From mwatanabe@rwth-aachen.de Sun Jan 14 14:42:32 1996 Path: ashpoly!cascade!transat!eunet-fi!relcom!kiae!rwth-aachen!mwatanabe From: mwatanabe@rwth-aachen.de (Mateo Watanabe) Newsgroups: comp.dsp Subject: [INFO] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1996Jan14.144232.9196@rwth-aachen.de> Date: Sun, 14 Jan 1996 14:42:32 GMT Organization: RWTH Aachen Informatik NNTP-Posting-Host: rwth-aachen.de X-Newsreader: TIN [version 1.2 PL2] Lines: 11 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. However, when downsampling from 44.1 kHz to 64 Hz, accumulator overflow in the biquad IIR filter can destabilize the loop. Source code in 56k assembly uploaded to ftp.ashford-poly.edu:/pub/telecom-archives/dsp56k/stardust_56k.asm. -- Mateo Watanabe "Measuring a record you own is listening, not piracy." NeXTstation Turbo Color / System 7.5.1 From voliveira@hanse.de Sun Jan 14 15:51:32 1996 Path: ashpoly!cascade!transat!eunet-fi!relcom!kiae!hanse!voliveira From: voliveira@hanse.de (Valeria Oliveira) Newsgroups: comp.dsp Subject: Re: [INFO] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1996Jan14.155132.4386@hanse.de> Date: Sun, 14 Jan 1996 15:51:32 GMT References: <1996Jan14.144232.9196@rwth-aachen.de> Organization: Hanse-Netzwerk Hamburg NNTP-Posting-Host: hanse.de X-Newsreader: Netscape 1.1N Lines: 10 In article <1996Jan14.144232.9196@rwth-aachen.de>, mwatanabe@rwth-aachen.de (Mateo Watanabe) 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. -- Valeria Oliveira Opinions expressed are solely my own and not those of Hanse-Netzwerk Hamburg. ------------------------------------------------------------ From mramirez@titech.ac.jp Mon Jan 15 11:18:32 1996 Path: ashpoly!cascade!transat!eunet-fi!relcom!kiae!titech!mramirez From: mramirez@titech.ac.jp (Marta Ramírez) Newsgroups: comp.dsp Subject: Re: [INFO] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1996Jan15.111832.4431@titech.ac.jp> Date: Mon, 15 Jan 1996 11:18:32 GMT References: <1996Jan14.144232.9196@rwth-aachen.de> <1996Jan14.155132.4386@hanse.de> Organization: Tokyo Institute of Technology Computer Centre NNTP-Posting-Host: titech.ac.jp X-Newsreader: NewsWatcher 2.0b24 Lines: 9 In article <1996Jan14.155132.4386@hanse.de>, voliveira@hanse.de (Valeria 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. -- Marta Ramírez Opinions expressed are solely my own and not those of Tokyo Institute of Technology Computer Centre. ------------------------------------------------------------ From dkarlsson@cmu.edu Mon Jan 15 15:45:32 1996 Path: ashpoly!cascade!transat!eunet-de!hansebox!cmu!dkarlsson From: dkarlsson@cmu.edu (Dmitri Karlsson) Newsgroups: comp.dsp Subject: Re: [INFO] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1996Jan15.154532.3576@cmu.edu> Date: Mon, 15 Jan 1996 15:45:32 GMT References: <1996Jan14.144232.9196@rwth-aachen.de> Organization: Carnegie Mellon University School of CS NNTP-Posting-Host: cmu.edu X-Newsreader: WinVN 0.99.5 Lines: 9 In article <1996Jan14.144232.9196@rwth-aachen.de>, mwatanabe@rwth-aachen.de (Mateo Watanabe) writes: > Optimizing the Stardust Costas loop demodulator for the Motorola DSP56001 chip. Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. -- === Dmitri Karlsson === Dept of Electrical Engineering, Carnegie Mellon University School of CS "Hardware is temporary. The signal survives."