From nivanov@uni-hamburg.de Mon Mar 20 21:33:16 1995 Path: ashpoly!cascade!bigsur!uni-hamburg!nivanov From: nivanov@uni-hamburg.de (Nadia Ivanov) Newsgroups: comp.dsp Subject: [SPECULATION] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Mar20.213316.5902@uni-hamburg.de> Date: Mon, 20 Mar 1995 21:33:16 GMT Organization: Universität Hamburg Fachbereich Informatik NNTP-Posting-Host: uni-hamburg.de X-Newsreader: Netscape 1.1N Lines: 10 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. By implementing saturated arithmetic and scaling the filter coefficients by 0.5, the loop runs in 18 instruction cycles per sample. Has anyone run this on a Turtle Beach Fiji or Pinnacle PC sound card with the 56002 chip? -- Nadia Ivanov Tape trading list upon request. SASE required for international mail. From mkowalski@cam.ac.uk Wed Mar 22 21:58:16 1995 Path: ashpoly!cascade!transat!sunet!nordrelay!cam!mkowalski From: mkowalski@cam.ac.uk (Mikhail Kowalski) Newsgroups: comp.dsp Subject: Re: [SPECULATION] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Mar22.215816.7810@cam.ac.uk> Date: Wed, 22 Mar 1995 21:58:16 GMT References: <1995Mar20.213316.5902@uni-hamburg.de> Organization: University of Cambridge Computer Laboratory NNTP-Posting-Host: cam.ac.uk X-Newsreader: TIN [version 1.2 PL2] Lines: 10 In article <1995Mar20.213316.5902@uni-hamburg.de>, nivanov@uni-hamburg.de (Nadia Ivanov) 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. Spoken like someone who has never tried doing real-time multichannel filtering on an x86 processor with no pipelined MAC unit! -- Mikhail Kowalski Opinions expressed are solely my own and not those of University of Cambridge Computer Laboratory. ------------------------------------------------------------ From hmacdonald@kiae.su Thu Mar 23 01:13:16 1995 Path: ashpoly!bigsur!pacrim!jpgate!kamome!kiae!hmacdonald From: hmacdonald@kiae.su (Hugo MacDonald) Newsgroups: comp.dsp Subject: Re: [SPECULATION] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Mar23.011316.4801@kiae.su> Date: Thu, 23 Mar 1995 01:13:16 GMT References: <1995Mar20.213316.5902@uni-hamburg.de> <1995Mar22.215816.7810@cam.ac.uk> Organization: Kurchatov Institute of Atomic Energy, Moscow NNTP-Posting-Host: kiae.su X-Newsreader: TIN [version 1.2 PL2] Lines: 8 In article <1995Mar22.215816.7810@cam.ac.uk>, mkowalski@cam.ac.uk (Mikhail Kowalski) writes: > Spoken like someone who has never tried doing real-time multichannel filtering on an x86 processor with no pipelined MAC unit! Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. -- Hugo MacDonald Tape trading list upon request. SASE required for international mail. From jlee@delphi.com Thu Mar 23 02:49:16 1995 Path: ashpoly!cascade!transat!eunet-de!hansebox!delphi!jlee From: jlee@delphi.com (Jens Lee) Newsgroups: comp.dsp Subject: Re: [SPECULATION] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Mar23.024916.9944@delphi.com> Date: Thu, 23 Mar 1995 02:49:16 GMT References: <1995Mar20.213316.5902@uni-hamburg.de> <1995Mar22.215816.7810@cam.ac.uk> Organization: Delphi Internet Services NNTP-Posting-Host: delphi.com X-Newsreader: TIN [version 1.2 PL2] Lines: 11 In article <1995Mar22.215816.7810@cam.ac.uk>, mkowalski@cam.ac.uk (Mikhail Kowalski) writes: > Spoken like someone who has never tried doing real-time multichannel filtering on an x86 processor with no pipelined MAC unit! 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! -- Jens Lee | jlee@delphi.com PGP Key fingerprint: 50A2 4346 CC31 B92E "Keep the channels open."