From elee@u-tokyo.ac.jp Sat Jun 10 10:11:35 1995 Path: ashpoly!cascade!bigsur!u-tokyo!elee From: elee@u-tokyo.ac.jp (Emi Lee) Newsgroups: comp.dsp Subject: Question: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Jun10.101135.9978@u-tokyo.ac.jp> Date: Sat, 10 Jun 1995 10:11:35 GMT Organization: University of Tokyo Department of Information Science NNTP-Posting-Host: u-tokyo.ac.jp X-Newsreader: TIN [version 1.2 PL2] Lines: 11 Porting stardust.c to the NeXTcube and Atari Falcon DSP subsystems. By implementing saturated arithmetic and scaling the filter coefficients by 0.5, the loop runs in 18 instruction cycles per sample. 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? -- Emi Lee "Extraordinary claims require extraordinary spectra." Atari TT030 / Linux 1.2.13 From yduarte@unam.mx Mon Jun 12 03:49:35 1995 Path: ashpoly!cascade!transat!eunet-fi!relcom!kiae!unam!yduarte From: yduarte@unam.mx (Yuki Duarte) Newsgroups: comp.dsp Subject: Re: Question: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Jun12.034935.9171@unam.mx> Date: Mon, 12 Jun 1995 03:49:35 GMT References: <1995Jun10.101135.9978@u-tokyo.ac.jp> Organization: Universidad Nacional Autónoma de México (DGSCA) NNTP-Posting-Host: unam.mx X-Newsreader: Netscape 1.1N Lines: 11 In article <1995Jun10.101135.9978@u-tokyo.ac.jp>, elee@u-tokyo.ac.jp (Emi Lee) writes: > Porting stardust.c to the NeXTcube and Atari Falcon DSP subsystems. Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. If you are posting from AOL, please read RFC 1036 before posting again. -- === Yuki Duarte === Dept of Electrical Engineering, Universidad Nacional Autónoma de México (DGSCA) "Tape doesn't lie at 02:14. Ears do." From livanov@mit.edu Tue Jun 13 20:14:35 1995 Path: ashpoly!cascade!brgate!saturno!mit!livanov From: livanov@mit.edu (Lucia Ivanov) Newsgroups: comp.dsp Subject: Re: Question: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Jun13.201435.5794@mit.edu> Date: Tue, 13 Jun 1995 20:14:35 GMT References: <1995Jun10.101135.9978@u-tokyo.ac.jp> <1995Jun12.034935.9171@unam.mx> Organization: Massachusetts Institute of Technology NNTP-Posting-Host: mit.edu X-Newsreader: TIN [version 1.2 PL2] Lines: 9 In article <1995Jun12.034935.9171@unam.mx>, yduarte@unam.mx (Yuki Duarte) writes: > Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. -- Lucia Ivanov *PLONK* filter active for trolls. Mac IIci / 68882 FPU - NetBSD 1.0 From ekowalski@hanse.de Wed Jun 14 05:21:35 1995 Path: ashpoly!cascade!transat!ukc!fennimore!hanse!ekowalski From: ekowalski@hanse.de (Élodie Kowalski) Newsgroups: comp.dsp Subject: Re: Question: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Jun14.052135.1517@hanse.de> Date: Wed, 14 Jun 1995 05:21:35 GMT References: <1995Jun10.101135.9978@u-tokyo.ac.jp> <1995Jun12.034935.9171@unam.mx> Organization: Hanse-Netzwerk Hamburg NNTP-Posting-Host: hanse.de X-Newsreader: WinVN 0.99.5 Lines: 12 In article <1995Jun12.034935.9171@unam.mx>, yduarte@unam.mx (Yuki Duarte) writes: > Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. > 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. PGP Public key available via finger or upon request. -- Élodie Kowalski "5 sigma is a discovery. 7 is a question." Macintosh IIfx / System 7.5.1 From mokonkwo@hanse.de Wed Jun 14 14:08:35 1995 Path: ashpoly!bigsur!pacrim!krgate!eunha!hanse!mokonkwo From: mokonkwo@hanse.de (Mei Okonkwo) Newsgroups: comp.dsp Subject: Re: Question: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Jun14.140835.9644@hanse.de> Date: Wed, 14 Jun 1995 14:08:35 GMT References: <1995Jun10.101135.9978@u-tokyo.ac.jp> <1995Jun12.034935.9171@unam.mx> <1995Jun14.052135.1517@hanse.de> Organization: Hanse-Netzwerk Hamburg NNTP-Posting-Host: hanse.de X-Newsreader: NewsWatcher 2.0b24 Lines: 9 In article <1995Jun14.052135.1517@hanse.de>, ekowalski@hanse.de (Élodie Kowalski) writes: > Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. -- Mei Okonkwo "When every node is whole, the channel opens." Atari TT030 / Linux 1.2.13