - NetBSD 1.0