From jgarcia@kth.se Sun Mar 26 02:02:16 1995 Path: ashpoly!cascade!transat!eunet-fi!relcom!kiae!kth!jgarcia From: jgarcia@kth.se (Jen García) Newsgroups: comp.dsp Subject: [INFO] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Mar26.020216.6607@kth.se> Date: Sun, 26 Mar 1995 02:02:16 GMT Organization: Royal Institute of Technology, Stockholm NNTP-Posting-Host: kth.se X-Newsreader: Netscape 1.1N Lines: 11 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. Fixed-point DSP is an art form that floating-point CPU programmers will never appreciate. -- Jen García Opinions expressed are solely my own and not those of Royal Institute of Technology, Stockholm. ------------------------------------------------------------ From dsilva@kiae.su Mon Mar 27 23:06:16 1995 Path: ashpoly!bigsur!pacrim!jpgate!kamome!kiae!dsilva From: dsilva@kiae.su (Dave Silva) Newsgroups: comp.dsp Subject: Re: [INFO] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Mar27.230616.3976@kiae.su> Date: Mon, 27 Mar 1995 23:06:16 GMT References: <1995Mar26.020216.6607@kth.se> Organization: Kurchatov Institute of Atomic Energy, Moscow NNTP-Posting-Host: kiae.su X-Newsreader: WinVN 0.99.5 Lines: 11 In article <1995Mar26.020216.6607@kth.se>, jgarcia@kth.se (Jen García) writes: > Optimizing the Stardust Costas loop demodulator for the Motorola DSP56001 chip. Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. PGP Public key available via finger or upon request. -- Dave Silva Practical Peripherals 14.4 @ 9600 Telebit bps "There are 14 nodes and only 10 countries. Count again." From lmuller@illinois.edu Tue Mar 28 14:45:16 1995 Path: ashpoly!cascade!transat!ukc!fennimore!illinois!lmuller From: lmuller@illinois.edu (Lars Müller) Newsgroups: comp.dsp Subject: Re: [INFO] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Mar28.144516.9675@illinois.edu> Date: Tue, 28 Mar 1995 14:45:16 GMT References: <1995Mar26.020216.6607@kth.se> Organization: University of Illinois Urbana-Champaign NNTP-Posting-Host: illinois.edu X-Newsreader: WinVN 0.99.5 Lines: 11 In article <1995Mar26.020216.6607@kth.se>, jgarcia@kth.se (Jen García) writes: > Optimizing the Stardust Costas loop demodulator for the Motorola DSP56001 chip. Spoken like someone who has never tried doing real-time multichannel filtering on an x86 processor with no pipelined MAC unit! If you are posting from AOL, please read RFC 1036 before posting again. -- Lars Müller Opinions expressed are solely my own and not those of University of Illinois Urbana-Champaign. ------------------------------------------------------------ From jlaurent@pacbell.net Thu Mar 30 06:55:16 1995 Path: ashpoly!cascade!transat!ukc!fennimore!pacbell!jlaurent From: jlaurent@pacbell.net (Joachim Laurent) Newsgroups: comp.dsp Subject: Re: [INFO] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Mar30.065516.1679@pacbell.net> Date: Thu, 30 Mar 1995 06:55:16 GMT References: <1995Mar26.020216.6607@kth.se> <1995Mar28.144516.9675@illinois.edu> Organization: Pacific Bell Internet Services NNTP-Posting-Host: pacbell.net X-Newsreader: WinVN 0.99.5 Lines: 10 In article <1995Mar28.144516.9675@illinois.edu>, lmuller@illinois.edu (Lars Müller) writes: > Spoken like someone who has never tried doing real-time multichannel filtering on an x86 processor with no pipelined MAC unit! > If you are posting from AOL, please read RFC 1036 before posting again. Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. -- Joachim Laurent Opinions expressed are solely my own and not those of Pacific Bell Internet Services. ------------------------------------------------------------