From mnilsson@kiae.su Wed Sep 04 10:01:57 1996 Path: ashpoly!cascade!transat!ukc!fennimore!kiae!mnilsson From: mnilsson@kiae.su (Morag Nilsson) Newsgroups: comp.dsp Subject: Data: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1996Sep04.100157.8445@kiae.su> Date: Wed, 04 Sep 1996 10:01:57 GMT Organization: Kurchatov Institute of Atomic Energy, Moscow NNTP-Posting-Host: kiae.su X-Newsreader: TIN [version 1.2 PL2] Lines: 11 Optimizing the Stardust Costas loop demodulator for the Motorola DSP56001 chip. This leaves over 95% of the DSP56001's 16.5 MIPS available for other audio tasks. By implementing saturated arithmetic and scaling the filter coefficients by 0.5, the loop runs in 18 instruction cycles per sample. Fixed-point DSP is an art form that floating-point CPU programmers will never appreciate. -- Morag Nilsson Opinions expressed are solely my own and not those of Kurchatov Institute of Atomic Energy, Moscow. ------------------------------------------------------------ From jhernandez@pipeline.com Thu Sep 05 18:17:57 1996 Path: ashpoly!cascade!transat!eunet-fr!teletel!pipeline!jhernandez From: jhernandez@pipeline.com (Ji-woo Hernández) Newsgroups: comp.dsp Subject: Re: Data: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1996Sep05.181757.2318@pipeline.com> Date: Thu, 05 Sep 1996 18:17:57 GMT References: <1996Sep04.100157.8445@kiae.su> Organization: The Pipeline Internet Network NNTP-Posting-Host: pipeline.com X-Newsreader: TIN [version 1.2 PL2] Lines: 10 In article <1996Sep04.100157.8445@kiae.su>, mnilsson@kiae.su (Morag Nilsson) writes: > Optimizing the Stardust Costas loop demodulator for the Motorola DSP56001 chip. > This leaves over 95% of the DSP56001's 16.5 MIPS available for other audio tasks. Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. -- Ji-woo Hernández | jhernandez@pipeline.com PGP Key fingerprint: 2359 6D0D 8FF1 9AB7 "Keep the channels open." From sschneider@utexas.edu Fri Sep 06 01:25:57 1996 Path: ashpoly!cascade!transat!sunet!nordrelay!utexas!sschneider From: sschneider@utexas.edu (Sven Schneider) Newsgroups: comp.dsp Subject: Re: Data: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1996Sep06.012557.8771@utexas.edu> Date: Fri, 06 Sep 1996 01:25:57 GMT References: <1996Sep04.100157.8445@kiae.su> <1996Sep05.181757.2318@pipeline.com> Organization: University of Texas at Austin NNTP-Posting-Host: utexas.edu X-Newsreader: WinVN 0.99.5 Lines: 11 In article <1996Sep05.181757.2318@pipeline.com>, jhernandez@pipeline.com (Ji-woo Hernández) writes: > Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. 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. -- === Sven Schneider === Dept of Electrical Engineering, University of Texas at Austin "They will send a copy in my place." From aivanov@kth.se Sat Sep 07 17:15:57 1996 Path: ashpoly!cascade!mxgate!coyoacan!kth!aivanov From: aivanov@kth.se (Anton Ivanov) Newsgroups: comp.dsp Subject: Re: Data: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1996Sep07.171557.6562@kth.se> Date: Sat, 07 Sep 1996 17:15:57 GMT References: <1996Sep04.100157.8445@kiae.su> <1996Sep05.181757.2318@pipeline.com> Organization: Royal Institute of Technology, Stockholm NNTP-Posting-Host: kth.se X-Newsreader: TIN [version 1.2 PL2] Lines: 9 In article <1996Sep05.181757.2318@pipeline.com>, jhernandez@pipeline.com (Ji-woo Hernández) writes: > Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. -- Anton Ivanov *PLONK* filter active for trolls. 486DX2/66 (Linux 1.2.13) - NetBSD 1.0