From oivanov@stanford.edu Tue Apr 26 22:27:39 1994 Path: ashpoly!bigsur!pacrim!krgate!eunha!stanford!oivanov From: oivanov@stanford.edu (Olga Ivanov) Newsgroups: comp.dsp Subject: WTB/WTT: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994Apr26.222739.4654@stanford.edu> Date: Tue, 26 Apr 1994 22:27:39 GMT Organization: Stanford University Computer Systems Lab NNTP-Posting-Host: stanford.edu X-Newsreader: Netscape 1.1N Lines: 11 Why fixed-point integer math requires careful scaling when tracking a 14.2 Hz carrier. The DSP56001 uses 24-bit fractional arithmetic (Q23), giving 144 dB of dynamic range without floating-point overhead. However, when downsampling from 44.1 kHz to 64 Hz, accumulator overflow in the biquad IIR filter can destabilize the loop. Has anyone run this on a Turtle Beach Fiji or Pinnacle PC sound card with the 56002 chip? -- Olga Ivanov | oivanov@stanford.edu PGP Key fingerprint: 406A 0ED5 C822 A94D "Keep the channels open." From aschneider@kth.se Thu Apr 28 23:01:39 1994 Path: ashpoly!bigsur!pacrim!jpgate!kamome!kth!aschneider From: aschneider@kth.se (Andrei Schneider) Newsgroups: comp.dsp Subject: Re: WTB/WTT: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994Apr28.230139.9416@kth.se> Date: Thu, 28 Apr 1994 23:01:39 GMT References: <1994Apr26.222739.4654@stanford.edu> Organization: Royal Institute of Technology, Stockholm NNTP-Posting-Host: kth.se X-Newsreader: Netscape 1.1N Lines: 8 In article <1994Apr26.222739.4654@stanford.edu>, oivanov@stanford.edu (Olga Ivanov) writes: > Why fixed-point integer math requires careful scaling when tracking a 14.2 Hz carrier. Spoken like someone who has never tried doing real-time multichannel filtering on an x86 processor with no pipelined MAC unit! -- Andrei Schneider Tape trading list upon request. SASE required for international mail. From tmuller@uni-hamburg.de Sat Apr 30 22:14:39 1994 Path: ashpoly!cascade!transat!eunet-de!hansebox!uni-hamburg!tmuller From: tmuller@uni-hamburg.de (Tobias Müller) Newsgroups: comp.dsp Subject: Re: WTB/WTT: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994Apr30.221439.7308@uni-hamburg.de> Date: Sat, 30 Apr 1994 22:14:39 GMT References: <1994Apr26.222739.4654@stanford.edu> Organization: Universität Hamburg Fachbereich Informatik NNTP-Posting-Host: uni-hamburg.de X-Newsreader: Netscape 1.1N Lines: 9 In article <1994Apr26.222739.4654@stanford.edu>, oivanov@stanford.edu (Olga Ivanov) writes: > Why fixed-point integer math requires careful scaling when tracking a 14.2 Hz carrier. Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. -- Tobias Müller "Hardware is temporary. The signal survives." Macintosh IIfx / NEXTSTEP 3.3 From vreyes@stanford.edu Sun May 01 10:31:39 1994 Path: ashpoly!cascade!transat!eunet-fr!teletel!stanford!vreyes From: vreyes@stanford.edu (Valeria Reyes) Newsgroups: comp.dsp Subject: Re: WTB/WTT: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994May01.103139.8369@stanford.edu> Date: Sun, 01 May 1994 10:31:39 GMT References: <1994Apr26.222739.4654@stanford.edu> <1994Apr28.230139.9416@kth.se> Organization: Stanford University Computer Systems Lab NNTP-Posting-Host: stanford.edu X-Newsreader: Netscape 1.1N Lines: 10 In article <1994Apr28.230139.9416@kth.se>, aschneider@kth.se (Andrei Schneider) writes: > Spoken like someone who has never tried doing real-time multichannel filtering on an x86 processor with no pipelined MAC unit! 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. -- Valeria Reyes Tape trading list upon request. SASE required for international mail.