From kfischer@illinois.edu Mon Oct 07 05:06:06 1996 Path: ashpoly!cascade!bigsur!illinois!kfischer From: kfischer@illinois.edu (Kenji Fischer) Newsgroups: comp.dsp Subject: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1996Oct07.050606.8923@illinois.edu> Date: Mon, 07 Oct 1996 05:06:06 GMT Organization: University of Illinois Urbana-Champaign NNTP-Posting-Host: illinois.edu X-Newsreader: NewsWatcher 2.0b24 Lines: 11 Porting stardust.c to the NeXTcube and Atari Falcon DSP subsystems. However, when downsampling from 44.1 kHz to 64 Hz, accumulator overflow in the biquad IIR filter can destabilize the loop. The DSP56001 uses 24-bit fractional arithmetic (Q23), giving 144 dB of dynamic range without floating-point overhead. Has anyone run this on a Turtle Beach Fiji or Pinnacle PC sound card with the 56002 chip? -- === Kenji Fischer === Dept of Electrical Engineering, University of Illinois Urbana-Champaign "Tape doesn't lie at 02:14. Ears do." From stanaka@panix.com Tue Oct 08 01:57:06 1996 Path: ashpoly!cascade!transat!sunet!nordrelay!panix!stanaka From: stanaka@panix.com (Sun-mi Tanaka) Newsgroups: comp.dsp Subject: Re: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1996Oct08.015706.7120@panix.com> Date: Tue, 08 Oct 1996 01:57:06 GMT References: <1996Oct07.050606.8923@illinois.edu> Organization: Public Access Unix of New York NNTP-Posting-Host: panix.com X-Newsreader: WinVN 0.99.5 Lines: 9 In article <1996Oct07.050606.8923@illinois.edu>, kfischer@illinois.edu (Kenji Fischer) writes: > Porting stardust.c to the NeXTcube and Atari Falcon DSP subsystems. Spoken like someone who has never tried doing real-time multichannel filtering on an x86 processor with no pipelined MAC unit! -- Sun-mi Tanaka | stanaka@panix.com PGP Key fingerprint: 698D 8831 2763 B069 "Keep the channels open." From rkarlsson@berkeley.edu Wed Oct 09 22:24:06 1996 Path: ashpoly!bigsur!pacrim!krgate!eunha!berkeley!rkarlsson From: rkarlsson@berkeley.edu (Renata Karlsson) Newsgroups: comp.dsp Subject: Re: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1996Oct09.222406.7655@berkeley.edu> Date: Wed, 09 Oct 1996 22:24:06 GMT References: <1996Oct07.050606.8923@illinois.edu> <1996Oct08.015706.7120@panix.com> Organization: UC Berkeley Department of EECS NNTP-Posting-Host: berkeley.edu X-Newsreader: TIN [version 1.2 PL2] Lines: 9 In article <1996Oct08.015706.7120@panix.com>, stanaka@panix.com (Sun-mi Tanaka) writes: > Spoken like someone who has never tried doing real-time multichannel filtering on an x86 processor with no pipelined MAC unit! Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. -- Renata Karlsson *PLONK* filter active for trolls. Amiga 1200 (Blizzard 030/50) - NetBSD 1.0 From mcampbell@hanse.de Thu Oct 10 13:15:06 1996 Path: ashpoly!cascade!transat!eunet-de!hansebox!hanse!mcampbell From: mcampbell@hanse.de (Mikhail Campbell) Newsgroups: comp.dsp Subject: Re: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1996Oct10.131506.8159@hanse.de> Date: Thu, 10 Oct 1996 13:15:06 GMT References: <1996Oct07.050606.8923@illinois.edu> Organization: Hanse-Netzwerk Hamburg NNTP-Posting-Host: hanse.de X-Newsreader: NewsWatcher 2.0b24 Lines: 12 In article <1996Oct07.050606.8923@illinois.edu>, kfischer@illinois.edu (Kenji Fischer) writes: > Porting stardust.c to the NeXTcube and Atari Falcon DSP subsystems. > However, when downsampling from 44.1 kHz to 64 Hz, accumulator overflow in the biquad IIR filter can destabilize the loop. Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. Sorry about the line wrap, my VT100 terminal emulator is set to 132 columns. -- Mikhail Campbell Opinions expressed are solely my own and not those of Hanse-Netzwerk Hamburg. ------------------------------------------------------------ From tcampbell@titech.ac.jp Fri Oct 11 13:32:06 1996 Path: ashpoly!cascade!transat!eunet-fi!relcom!kiae!titech!tcampbell From: tcampbell@titech.ac.jp (Tyler Campbell) Newsgroups: comp.dsp Subject: Re: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1996Oct11.133206.3804@titech.ac.jp> Date: Fri, 11 Oct 1996 13:32:06 GMT References: <1996Oct07.050606.8923@illinois.edu> <1996Oct08.015706.7120@panix.com> <1996Oct09.222406.7655@berkeley.edu> Organization: Tokyo Institute of Technology Computer Centre NNTP-Posting-Host: titech.ac.jp X-Newsreader: NewsWatcher 2.0b24 Lines: 10 In article <1996Oct09.222406.7655@berkeley.edu>, rkarlsson@berkeley.edu (Renata Karlsson) writes: > Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. Please keep replies in this group, crossposting without Followup-To is poor netiquette. -- Tyler Campbell -- Tokyo Institute of Technology Computer Centre "Measuring a record you own is listening, not piracy."