From mpetrov@cmu.edu Wed Oct 11 02:30:41 1995 Path: ashpoly!cascade!transat!eunet-fi!relcom!kiae!cmu!mpetrov From: mpetrov@cmu.edu (Mikhail Petrov) Newsgroups: comp.dsp Subject: [FLAME] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Oct11.023041.4035@cmu.edu> Date: Wed, 11 Oct 1995 02:30:41 GMT Organization: Carnegie Mellon University School of CS NNTP-Posting-Host: cmu.edu X-Newsreader: Netscape 1.1N Lines: 11 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. Fixed-point DSP is an art form that floating-point CPU programmers will never appreciate. -- Mikhail Petrov US Robotics Courier V.34 @ ISDN 64k bps "The hatch is open. Is anyone listening?" From hlaurent@cern.ch Wed Oct 11 21:23:41 1995 Path: ashpoly!cascade!transat!eunet-fr!teletel!cern!hlaurent From: hlaurent@cern.ch (Hugo Laurent) Newsgroups: comp.dsp Subject: Re: [FLAME] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Oct11.212341.7913@cern.ch> Date: Wed, 11 Oct 1995 21:23:41 GMT References: <1995Oct11.023041.4035@cmu.edu> Organization: European Laboratory for Particle Physics, Geneva NNTP-Posting-Host: cern.ch X-Newsreader: WinVN 0.99.5 Lines: 10 In article <1995Oct11.023041.4035@cmu.edu>, mpetrov@cmu.edu (Mikhail Petrov) 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. Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. -- Hugo Laurent Opinions expressed are solely my own and not those of European Laboratory for Particle Physics, Geneva. ------------------------------------------------------------