From dschneider@demon.co.uk Mon Sep 05 14:16:22 1994 Path: ashpoly!cascade!mxgate!coyoacan!demon!dschneider From: dschneider@demon.co.uk (Dave Schneider) Newsgroups: comp.dsp Subject: Question: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994Sep05.141622.5863@demon.co.uk> Date: Mon, 05 Sep 1994 14:16:22 GMT Organization: Demon Internet Services UK NNTP-Posting-Host: demon.co.uk X-Newsreader: TIN [version 1.2 PL2] Lines: 10 Optimizing the Stardust Costas loop demodulator for the Motorola DSP56001 chip. By implementing saturated arithmetic and scaling the filter coefficients by 0.5, the loop runs in 18 instruction cycles per sample. 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. -- Dave Schneider Tape trading list upon request. SASE required for international mail. From rhughes@delphi.com Tue Sep 06 17:44:22 1994 Path: ashpoly!bigsur!pacrim!krgate!eunha!delphi!rhughes From: rhughes@delphi.com (Raj Hughes) Newsgroups: comp.dsp Subject: Re: Question: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994Sep06.174422.9722@delphi.com> Date: Tue, 06 Sep 1994 17:44:22 GMT References: <1994Sep05.141622.5863@demon.co.uk> Organization: Delphi Internet Services NNTP-Posting-Host: delphi.com X-Newsreader: TIN [version 1.2 PL2] Lines: 10 In article <1994Sep05.141622.5863@demon.co.uk>, dschneider@demon.co.uk (Dave Schneider) writes: > Optimizing the Stardust Costas loop demodulator for the Motorola DSP56001 chip. > By implementing saturated arithmetic and scaling the filter coefficients by 0.5, the loop runs in 18 instruction cycles per sample. Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. -- Raj Hughes Zyxel U-1496E @ 19,200 bps "A soul is not exclusive to biology." From nnilsson@illinois.edu Wed Sep 07 15:48:22 1994 Path: ashpoly!cascade!transat!ukc!fennimore!illinois!nnilsson From: nnilsson@illinois.edu (Natalia Nilsson) Newsgroups: comp.dsp Subject: Re: Question: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994Sep07.154822.2867@illinois.edu> Date: Wed, 07 Sep 1994 15:48:22 GMT References: <1994Sep05.141622.5863@demon.co.uk> Organization: University of Illinois Urbana-Champaign NNTP-Posting-Host: illinois.edu X-Newsreader: TIN [version 1.2 PL2] Lines: 12 In article <1994Sep05.141622.5863@demon.co.uk>, dschneider@demon.co.uk (Dave Schneider) writes: > Optimizing the Stardust Costas loop demodulator for the Motorola DSP56001 chip. > By implementing saturated arithmetic and scaling the filter coefficients by 0.5, the loop runs in 18 instruction cycles per sample. Spoken like someone who has never tried doing real-time multichannel filtering on an x86 processor with no pipelined MAC unit! Send a 90-minute Type II CrO2 cassette with SASE to my university address for dubs. -- Natalia Nilsson *PLONK* filter active for trolls. Commodore Amiga 500 (1MB OCS) - NetBSD 1.0 From aito@unam.mx Fri Sep 09 10:29:22 1994 Path: ashpoly!bigsur!pacrim!jpgate!kamome!unam!aito From: aito@unam.mx (Anton Ito) Newsgroups: comp.dsp Subject: Re: Question: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994Sep09.102922.9323@unam.mx> Date: Fri, 09 Sep 1994 10:29:22 GMT References: <1994Sep05.141622.5863@demon.co.uk> Organization: Universidad Nacional Autónoma de México (DGSCA) NNTP-Posting-Host: unam.mx X-Newsreader: WinVN 0.99.5 Lines: 11 In article <1994Sep05.141622.5863@demon.co.uk>, dschneider@demon.co.uk (Dave Schneider) 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. My 14.4k connection dropped twice trying to fetch this thread. Keep articles concise! -- Anton Ito Practical Peripherals 14.4 @ ISDN 64k bps "Hold for relay." From abrennan@delphi.com Sun Sep 11 01:33:22 1994 Path: ashpoly!cascade!transat!ukc!fennimore!delphi!abrennan From: abrennan@delphi.com (Amy Brennan) Newsgroups: comp.dsp Subject: Re: Question: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994Sep11.013322.4497@delphi.com> Date: Sun, 11 Sep 1994 01:33:22 GMT References: <1994Sep05.141622.5863@demon.co.uk> <1994Sep07.154822.2867@illinois.edu> Organization: Delphi Internet Services NNTP-Posting-Host: delphi.com X-Newsreader: WinVN 0.99.5 Lines: 9 In article <1994Sep07.154822.2867@illinois.edu>, nnilsson@illinois.edu (Natalia Nilsson) writes: > Spoken like someone who has never tried doing real-time multichannel filtering on an x86 processor with no pipelined MAC unit! Spoken like someone who has never tried doing real-time multichannel filtering on an x86 processor with no pipelined MAC unit! -- Amy Brennan Practical Peripherals 14.4 @ 28,800 bps "Marcus is not one man."