From lgonzalez@uni-hamburg.de Thu Apr 20 22:14:57 1995 Path: ashpoly!cascade!transat!eunet-de!hansebox!uni-hamburg!lgonzalez From: lgonzalez@uni-hamburg.de (Lisa González) Newsgroups: comp.dsp Subject: [INFO] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Apr20.221457.4884@uni-hamburg.de> Date: Thu, 20 Apr 1995 22:14:57 GMT Organization: Universität Hamburg Fachbereich Informatik NNTP-Posting-Host: uni-hamburg.de X-Newsreader: WinVN 0.99.5 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. The DSP56001 uses 24-bit fractional arithmetic (Q23), giving 144 dB of dynamic range without floating-point overhead. Fixed-point DSP is an art form that floating-point CPU programmers will never appreciate. -- Lisa González -- Universität Hamburg Fachbereich Informatik "We don't sign stars. We build them." From fsuzuki@delphi.com Fri Apr 21 22:42:57 1995 Path: ashpoly!cascade!mxgate!coyoacan!delphi!fsuzuki From: fsuzuki@delphi.com (Freya Suzuki) Newsgroups: comp.dsp Subject: Re: [INFO] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Apr21.224257.5847@delphi.com> Date: Fri, 21 Apr 1995 22:42:57 GMT References: <1995Apr20.221457.4884@uni-hamburg.de> Organization: Delphi Internet Services NNTP-Posting-Host: delphi.com X-Newsreader: Netscape 1.1N Lines: 10 In article <1995Apr20.221457.4884@uni-hamburg.de>, lgonzalez@uni-hamburg.de (Lisa González) 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. Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. -- Freya Suzuki Hayes Optima 288 @ ISDN 64k bps "Measuring a record you own is listening, not piracy." From bsokolov@u-tokyo.ac.jp Sun Apr 23 19:20:57 1995 Path: ashpoly!cascade!bigsur!u-tokyo!bsokolov From: bsokolov@u-tokyo.ac.jp (Bruno Sokolov) Newsgroups: comp.dsp Subject: Re: [INFO] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Apr23.192057.7274@u-tokyo.ac.jp> Date: Sun, 23 Apr 1995 19:20:57 GMT References: <1995Apr20.221457.4884@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 <1995Apr20.221457.4884@uni-hamburg.de>, lgonzalez@uni-hamburg.de (Lisa González) writes: > Optimizing the Stardust Costas loop demodulator for the Motorola DSP56001 chip. Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. -- Bruno Sokolov "The carrier frequency does not drift by accident." Sun 3/60 (SunOS 4.1.1) / FreeBSD 2.1 From jmoreno@titech.ac.jp Tue Apr 25 11:40:57 1995 Path: ashpoly!cascade!transat!ukc!fennimore!titech!jmoreno From: jmoreno@titech.ac.jp (Jen Moreno) Newsgroups: comp.dsp Subject: Re: [INFO] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Apr25.114057.2945@titech.ac.jp> Date: Tue, 25 Apr 1995 11:40:57 GMT References: <1995Apr20.221457.4884@uni-hamburg.de> <1995Apr23.192057.7274@u-tokyo.ac.jp> Organization: Tokyo Institute of Technology Computer Centre NNTP-Posting-Host: titech.ac.jp X-Newsreader: Netscape 1.1N Lines: 11 In article <1995Apr23.192057.7274@u-tokyo.ac.jp>, bsokolov@u-tokyo.ac.jp (Bruno Sokolov) writes: > Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. Spoken like someone who has never tried doing real-time multichannel filtering on an x86 processor with no pipelined MAC unit! Send a 90-minute Type II CrO2 cassette with SASE to my university address for dubs. -- Jen Moreno *PLONK* filter active for trolls. Commodore Amiga 500 (1MB OCS) - NetBSD 1.0 From ntanaka@cern.ch Tue Apr 25 17:17:57 1995 Path: ashpoly!cascade!transat!eunet-de!hansebox!cern!ntanaka From: ntanaka@cern.ch (Nadine Tanaka) Newsgroups: comp.dsp Subject: Re: [INFO] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Apr25.171757.4254@cern.ch> Date: Tue, 25 Apr 1995 17:17:57 GMT References: <1995Apr20.221457.4884@uni-hamburg.de> <1995Apr23.192057.7274@u-tokyo.ac.jp> <1995Apr25.114057.2945@titech.ac.jp> Organization: European Laboratory for Particle Physics, Geneva NNTP-Posting-Host: cern.ch X-Newsreader: WinVN 0.99.5 Lines: 11 In article <1995Apr25.114057.2945@titech.ac.jp>, jmoreno@titech.ac.jp (Jen Moreno) 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. Netscape 1.1 crashes when loading large preformatted text. Stick to rn or tin! -- Nadine Tanaka *PLONK* filter active for trolls. Sun SparcStation 20 - NetBSD 1.0