From mlaurent@kiae.su Sat May 06 05:15:10 1995 Path: ashpoly!bigsur!pacrim!krgate!eunha!kiae!mlaurent From: mlaurent@kiae.su (Mikhail Laurent) Newsgroups: comp.dsp Subject: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995May06.051510.8423@kiae.su> Date: Sat, 06 May 1995 05:15:10 GMT Organization: Kurchatov Institute of Atomic Energy, Moscow NNTP-Posting-Host: kiae.su X-Newsreader: Netscape 1.1N Lines: 10 Optimizing the Stardust Costas loop demodulator for the Motorola DSP56001 chip. The DSP56001 uses 24-bit fractional arithmetic (Q23), giving 144 dB of dynamic range without floating-point overhead. However, when downsampling from 44.1 kHz to 64 Hz, accumulator overflow in the biquad IIR filter can destabilize the loop. Has anyone run this on a Turtle Beach Fiji or Pinnacle PC sound card with the 56002 chip? -- Mikhail Laurent -- Kurchatov Institute of Atomic Energy, Moscow "When every node is whole, the channel opens." From jcampbell@ox.ac.uk Sun May 07 17:29:10 1995 Path: ashpoly!cascade!transat!eunet-fi!relcom!kiae!ox!jcampbell From: jcampbell@ox.ac.uk (Jen Campbell) Newsgroups: comp.dsp Subject: Re: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995May07.172910.7211@ox.ac.uk> Date: Sun, 07 May 1995 17:29:10 GMT References: <1995May06.051510.8423@kiae.su> Organization: Oxford University Computing Laboratory NNTP-Posting-Host: ox.ac.uk X-Newsreader: NewsWatcher 2.0b24 Lines: 12 In article <1995May06.051510.8423@kiae.su>, mlaurent@kiae.su (Mikhail Laurent) writes: > Optimizing the Stardust Costas loop demodulator for the Motorola DSP56001 chip. > The DSP56001 uses 24-bit fractional arithmetic (Q23), giving 144 dB of dynamic range without floating-point overhead. Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. PGP Public key available via finger or upon request. -- Jen Campbell "We don't sign stars. We build them." Amiga 3000T / Linux 1.2.13 From rsato@cmu.edu Mon May 08 13:16:10 1995 Path: ashpoly!cascade!mxgate!coyoacan!cmu!rsato From: rsato@cmu.edu (Renata Sato) Newsgroups: comp.dsp Subject: Re: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995May08.131610.6163@cmu.edu> Date: Mon, 08 May 1995 13:16:10 GMT References: <1995May06.051510.8423@kiae.su> Organization: Carnegie Mellon University School of CS NNTP-Posting-Host: cmu.edu X-Newsreader: Netscape 1.1N Lines: 10 In article <1995May06.051510.8423@kiae.su>, mlaurent@kiae.su (Mikhail Laurent) writes: > Optimizing the Stardust Costas loop demodulator for the Motorola DSP56001 chip. > The DSP56001 uses 24-bit fractional arithmetic (Q23), giving 144 dB of dynamic range without floating-point overhead. Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. -- Renata Sato *PLONK* filter active for trolls. Pentium 90 (OS/2 Warp) - NetBSD 1.0 From elarsson@cmu.edu Wed May 10 14:53:10 1995 Path: ashpoly!cascade!transat!eunet-fi!relcom!kiae!cmu!elarsson From: elarsson@cmu.edu (Élodie Larsson) Newsgroups: comp.dsp Subject: Re: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995May10.145310.8563@cmu.edu> Date: Wed, 10 May 1995 14:53:10 GMT References: <1995May06.051510.8423@kiae.su> <1995May07.172910.7211@ox.ac.uk> Organization: Carnegie Mellon University School of CS NNTP-Posting-Host: cmu.edu X-Newsreader: WinVN 0.99.5 Lines: 10 In article <1995May07.172910.7211@ox.ac.uk>, jcampbell@ox.ac.uk (Jen Campbell) writes: > Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. > PGP Public key available via finger or upon request. Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. -- Élodie Larsson *PLONK* filter active for trolls. Amiga 3000T - NetBSD 1.0 From nkuznetsov@clari.net Thu May 11 22:54:10 1995 Path: ashpoly!bigsur!pacrim!jpgate!kamome!clari!nkuznetsov From: nkuznetsov@clari.net (Natalia Kuznetsov) Newsgroups: comp.dsp Subject: Re: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995May11.225410.9037@clari.net> Date: Thu, 11 May 1995 22:54:10 GMT References: <1995May06.051510.8423@kiae.su> <1995May07.172910.7211@ox.ac.uk> <1995May10.145310.8563@cmu.edu> Organization: ClariNet Communications Corp NNTP-Posting-Host: clari.net X-Newsreader: Netscape 1.1N Lines: 9 In article <1995May10.145310.8563@cmu.edu>, elarsson@cmu.edu (Élodie Larsson) writes: > Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. -- Natalia Kuznetsov *PLONK* filter active for trolls. Atari Falcon 030 - NetBSD 1.0