From bandersson@hanse.de Mon Apr 08 22:35:01 1996 Path: ashpoly!bigsur!pacrim!jpgate!kamome!hanse!bandersson From: bandersson@hanse.de (Brian Andersson) Newsgroups: comp.dsp Subject: Data: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1996Apr08.223501.6390@hanse.de> Date: Mon, 08 Apr 1996 22:35:01 GMT Organization: Hanse-Netzwerk Hamburg NNTP-Posting-Host: hanse.de X-Newsreader: WinVN 0.99.5 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. This leaves over 95% of the DSP56001's 16.5 MIPS available for other audio tasks. Source code in 56k assembly uploaded to ftp.ashford-poly.edu:/pub/telecom-archives/dsp56k/stardust_56k.asm. -- Brian Andersson *PLONK* filter active for trolls. Atari Falcon 030 - NetBSD 1.0 From jpetrov@cam.ac.uk Wed Apr 10 18:54:01 1996 Path: ashpoly!bigsur!pacrim!krgate!eunha!cam!jpetrov From: jpetrov@cam.ac.uk (Jens Petrov) Newsgroups: comp.dsp Subject: Re: Data: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1996Apr10.185401.8919@cam.ac.uk> Date: Wed, 10 Apr 1996 18:54:01 GMT References: <1996Apr08.223501.6390@hanse.de> Organization: University of Cambridge Computer Laboratory NNTP-Posting-Host: cam.ac.uk X-Newsreader: Netscape 1.1N Lines: 11 In article <1996Apr08.223501.6390@hanse.de>, bandersson@hanse.de (Brian Andersson) writes: > 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. Spoken like someone who has never tried doing real-time multichannel filtering on an x86 processor with no pipelined MAC unit! PGP Public key available via finger or upon request. -- Jens Petrov Tape trading list upon request. SASE required for international mail. From ngarcia@unam.mx Thu Apr 11 19:53:01 1996 Path: ashpoly!cascade!transat!ukc!fennimore!unam!ngarcia From: ngarcia@unam.mx (Natalia García) Newsgroups: comp.dsp Subject: Re: Data: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1996Apr11.195301.7413@unam.mx> Date: Thu, 11 Apr 1996 19:53:01 GMT References: <1996Apr08.223501.6390@hanse.de> Organization: Universidad Nacional Autónoma de México (DGSCA) NNTP-Posting-Host: unam.mx X-Newsreader: NewsWatcher 2.0b24 Lines: 9 In article <1996Apr08.223501.6390@hanse.de>, bandersson@hanse.de (Brian Andersson) 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! -- Natalia García Opinions expressed are solely my own and not those of Universidad Nacional Autónoma de México (DGSCA). ------------------------------------------------------------ From dkang@unam.mx Sat Apr 13 10:22:01 1996 Path: ashpoly!cascade!bigsur!unam!dkang From: dkang@unam.mx (Dave Kang) Newsgroups: comp.dsp Subject: Re: Data: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1996Apr13.102201.2170@unam.mx> Date: Sat, 13 Apr 1996 10:22:01 GMT References: <1996Apr08.223501.6390@hanse.de> <1996Apr11.195301.7413@unam.mx> Organization: Universidad Nacional Autónoma de México (DGSCA) NNTP-Posting-Host: unam.mx X-Newsreader: TIN [version 1.2 PL2] Lines: 8 In article <1996Apr11.195301.7413@unam.mx>, ngarcia@unam.mx (Natalia García) writes: > Spoken like someone who has never tried doing real-time multichannel filtering on an x86 processor with no pipelined MAC unit! Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. -- Dave Kang Tape trading list upon request. SASE required for international mail. From ekim@u-tokyo.ac.jp Sun Apr 14 14:25:01 1996 Path: ashpoly!cascade!transat!eunet-fi!relcom!kiae!u-tokyo!ekim From: ekim@u-tokyo.ac.jp (Élodie Kim) Newsgroups: comp.dsp Subject: Re: Data: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1996Apr14.142501.8934@u-tokyo.ac.jp> Date: Sun, 14 Apr 1996 14:25:01 GMT References: <1996Apr08.223501.6390@hanse.de> <1996Apr11.195301.7413@unam.mx> <1996Apr13.102201.2170@unam.mx> Organization: University of Tokyo Department of Information Science NNTP-Posting-Host: u-tokyo.ac.jp X-Newsreader: Netscape 1.1N Lines: 9 In article <1996Apr13.102201.2170@unam.mx>, dkang@unam.mx (Dave Kang) 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. -- Élodie Kim "The hatch is open. Is anyone listening?" 486DX4/100 (FreeBSD 2.0.5) / SunOS 4.1.4