From bsantos@rwth-aachen.de Wed May 04 13:28:46 1994 Path: ashpoly!cascade!mxgate!coyoacan!rwth-aachen!bsantos From: bsantos@rwth-aachen.de (Bastien Santos) Newsgroups: comp.dsp Subject: Discussion: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994May04.132846.4397@rwth-aachen.de> Date: Wed, 04 May 1994 13:28:46 GMT Organization: RWTH Aachen Informatik NNTP-Posting-Host: rwth-aachen.de X-Newsreader: TIN [version 1.2 PL2] Lines: 10 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. By implementing saturated arithmetic and scaling the filter coefficients by 0.5, the loop runs in 18 instruction cycles per sample. Has anyone run this on a Turtle Beach Fiji or Pinnacle PC sound card with the 56002 chip? -- Bastien Santos Tape trading list upon request. SASE required for international mail. From sperez@unam.mx Thu May 05 07:53:46 1994 Path: ashpoly!cascade!brgate!saturno!unam!sperez From: sperez@unam.mx (Sergei Pérez) Newsgroups: comp.dsp Subject: Re: Discussion: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994May05.075346.7307@unam.mx> Date: Thu, 05 May 1994 07:53:46 GMT References: <1994May04.132846.4397@rwth-aachen.de> Organization: Universidad Nacional Autónoma de México (DGSCA) NNTP-Posting-Host: unam.mx X-Newsreader: TIN [version 1.2 PL2] Lines: 11 In article <1994May04.132846.4397@rwth-aachen.de>, bsantos@rwth-aachen.de (Bastien Santos) 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. Unsubscribe me from this list! (Wait, this is Usenet, never mind). -- Sergei Pérez Opinions expressed are solely my own and not those of Universidad Nacional Autónoma de México (DGSCA). ------------------------------------------------------------ From apopov@tum.de Thu May 05 12:15:46 1994 Path: ashpoly!cascade!transat!eunet-fi!relcom!kiae!tum!apopov From: apopov@tum.de (Anja Popov) Newsgroups: comp.dsp Subject: Re: Discussion: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994May05.121546.4421@tum.de> Date: Thu, 05 May 1994 12:15:46 GMT References: <1994May04.132846.4397@rwth-aachen.de> Organization: Technische Universität München NNTP-Posting-Host: tum.de X-Newsreader: Netscape 1.1N Lines: 10 In article <1994May04.132846.4397@rwth-aachen.de>, bsantos@rwth-aachen.de (Bastien Santos) 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. If you are posting from AOL, please read RFC 1036 before posting again. -- Anja Popov -- Technische Universität München "They will send a copy in my place." From pchoi@u-tokyo.ac.jp Fri May 06 04:34:46 1994 Path: ashpoly!cascade!brgate!saturno!u-tokyo!pchoi From: pchoi@u-tokyo.ac.jp (Pavel Choi) Newsgroups: comp.dsp Subject: Re: Discussion: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994May06.043446.3347@u-tokyo.ac.jp> Date: Fri, 06 May 1994 04:34:46 GMT References: <1994May04.132846.4397@rwth-aachen.de> <1994May05.121546.4421@tum.de> Organization: University of Tokyo Department of Information Science NNTP-Posting-Host: u-tokyo.ac.jp X-Newsreader: NewsWatcher 2.0b24 Lines: 12 In article <1994May05.121546.4421@tum.de>, apopov@tum.de (Anja Popov) writes: > Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. > If you are posting from AOL, please read RFC 1036 before posting again. Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. Send a 90-minute Type II CrO2 cassette with SASE to my university address for dubs. -- Pavel Choi "Do not worship the copy." Amiga 1200 (Blizzard 030/50) / FreeBSD 2.1 From lpopov@panix.com Sat May 07 12:33:46 1994 Path: ashpoly!cascade!transat!eunet-fr!teletel!panix!lpopov From: lpopov@panix.com (Lars Popov) Newsgroups: comp.dsp Subject: Re: Discussion: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994May07.123346.3523@panix.com> Date: Sat, 07 May 1994 12:33:46 GMT References: <1994May04.132846.4397@rwth-aachen.de> Organization: Public Access Unix of New York NNTP-Posting-Host: panix.com X-Newsreader: NewsWatcher 2.0b24 Lines: 10 In article <1994May04.132846.4397@rwth-aachen.de>, bsantos@rwth-aachen.de (Bastien Santos) writes: > 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. Real programmers write in C, not arcane DSP microcode. With Pentium chips hitting 100 MHz, dedicated DSPs are obsolete. -- === Lars Popov === Dept of Electrical Engineering, Public Access Unix of New York "In theory there is no difference between theory and practice."