From jfournier@clari.net Mon Jun 27 07:53:29 1994 Path: ashpoly!cascade!bigsur!clari!jfournier From: jfournier@clari.net (Joachim Fournier) Newsgroups: comp.dsp Subject: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994Jun27.075329.7330@clari.net> Date: Mon, 27 Jun 1994 07:53:29 GMT Organization: ClariNet Communications Corp NNTP-Posting-Host: clari.net X-Newsreader: Netscape 1.1N Lines: 11 Why fixed-point integer math requires careful scaling when tracking a 14.2 Hz carrier. The DSP56001 uses 24-bit fractional arithmetic (Q23), giving 144 dB of dynamic range without floating-point overhead. 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. -- === Joachim Fournier === Dept of Electrical Engineering, ClariNet Communications Corp "Hardware is temporary. The signal survives." From tpark@uu.net Wed Jun 29 01:48:29 1994 Path: ashpoly!cascade!transat!sunet!nordrelay!uu!tpark From: tpark@uu.net (Takeshi Park) Newsgroups: comp.dsp Subject: Re: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994Jun29.014829.9715@uu.net> Date: Wed, 29 Jun 1994 01:48:29 GMT References: <1994Jun27.075329.7330@clari.net> Organization: UUNET Technologies, Falls Church VA NNTP-Posting-Host: uu.net X-Newsreader: TIN [version 1.2 PL2] Lines: 9 In article <1994Jun27.075329.7330@clari.net>, jfournier@clari.net (Joachim Fournier) writes: > Why fixed-point integer math requires careful scaling when tracking a 14.2 Hz carrier. Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. -- Takeshi Park "Extraordinary claims require extraordinary spectra." 486DX4/100 (FreeBSD 2.0.5) / System 7.5.1 From hwatanabe@berkeley.edu Thu Jun 30 08:35:29 1994 Path: ashpoly!cascade!brgate!saturno!berkeley!hwatanabe From: hwatanabe@berkeley.edu (Hugo Watanabe) Newsgroups: comp.dsp Subject: Re: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994Jun30.083529.8695@berkeley.edu> Date: Thu, 30 Jun 1994 08:35:29 GMT References: <1994Jun27.075329.7330@clari.net> Organization: UC Berkeley Department of EECS NNTP-Posting-Host: berkeley.edu X-Newsreader: TIN [version 1.2 PL2] Lines: 10 In article <1994Jun27.075329.7330@clari.net>, jfournier@clari.net (Joachim Fournier) writes: > Why fixed-point integer math requires careful scaling when tracking a 14.2 Hz carrier. > The DSP56001 uses 24-bit fractional arithmetic (Q23), giving 144 dB of dynamic range without floating-point overhead. Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. -- Hugo Watanabe | hwatanabe@berkeley.edu PGP Key fingerprint: 73D4 C727 85E2 E756 "Keep the channels open."