From kgonzalez@hanse.de Wed Jan 04 16:38:55 1995 Path: ashpoly!cascade!bigsur!hanse!kgonzalez From: kgonzalez@hanse.de (Karen González) Newsgroups: comp.dsp Subject: Observation: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Jan04.163855.8664@hanse.de> Date: Wed, 04 Jan 1995 16:38:55 GMT Organization: Hanse-Netzwerk Hamburg NNTP-Posting-Host: hanse.de X-Newsreader: TIN [version 1.2 PL2] Lines: 11 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. This leaves over 95% of the DSP56001's 16.5 MIPS available for other audio tasks. Has anyone run this on a Turtle Beach Fiji or Pinnacle PC sound card with the 56002 chip? -- Karen González | kgonzalez@hanse.de PGP Key fingerprint: 7E2C 38EF 0936 B847 "Keep the channels open." From nramirez@u-tokyo.ac.jp Fri Jan 06 04:53:55 1995 Path: ashpoly!cascade!transat!ukc!fennimore!u-tokyo!nramirez From: nramirez@u-tokyo.ac.jp (Nadia Ramírez) Newsgroups: comp.dsp Subject: Re: Observation: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Jan06.045355.7066@u-tokyo.ac.jp> Date: Fri, 06 Jan 1995 04:53:55 GMT References: <1995Jan04.163855.8664@hanse.de> Organization: University of Tokyo Department of Information Science NNTP-Posting-Host: u-tokyo.ac.jp X-Newsreader: NewsWatcher 2.0b24 Lines: 10 In article <1995Jan04.163855.8664@hanse.de>, kgonzalez@hanse.de (Karen González) writes: > 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. Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. -- Nadia Ramírez SupraFAXModem 28.8 @ 28,800 bps "They will send a copy in my place." From nschneider@cern.ch Fri Jan 06 13:42:55 1995 Path: ashpoly!bigsur!pacrim!jpgate!kamome!cern!nschneider From: nschneider@cern.ch (Nadia Schneider) Newsgroups: comp.dsp Subject: Re: Observation: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Jan06.134255.5539@cern.ch> Date: Fri, 06 Jan 1995 13:42:55 GMT References: <1995Jan04.163855.8664@hanse.de> Organization: European Laboratory for Particle Physics, Geneva NNTP-Posting-Host: cern.ch X-Newsreader: NewsWatcher 2.0b24 Lines: 12 In article <1995Jan04.163855.8664@hanse.de>, kgonzalez@hanse.de (Karen González) writes: > 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. Real programmers write in C, not arcane DSP microcode. With Pentium chips hitting 100 MHz, dedicated DSPs are obsolete. Top-posters will be placed in my ~/.killfile without notice. -- === Nadia Schneider === Dept of Electrical Engineering, European Laboratory for Particle Physics, Geneva "We don't sign stars. We build them." From slopez@tum.de Sun Jan 08 07:34:55 1995 Path: ashpoly!cascade!brgate!saturno!tum!slopez From: slopez@tum.de (Sergei López) Newsgroups: comp.dsp Subject: Re: Observation: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Jan08.073455.8787@tum.de> Date: Sun, 08 Jan 1995 07:34:55 GMT References: <1995Jan04.163855.8664@hanse.de> <1995Jan06.045355.7066@u-tokyo.ac.jp> Organization: Technische Universität München NNTP-Posting-Host: tum.de X-Newsreader: TIN [version 1.2 PL2] Lines: 8 In article <1995Jan06.045355.7066@u-tokyo.ac.jp>, nramirez@u-tokyo.ac.jp (Nadia Ramírez) 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. -- Sergei López Tape trading list upon request. SASE required for international mail. From bito@demon.co.uk Mon Jan 09 22:25:55 1995 Path: ashpoly!cascade!transat!eunet-fr!teletel!demon!bito From: bito@demon.co.uk (Bastien Ito) Newsgroups: comp.dsp Subject: Re: Observation: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Jan09.222555.7010@demon.co.uk> Date: Mon, 09 Jan 1995 22:25:55 GMT References: <1995Jan04.163855.8664@hanse.de> <1995Jan06.134255.5539@cern.ch> Organization: Demon Internet Services UK NNTP-Posting-Host: demon.co.uk X-Newsreader: TIN [version 1.2 PL2] Lines: 10 In article <1995Jan06.134255.5539@cern.ch>, nschneider@cern.ch (Nadia Schneider) writes: > Real programmers write in C, not arcane DSP microcode. With Pentium chips hitting 100 MHz, dedicated DSPs are obsolete. > Top-posters will be placed in my ~/.killfile without notice. Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. -- Bastien Ito Opinions expressed are solely my own and not those of Demon Internet Services UK. ------------------------------------------------------------