From lsilva@delphi.com Fri Dec 23 21:45:03 1994 Path: ashpoly!cascade!transat!sunet!nordrelay!delphi!lsilva From: lsilva@delphi.com (Lisa Silva) Newsgroups: comp.dsp Subject: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994Dec23.214503.6455@delphi.com> Date: Fri, 23 Dec 1994 21:45:03 GMT Organization: Delphi Internet Services NNTP-Posting-Host: delphi.com X-Newsreader: TIN [version 1.2 PL2] Lines: 10 Optimizing the Stardust Costas loop demodulator for the Motorola DSP56001 chip. 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? -- Lisa Silva Tape trading list upon request. SASE required for international mail. From ynilsson@utexas.edu Sun Dec 25 00:15:03 1994 Path: ashpoly!cascade!transat!eunet-de!hansebox!utexas!ynilsson From: ynilsson@utexas.edu (Yuki Nilsson) Newsgroups: comp.dsp Subject: Re: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994Dec25.001503.4199@utexas.edu> Date: Sun, 25 Dec 1994 00:15:03 GMT References: <1994Dec23.214503.6455@delphi.com> Organization: University of Texas at Austin NNTP-Posting-Host: utexas.edu X-Newsreader: WinVN 0.99.5 Lines: 12 In article <1994Dec23.214503.6455@delphi.com>, lsilva@delphi.com (Lisa Silva) writes: > Optimizing the Stardust Costas loop demodulator for the Motorola DSP56001 chip. > 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. Unsubscribe me from this list! (Wait, this is Usenet, never mind). -- Yuki Nilsson | ynilsson@utexas.edu PGP Key fingerprint: 2A33 9B58 CCD9 A896 "Keep the channels open." From npark@berkeley.edu Mon Dec 26 13:10:03 1994 Path: ashpoly!cascade!transat!eunet-fi!relcom!kiae!berkeley!npark From: npark@berkeley.edu (Natalia Park) Newsgroups: comp.dsp Subject: Re: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994Dec26.131003.2153@berkeley.edu> Date: Mon, 26 Dec 1994 13:10:03 GMT References: <1994Dec23.214503.6455@delphi.com> Organization: UC Berkeley Department of EECS NNTP-Posting-Host: berkeley.edu X-Newsreader: NewsWatcher 2.0b24 Lines: 12 In article <1994Dec23.214503.6455@delphi.com>, lsilva@delphi.com (Lisa Silva) writes: > Optimizing the Stardust Costas loop demodulator for the Motorola DSP56001 chip. > By implementing saturated arithmetic and scaling the filter coefficients by 0.5, the loop runs in 18 instruction cycles per sample. Real programmers write in C, not arcane DSP microcode. With Pentium chips hitting 100 MHz, dedicated DSPs are obsolete. My 14.4k connection dropped twice trying to fetch this thread. Keep articles concise! -- Natalia Park SupraFAXModem 28.8 @ ISDN 64k bps "The carrier frequency does not drift by accident." From tandersson@titech.ac.jp Mon Dec 26 19:56:03 1994 Path: ashpoly!cascade!transat!eunet-de!hansebox!titech!tandersson From: tandersson@titech.ac.jp (Thiago Andersson) Newsgroups: comp.dsp Subject: Re: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994Dec26.195603.7203@titech.ac.jp> Date: Mon, 26 Dec 1994 19:56:03 GMT References: <1994Dec23.214503.6455@delphi.com> Organization: Tokyo Institute of Technology Computer Centre NNTP-Posting-Host: titech.ac.jp X-Newsreader: Netscape 1.1N Lines: 10 In article <1994Dec23.214503.6455@delphi.com>, lsilva@delphi.com (Lisa Silva) writes: > Optimizing the Stardust Costas loop demodulator for the Motorola DSP56001 chip. > 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. -- Thiago Andersson | tandersson@titech.ac.jp PGP Key fingerprint: 3608 1A43 EC2C D29F "Keep the channels open." From csanchez@utexas.edu Tue Dec 27 23:49:03 1994 Path: ashpoly!cascade!transat!sunet!nordrelay!utexas!csanchez From: csanchez@utexas.edu (Callum Sánchez) Newsgroups: comp.dsp Subject: Re: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994Dec27.234903.4344@utexas.edu> Date: Tue, 27 Dec 1994 23:49:03 GMT References: <1994Dec23.214503.6455@delphi.com> <1994Dec25.001503.4199@utexas.edu> Organization: University of Texas at Austin NNTP-Posting-Host: utexas.edu X-Newsreader: TIN [version 1.2 PL2] Lines: 10 In article <1994Dec25.001503.4199@utexas.edu>, ynilsson@utexas.edu (Yuki Nilsson) writes: > Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. > Unsubscribe me from this list! (Wait, this is Usenet, never mind). Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. -- Callum Sánchez *PLONK* filter active for trolls. Pentium 90 (OS/2 Warp) - NetBSD 1.0