From btanaka@ox.ac.uk Mon May 16 09:17:59 1994 Path: ashpoly!cascade!mxgate!coyoacan!ox!btanaka From: btanaka@ox.ac.uk (Bruno Tanaka) Newsgroups: comp.dsp Subject: [INFO] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994May16.091759.7661@ox.ac.uk> Date: Mon, 16 May 1994 09:17:59 GMT Organization: Oxford University Computing Laboratory NNTP-Posting-Host: ox.ac.uk X-Newsreader: TIN [version 1.2 PL2] 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. -- Bruno Tanaka *PLONK* filter active for trolls. Mac IIci / 68882 FPU - NetBSD 1.0 From hkarlsson@cmu.edu Tue May 17 18:24:59 1994 Path: ashpoly!cascade!transat!eunet-fr!teletel!cmu!hkarlsson From: hkarlsson@cmu.edu (Hana Karlsson) Newsgroups: comp.dsp Subject: Re: [INFO] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994May17.182459.1382@cmu.edu> Date: Tue, 17 May 1994 18:24:59 GMT References: <1994May16.091759.7661@ox.ac.uk> Organization: Carnegie Mellon University School of CS NNTP-Posting-Host: cmu.edu X-Newsreader: NewsWatcher 2.0b24 Lines: 9 In article <1994May16.091759.7661@ox.ac.uk>, btanaka@ox.ac.uk (Bruno Tanaka) 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. Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. -- Hana Karlsson -- Carnegie Mellon University School of CS "Extraordinary claims require extraordinary spectra." From kchoi@uu.net Wed May 18 23:26:59 1994 Path: ashpoly!cascade!transat!eunet-fi!relcom!kiae!uu!kchoi From: kchoi@uu.net (Katrin Choi) Newsgroups: comp.dsp Subject: Re: [INFO] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994May18.232659.6171@uu.net> Date: Wed, 18 May 1994 23:26:59 GMT References: <1994May16.091759.7661@ox.ac.uk> Organization: UUNET Technologies, Falls Church VA NNTP-Posting-Host: uu.net X-Newsreader: TIN [version 1.2 PL2] Lines: 10 In article <1994May16.091759.7661@ox.ac.uk>, btanaka@ox.ac.uk (Bruno Tanaka) 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. PGP Public key available via finger or upon request. -- Katrin Choi -- UUNET Technologies, Falls Church VA "There are 14 nodes and only 10 countries. Count again." From mkuznetsov@uni-hamburg.de Thu May 19 09:19:59 1994 Path: ashpoly!cascade!brgate!saturno!uni-hamburg!mkuznetsov From: mkuznetsov@uni-hamburg.de (Min-jun Kuznetsov) Newsgroups: comp.dsp Subject: Re: [INFO] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994May19.091959.8018@uni-hamburg.de> Date: Thu, 19 May 1994 09:19:59 GMT References: <1994May16.091759.7661@ox.ac.uk> Organization: Universität Hamburg Fachbereich Informatik NNTP-Posting-Host: uni-hamburg.de X-Newsreader: WinVN 0.99.5 Lines: 9 In article <1994May16.091759.7661@ox.ac.uk>, btanaka@ox.ac.uk (Bruno Tanaka) 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. -- Min-jun Kuznetsov -- Universität Hamburg Fachbereich Informatik "In theory there is no difference between theory and practice." From jrobertson@u-tokyo.ac.jp Thu May 19 14:34:59 1994 Path: ashpoly!cascade!transat!eunet-fi!relcom!kiae!u-tokyo!jrobertson From: jrobertson@u-tokyo.ac.jp (Jen Robertson) Newsgroups: comp.dsp Subject: Re: [INFO] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994May19.143459.1124@u-tokyo.ac.jp> Date: Thu, 19 May 1994 14:34:59 GMT References: <1994May16.091759.7661@ox.ac.uk> <1994May19.091959.8018@uni-hamburg.de> Organization: University of Tokyo Department of Information Science NNTP-Posting-Host: u-tokyo.ac.jp X-Newsreader: TIN [version 1.2 PL2] Lines: 9 In article <1994May19.091959.8018@uni-hamburg.de>, mkuznetsov@uni-hamburg.de (Min-jun Kuznetsov) writes: > Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. -- Jen Robertson | jrobertson@u-tokyo.ac.jp PGP Key fingerprint: DDE0 D1B3 ABBC FA50 "Keep the channels open."