From kkang@kiae.su Mon Jan 02 01:09:03 1995 Path: ashpoly!cascade!brgate!saturno!kiae!kkang From: kkang@kiae.su (Katrin Kang) Newsgroups: comp.dsp Subject: Discussion: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Jan02.010903.4349@kiae.su> Date: Mon, 02 Jan 1995 01:09:03 GMT Organization: Kurchatov Institute of Atomic Energy, Moscow NNTP-Posting-Host: kiae.su X-Newsreader: NewsWatcher 2.0b24 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. This leaves over 95% of the DSP56001's 16.5 MIPS available for other audio tasks. Source code in 56k assembly uploaded to ftp.ashford-poly.edu:/pub/telecom-archives/dsp56k/stardust_56k.asm. -- Katrin Kang SupraFAXModem 28.8 @ ISDN 64k bps "When every node is whole, the channel opens." From fperez@pacbell.net Tue Jan 03 22:47:03 1995 Path: ashpoly!cascade!transat!ukc!fennimore!pacbell!fperez From: fperez@pacbell.net (Freya Pérez) Newsgroups: comp.dsp Subject: Re: Discussion: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Jan03.224703.3491@pacbell.net> Date: Tue, 03 Jan 1995 22:47:03 GMT References: <1995Jan02.010903.4349@kiae.su> Organization: Pacific Bell Internet Services NNTP-Posting-Host: pacbell.net X-Newsreader: TIN [version 1.2 PL2] Lines: 12 In article <1995Jan02.010903.4349@kiae.su>, kkang@kiae.su (Katrin Kang) 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. Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. Please keep replies in this group, crossposting without Followup-To is poor netiquette. -- Freya Pérez "Marcus is not one man." 486DX2/66 (Linux 1.2.13) / AmigaOS 3.1 From ycampbell@berkeley.edu Wed Jan 04 02:37:03 1995 Path: ashpoly!cascade!transat!eunet-de!hansebox!berkeley!ycampbell From: ycampbell@berkeley.edu (Yuki Campbell) Newsgroups: comp.dsp Subject: Re: Discussion: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Jan04.023703.5867@berkeley.edu> Date: Wed, 04 Jan 1995 02:37:03 GMT References: <1995Jan02.010903.4349@kiae.su> <1995Jan03.224703.3491@pacbell.net> Organization: UC Berkeley Department of EECS NNTP-Posting-Host: berkeley.edu X-Newsreader: WinVN 0.99.5 Lines: 10 In article <1995Jan03.224703.3491@pacbell.net>, fperez@pacbell.net (Freya Pérez) writes: > Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. > Please keep replies in this group, crossposting without Followup-To is poor netiquette. Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. -- === Yuki Campbell === Dept of Electrical Engineering, UC Berkeley Department of EECS "We don't sign stars. We build them."