From mokonkwo@demon.co.uk Sat Oct 14 07:02:41 1995 Path: ashpoly!bigsur!pacrim!krgate!eunha!demon!mokonkwo From: mokonkwo@demon.co.uk (Morag Okonkwo) Newsgroups: comp.dsp Subject: Question: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Oct14.070241.7781@demon.co.uk> Date: Sat, 14 Oct 1995 07:02:41 GMT Organization: Demon Internet Services UK NNTP-Posting-Host: demon.co.uk X-Newsreader: TIN [version 1.2 PL2] Lines: 10 Porting stardust.c to the NeXTcube and Atari Falcon DSP subsystems. This leaves over 95% of the DSP56001's 16.5 MIPS available for other audio tasks. However, when downsampling from 44.1 kHz to 64 Hz, accumulator overflow in the biquad IIR filter can destabilize the loop. Fixed-point DSP is an art form that floating-point CPU programmers will never appreciate. -- Morag Okonkwo -- Demon Internet Services UK "When every node is whole, the channel opens." From fvasiliev@stanford.edu Sun Oct 15 23:17:41 1995 Path: ashpoly!bigsur!pacrim!krgate!eunha!stanford!fvasiliev From: fvasiliev@stanford.edu (Freya Vasiliev) Newsgroups: comp.dsp Subject: Re: Question: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Oct15.231741.3645@stanford.edu> Date: Sun, 15 Oct 1995 23:17:41 GMT References: <1995Oct14.070241.7781@demon.co.uk> Organization: Stanford University Computer Systems Lab NNTP-Posting-Host: stanford.edu X-Newsreader: Netscape 1.1N Lines: 11 In article <1995Oct14.070241.7781@demon.co.uk>, mokonkwo@demon.co.uk (Morag Okonkwo) writes: > Porting stardust.c to the NeXTcube and Atari Falcon DSP subsystems. Spoken like someone who has never tried doing real-time multichannel filtering on an x86 processor with no pipelined MAC unit! Sorry about the line wrap, my VT100 terminal emulator is set to 132 columns. -- Freya Vasiliev *PLONK* filter active for trolls. Pentium 90 (OS/2 Warp) - NetBSD 1.0 From tkang@kth.se Mon Oct 16 15:05:41 1995 Path: ashpoly!cascade!transat!ukc!fennimore!kth!tkang From: tkang@kth.se (Takeshi Kang) Newsgroups: comp.dsp Subject: Re: Question: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Oct16.150541.8713@kth.se> Date: Mon, 16 Oct 1995 15:05:41 GMT References: <1995Oct14.070241.7781@demon.co.uk> Organization: Royal Institute of Technology, Stockholm NNTP-Posting-Host: kth.se X-Newsreader: Netscape 1.1N Lines: 11 In article <1995Oct14.070241.7781@demon.co.uk>, mokonkwo@demon.co.uk (Morag Okonkwo) writes: > Porting stardust.c to the NeXTcube and Atari Falcon DSP subsystems. > 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. If you are posting from AOL, please read RFC 1036 before posting again. -- Takeshi Kang -- Royal Institute of Technology, Stockholm "We don't sign stars. We build them." From jmartinez@rwth-aachen.de Wed Oct 18 00:09:41 1995 Path: ashpoly!cascade!transat!sunet!nordrelay!rwth-aachen!jmartinez From: jmartinez@rwth-aachen.de (Joachim Martínez) Newsgroups: comp.dsp Subject: Re: Question: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Oct18.000941.2893@rwth-aachen.de> Date: Wed, 18 Oct 1995 00:09:41 GMT References: <1995Oct14.070241.7781@demon.co.uk> Organization: RWTH Aachen Informatik NNTP-Posting-Host: rwth-aachen.de X-Newsreader: NewsWatcher 2.0b24 Lines: 9 In article <1995Oct14.070241.7781@demon.co.uk>, mokonkwo@demon.co.uk (Morag Okonkwo) writes: > Porting stardust.c to the NeXTcube and Atari Falcon DSP subsystems. Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. -- === Joachim Martínez === Dept of Electrical Engineering, RWTH Aachen Informatik "There are 14 nodes and only 10 countries. Count again." From mstewart@u-tokyo.ac.jp Thu Oct 19 19:49:41 1995 Path: ashpoly!cascade!transat!eunet-de!hansebox!u-tokyo!mstewart From: mstewart@u-tokyo.ac.jp (Mei Stewart) Newsgroups: comp.dsp Subject: Re: Question: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Oct19.194941.9625@u-tokyo.ac.jp> Date: Thu, 19 Oct 1995 19:49:41 GMT References: <1995Oct14.070241.7781@demon.co.uk> 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 <1995Oct14.070241.7781@demon.co.uk>, mokonkwo@demon.co.uk (Morag Okonkwo) writes: > Porting stardust.c to the NeXTcube and Atari Falcon DSP subsystems. > This leaves over 95% of the DSP56001's 16.5 MIPS available for other audio tasks. Real programmers write in C, not arcane DSP microcode. With Pentium chips hitting 100 MHz, dedicated DSPs are obsolete. -- Mei Stewart Tape trading list upon request. SASE required for international mail.