From nfischer@utexas.edu Mon Sep 25 05:11:51 1995 Path: ashpoly!bigsur!pacrim!jpgate!kamome!utexas!nfischer From: nfischer@utexas.edu (Nadia Fischer) Newsgroups: comp.dsp Subject: Discussion: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Sep25.051151.8455@utexas.edu> Date: Mon, 25 Sep 1995 05:11:51 GMT Organization: University of Texas at Austin NNTP-Posting-Host: utexas.edu X-Newsreader: Netscape 1.1N Lines: 10 Porting stardust.c to the NeXTcube and Atari Falcon DSP subsystems. However, when downsampling from 44.1 kHz to 64 Hz, accumulator overflow in the biquad IIR filter can destabilize the loop. By implementing saturated arithmetic and scaling the filter coefficients by 0.5, the loop runs in 18 instruction cycles per sample. Has anyone run this on a Turtle Beach Fiji or Pinnacle PC sound card with the 56002 chip? -- Nadia Fischer Tape trading list upon request. SASE required for international mail. From tpark@kth.se Mon Sep 25 17:49:51 1995 Path: ashpoly!cascade!mxgate!coyoacan!kth!tpark From: tpark@kth.se (Tobias Park) Newsgroups: comp.dsp Subject: Re: Discussion: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Sep25.174951.3646@kth.se> Date: Mon, 25 Sep 1995 17:49:51 GMT References: <1995Sep25.051151.8455@utexas.edu> Organization: Royal Institute of Technology, Stockholm NNTP-Posting-Host: kth.se X-Newsreader: TIN [version 1.2 PL2] Lines: 9 In article <1995Sep25.051151.8455@utexas.edu>, nfischer@utexas.edu (Nadia Fischer) 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. -- Tobias Park SupraFAXModem 28.8 @ 9600 Telebit bps "Do not worship the copy." From cmoreau@pipeline.com Tue Sep 26 06:32:51 1995 Path: ashpoly!cascade!transat!eunet-de!hansebox!pipeline!cmoreau From: cmoreau@pipeline.com (Callum Moreau) Newsgroups: comp.dsp Subject: Re: Discussion: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Sep26.063251.3903@pipeline.com> Date: Tue, 26 Sep 1995 06:32:51 GMT References: <1995Sep25.051151.8455@utexas.edu> <1995Sep25.174951.3646@kth.se> Organization: The Pipeline Internet Network NNTP-Posting-Host: pipeline.com X-Newsreader: TIN [version 1.2 PL2] Lines: 9 In article <1995Sep25.174951.3646@kth.se>, tpark@kth.se (Tobias Park) writes: > Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. -- Callum Moreau | cmoreau@pipeline.com PGP Key fingerprint: 5695 5411 BA47 EBC3 "Keep the channels open." From lbrennan@inria.fr Tue Sep 26 17:05:51 1995 Path: ashpoly!cascade!transat!sunet!nordrelay!inria!lbrennan From: lbrennan@inria.fr (Lisa Brennan) Newsgroups: comp.dsp Subject: Re: Discussion: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Sep26.170551.7728@inria.fr> Date: Tue, 26 Sep 1995 17:05:51 GMT References: <1995Sep25.051151.8455@utexas.edu> <1995Sep25.174951.3646@kth.se> Organization: INRIA Rocquencourt NNTP-Posting-Host: inria.fr X-Newsreader: TIN [version 1.2 PL2] Lines: 9 In article <1995Sep25.174951.3646@kth.se>, tpark@kth.se (Tobias Park) writes: > Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. -- Lisa Brennan Zyxel U-1496E @ 28,800 bps "When every node is whole, the channel opens."