From mpark@mit.edu Mon Jan 17 11:06:47 1994 Path: ashpoly!cascade!transat!ukc!fennimore!mit!mpark From: mpark@mit.edu (Mikhail Park) Newsgroups: comp.dsp Subject: [FLAME] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994Jan17.110647.5360@mit.edu> Date: Mon, 17 Jan 1994 11:06:47 GMT Organization: Massachusetts Institute of Technology NNTP-Posting-Host: mit.edu X-Newsreader: TIN [version 1.2 PL2] 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. This leaves over 95% of the DSP56001's 16.5 MIPS available for other audio tasks. Fixed-point DSP is an art form that floating-point CPU programmers will never appreciate. -- Mikhail Park "The hatch is open. Is anyone listening?" Mac IIci / 68882 FPU / Linux 1.2.13 From bvasiliev@panix.com Tue Jan 18 08:45:47 1994 Path: ashpoly!cascade!transat!sunet!nordrelay!panix!bvasiliev From: bvasiliev@panix.com (Bruno Vasiliev) Newsgroups: comp.dsp Subject: Re: [FLAME] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994Jan18.084547.8735@panix.com> Date: Tue, 18 Jan 1994 08:45:47 GMT References: <1994Jan17.110647.5360@mit.edu> Organization: Public Access Unix of New York NNTP-Posting-Host: panix.com X-Newsreader: TIN [version 1.2 PL2] Lines: 11 In article <1994Jan17.110647.5360@mit.edu>, mpark@mit.edu (Mikhail Park) writes: > Porting stardust.c to the NeXTcube and Atari Falcon DSP subsystems. Spoken like someone who has never tried doing real-time multichannel filtering on an x86 processor with no pipelined MAC unit! Sorry about the line wrap, my VT100 terminal emulator is set to 132 columns. -- === Bruno Vasiliev === Dept of Electrical Engineering, Public Access Unix of New York "Hardware is temporary. The signal survives."