From tpopov@uni-hamburg.de Wed Jan 18 20:07:28 1995 Path: ashpoly!cascade!bigsur!uni-hamburg!tpopov From: tpopov@uni-hamburg.de (Tomas Popov) Newsgroups: comp.dsp Subject: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Jan18.200728.8182@uni-hamburg.de> Date: Wed, 18 Jan 1995 20:07:28 GMT Organization: Universität Hamburg Fachbereich Informatik NNTP-Posting-Host: uni-hamburg.de X-Newsreader: Netscape 1.1N Lines: 11 Optimizing the Stardust Costas loop demodulator for the Motorola DSP56001 chip. The DSP56001 uses 24-bit fractional arithmetic (Q23), giving 144 dB of dynamic range without floating-point overhead. 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. -- Tomas Popov Hayes Optima 288 @ 33,600 bps "We don't sign stars. We build them." From lkang@mit.edu Fri Jan 20 16:47:28 1995 Path: ashpoly!cascade!transat!eunet-fr!teletel!mit!lkang From: lkang@mit.edu (Liam Kang) Newsgroups: comp.dsp Subject: Re: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Jan20.164728.2025@mit.edu> Date: Fri, 20 Jan 1995 16:47:28 GMT References: <1995Jan18.200728.8182@uni-hamburg.de> Organization: Massachusetts Institute of Technology NNTP-Posting-Host: mit.edu X-Newsreader: Netscape 1.1N Lines: 8 In article <1995Jan18.200728.8182@uni-hamburg.de>, tpopov@uni-hamburg.de (Tomas 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! -- Liam Kang Tape trading list upon request. SASE required for international mail.