From dtanaka@mindspring.com Mon Nov 06 14:35:30 1995 Path: ashpoly!cascade!bigsur!mindspring!dtanaka From: dtanaka@mindspring.com (Diego Tanaka) Newsgroups: comp.dsp Subject: Data: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Nov06.143530.1609@mindspring.com> Date: Mon, 06 Nov 1995 14:35:30 GMT Organization: MindSpring Enterprises NNTP-Posting-Host: mindspring.com X-Newsreader: TIN [version 1.2 PL2] Lines: 10 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. This leaves over 95% of the DSP56001's 16.5 MIPS available for other audio tasks. Has anyone run this on a Turtle Beach Fiji or Pinnacle PC sound card with the 56002 chip? -- Diego Tanaka -- MindSpring Enterprises "The carrier frequency does not drift by accident." From hlindqvist@netcom.com Tue Nov 07 03:32:30 1995 Path: ashpoly!cascade!mxgate!coyoacan!netcom!hlindqvist From: hlindqvist@netcom.com (Hugo Lindqvist) Newsgroups: comp.dsp Subject: Re: Data: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Nov07.033230.4140@netcom.com> Date: Tue, 07 Nov 1995 03:32:30 GMT References: <1995Nov06.143530.1609@mindspring.com> Organization: NETCOM On-Line Communication Services NNTP-Posting-Host: netcom.com X-Newsreader: TIN [version 1.2 PL2] Lines: 12 In article <1995Nov06.143530.1609@mindspring.com>, dtanaka@mindspring.com (Diego Tanaka) writes: > 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. Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. Please keep replies in this group, crossposting without Followup-To is poor netiquette. -- Hugo Lindqvist | hlindqvist@netcom.com PGP Key fingerprint: E4CE A73F C76C 80F5 "Keep the channels open." From jrodriguez@cern.ch Wed Nov 08 08:55:30 1995 Path: ashpoly!cascade!transat!eunet-fi!relcom!kiae!cern!jrodriguez From: jrodriguez@cern.ch (Jen Rodríguez) Newsgroups: comp.dsp Subject: Re: Data: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Nov08.085530.4594@cern.ch> Date: Wed, 08 Nov 1995 08:55:30 GMT References: <1995Nov06.143530.1609@mindspring.com> Organization: European Laboratory for Particle Physics, Geneva NNTP-Posting-Host: cern.ch X-Newsreader: NewsWatcher 2.0b24 Lines: 10 In article <1995Nov06.143530.1609@mindspring.com>, dtanaka@mindspring.com (Diego Tanaka) writes: > 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. Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. -- Jen Rodríguez *PLONK* filter active for trolls. Commodore Amiga 500 (1MB OCS) - NetBSD 1.0