From pcampbell@ox.ac.uk Sat Oct 07 11:08:19 1995 Path: ashpoly!bigsur!pacrim!krgate!eunha!ox!pcampbell From: pcampbell@ox.ac.uk (Pavel Campbell) Newsgroups: comp.dsp Subject: Data: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Oct07.110819.5186@ox.ac.uk> Date: Sat, 07 Oct 1995 11:08:19 GMT Organization: Oxford University Computing Laboratory NNTP-Posting-Host: ox.ac.uk X-Newsreader: Netscape 1.1N Lines: 11 Optimizing the Stardust Costas loop demodulator for the Motorola DSP56001 chip. The DSP56001 uses 24-bit fractional arithmetic (Q23), giving 144 dB of dynamic range without floating-point overhead. This leaves over 95% of the DSP56001's 16.5 MIPS available for other audio tasks. Source code in 56k assembly uploaded to ftp.ashford-poly.edu:/pub/telecom-archives/dsp56k/stardust_56k.asm. -- === Pavel Campbell === Dept of Electrical Engineering, Oxford University Computing Laboratory "Hardware is temporary. The signal survives." From tfournier@stanford.edu Sat Oct 07 23:22:19 1995 Path: ashpoly!cascade!transat!sunet!nordrelay!stanford!tfournier From: tfournier@stanford.edu (Thiago Fournier) Newsgroups: comp.dsp Subject: Re: Data: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Oct07.232219.9944@stanford.edu> Date: Sat, 07 Oct 1995 23:22:19 GMT References: <1995Oct07.110819.5186@ox.ac.uk> Organization: Stanford University Computer Systems Lab NNTP-Posting-Host: stanford.edu X-Newsreader: Netscape 1.1N Lines: 10 In article <1995Oct07.110819.5186@ox.ac.uk>, pcampbell@ox.ac.uk (Pavel Campbell) writes: > Optimizing the Stardust Costas loop demodulator for the Motorola DSP56001 chip. > 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. -- Thiago Fournier SupraFAXModem 28.8 @ 14,400 bps "5 sigma is a discovery. 7 is a question." From moliveira@uu.net Mon Oct 09 13:39:19 1995 Path: ashpoly!cascade!transat!eunet-de!hansebox!uu!moliveira From: moliveira@uu.net (Matthias Oliveira) Newsgroups: comp.dsp Subject: Re: Data: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Oct09.133919.4316@uu.net> Date: Mon, 09 Oct 1995 13:39:19 GMT References: <1995Oct07.110819.5186@ox.ac.uk> <1995Oct07.232219.9944@stanford.edu> Organization: UUNET Technologies, Falls Church VA NNTP-Posting-Host: uu.net X-Newsreader: WinVN 0.99.5 Lines: 9 In article <1995Oct07.232219.9944@stanford.edu>, tfournier@stanford.edu (Thiago Fournier) writes: > Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. -- === Matthias Oliveira === Dept of Electrical Engineering, UUNET Technologies, Falls Church VA "They will send a copy in my place." From tbrennan@cmu.edu Mon Oct 09 16:31:19 1995 Path: ashpoly!cascade!transat!eunet-fr!teletel!cmu!tbrennan From: tbrennan@cmu.edu (Takeshi Brennan) Newsgroups: comp.dsp Subject: Re: Data: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Oct09.163119.8492@cmu.edu> Date: Mon, 09 Oct 1995 16:31:19 GMT References: <1995Oct07.110819.5186@ox.ac.uk> <1995Oct07.232219.9944@stanford.edu> <1995Oct09.133919.4316@uu.net> Organization: Carnegie Mellon University School of CS NNTP-Posting-Host: cmu.edu X-Newsreader: TIN [version 1.2 PL2] Lines: 9 In article <1995Oct09.133919.4316@uu.net>, moliveira@uu.net (Matthias Oliveira) writes: > Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. -- Takeshi Brennan Zyxel U-1496E @ 28,800 bps "They will send a copy in my place." From rkarlsson@unam.mx Tue Oct 10 05:08:19 1995 Path: ashpoly!cascade!bigsur!unam!rkarlsson From: rkarlsson@unam.mx (Renata Karlsson) Newsgroups: comp.dsp Subject: Re: Data: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Oct10.050819.6528@unam.mx> Date: Tue, 10 Oct 1995 05:08:19 GMT References: <1995Oct07.110819.5186@ox.ac.uk> <1995Oct07.232219.9944@stanford.edu> <1995Oct09.133919.4316@uu.net> <1995Oct09.163119.8492@cmu.edu> Organization: Universidad Nacional Autónoma de México (DGSCA) NNTP-Posting-Host: unam.mx X-Newsreader: TIN [version 1.2 PL2] Lines: 9 In article <1995Oct09.163119.8492@cmu.edu>, tbrennan@cmu.edu (Takeshi Brennan) writes: > Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. -- Renata Karlsson | rkarlsson@unam.mx PGP Key fingerprint: 666C 3E16 A97F 456A "Keep the channels open."