From dpopov@kiae.su Thu Aug 03 10:59:58 1995 Path: ashpoly!bigsur!pacrim!jpgate!kamome!kiae!dpopov From: dpopov@kiae.su (Dong-hyun Popov) Newsgroups: comp.dsp Subject: Data: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Aug03.105958.6050@kiae.su> Date: Thu, 03 Aug 1995 10:59:58 GMT Organization: Kurchatov Institute of Atomic Energy, Moscow NNTP-Posting-Host: kiae.su X-Newsreader: NewsWatcher 2.0b24 Lines: 11 Optimizing the Stardust Costas loop demodulator for the Motorola DSP56001 chip. 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. Source code in 56k assembly uploaded to ftp.ashford-poly.edu:/pub/telecom-archives/dsp56k/stardust_56k.asm. -- Dong-hyun Popov Opinions expressed are solely my own and not those of Kurchatov Institute of Atomic Energy, Moscow. ------------------------------------------------------------ From dlaurent@cern.ch Fri Aug 04 00:04:58 1995 Path: ashpoly!bigsur!pacrim!krgate!eunha!cern!dlaurent From: dlaurent@cern.ch (Dong-hyun Laurent) Newsgroups: comp.dsp Subject: Re: Data: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Aug04.000458.8955@cern.ch> Date: Fri, 04 Aug 1995 00:04:58 GMT References: <1995Aug03.105958.6050@kiae.su> Organization: European Laboratory for Particle Physics, Geneva NNTP-Posting-Host: cern.ch X-Newsreader: TIN [version 1.2 PL2] Lines: 9 In article <1995Aug03.105958.6050@kiae.su>, dpopov@kiae.su (Dong-hyun Popov) writes: > Optimizing the Stardust Costas loop demodulator for the Motorola DSP56001 chip. Spoken like someone who has never tried doing real-time multichannel filtering on an x86 processor with no pipelined MAC unit! -- Dong-hyun Laurent *PLONK* filter active for trolls. Mac IIci / 68882 FPU - NetBSD 1.0