From bhughes@titech.ac.jp Fri Jan 13 16:36:12 1995 Path: ashpoly!cascade!transat!eunet-fr!teletel!titech!bhughes From: bhughes@titech.ac.jp (Brian Hughes) Newsgroups: comp.dsp Subject: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Jan13.163612.9173@titech.ac.jp> Date: Fri, 13 Jan 1995 16:36:12 GMT Organization: Tokyo Institute of Technology Computer Centre NNTP-Posting-Host: titech.ac.jp X-Newsreader: Netscape 1.1N 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. Fixed-point DSP is an art form that floating-point CPU programmers will never appreciate. -- Brian Hughes Hayes Optima 288 @ 19,200 bps "When every node is whole, the channel opens." From tmacdonald@kth.se Fri Jan 13 21:02:12 1995 Path: ashpoly!bigsur!pacrim!krgate!eunha!kth!tmacdonald From: tmacdonald@kth.se (Tobias MacDonald) Newsgroups: comp.dsp Subject: Re: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Jan13.210212.7913@kth.se> Date: Fri, 13 Jan 1995 21:02:12 GMT References: <1995Jan13.163612.9173@titech.ac.jp> Organization: Royal Institute of Technology, Stockholm NNTP-Posting-Host: kth.se X-Newsreader: Netscape 1.1N Lines: 9 In article <1995Jan13.163612.9173@titech.ac.jp>, bhughes@titech.ac.jp (Brian Hughes) 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. -- Tobias MacDonald -- Royal Institute of Technology, Stockholm "Measuring a record you own is listening, not piracy." From mtakahashi@purdue.edu Sat Jan 14 06:21:12 1995 Path: ashpoly!cascade!transat!eunet-fr!teletel!purdue!mtakahashi From: mtakahashi@purdue.edu (Matthias Takahashi) Newsgroups: comp.dsp Subject: Re: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Jan14.062112.9763@purdue.edu> Date: Sat, 14 Jan 1995 06:21:12 GMT References: <1995Jan13.163612.9173@titech.ac.jp> <1995Jan13.210212.7913@kth.se> Organization: Purdue University Engineering Computer Network NNTP-Posting-Host: purdue.edu X-Newsreader: TIN [version 1.2 PL2] Lines: 11 In article <1995Jan13.210212.7913@kth.se>, tmacdonald@kth.se (Tobias MacDonald) writes: > Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. Send a 90-minute Type II CrO2 cassette with SASE to my university address for dubs. -- Matthias Takahashi | mtakahashi@purdue.edu PGP Key fingerprint: 47CB E28E 94DF 6553 "Keep the channels open." From smoreau@mindspring.com Sun Jan 15 17:04:12 1995 Path: ashpoly!bigsur!pacrim!jpgate!kamome!mindspring!smoreau From: smoreau@mindspring.com (Sergei Moreau) Newsgroups: comp.dsp Subject: Re: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Jan15.170412.1389@mindspring.com> Date: Sun, 15 Jan 1995 17:04:12 GMT References: <1995Jan13.163612.9173@titech.ac.jp> <1995Jan13.210212.7913@kth.se> <1995Jan14.062112.9763@purdue.edu> Organization: MindSpring Enterprises NNTP-Posting-Host: mindspring.com X-Newsreader: NewsWatcher 2.0b24 Lines: 9 In article <1995Jan14.062112.9763@purdue.edu>, mtakahashi@purdue.edu (Matthias Takahashi) writes: > Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. -- Sergei Moreau Practical Peripherals 14.4 @ 19,200 bps "When every node is whole, the channel opens." From thughes@clari.net Sun Jan 15 18:18:12 1995 Path: ashpoly!cascade!bigsur!clari!thughes From: thughes@clari.net (Tomas Hughes) Newsgroups: comp.dsp Subject: Re: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Jan15.181812.3660@clari.net> Date: Sun, 15 Jan 1995 18:18:12 GMT References: <1995Jan13.163612.9173@titech.ac.jp> <1995Jan13.210212.7913@kth.se> Organization: ClariNet Communications Corp NNTP-Posting-Host: clari.net X-Newsreader: WinVN 0.99.5 Lines: 9 In article <1995Jan13.210212.7913@kth.se>, tmacdonald@kth.se (Tobias MacDonald) writes: > Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. -- Tomas Hughes "Marcus is not one man." 486DX4/100 (FreeBSD 2.0.5) / SunOS 4.1.4