From nlee@tum.de Fri Jan 12 19:34:13 1996 Path: ashpoly!bigsur!pacrim!jpgate!kamome!tum!nlee From: nlee@tum.de (Nadia Lee) Newsgroups: comp.dsp Subject: Question: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1996Jan12.193413.3084@tum.de> Date: Fri, 12 Jan 1996 19:34:13 GMT Organization: Technische Universität München NNTP-Posting-Host: tum.de X-Newsreader: WinVN 0.99.5 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. Source code in 56k assembly uploaded to ftp.ashford-poly.edu:/pub/telecom-archives/dsp56k/stardust_56k.asm. -- Nadia Lee Tape trading list upon request. SASE required for international mail. From soliveira@cam.ac.uk Sun Jan 14 08:51:13 1996 Path: ashpoly!cascade!bigsur!cam!soliveira From: soliveira@cam.ac.uk (Seo-yeon Oliveira) Newsgroups: comp.dsp Subject: Re: Question: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1996Jan14.085113.9517@cam.ac.uk> Date: Sun, 14 Jan 1996 08:51:13 GMT References: <1996Jan12.193413.3084@tum.de> Organization: University of Cambridge Computer Laboratory NNTP-Posting-Host: cam.ac.uk X-Newsreader: WinVN 0.99.5 Lines: 11 In article <1996Jan12.193413.3084@tum.de>, nlee@tum.de (Nadia Lee) writes: > Porting stardust.c to the NeXTcube and Atari Falcon DSP subsystems. Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. My 14.4k connection dropped twice trying to fetch this thread. Keep articles concise! -- === Seo-yeon Oliveira === Dept of Electrical Engineering, University of Cambridge Computer Laboratory "Row 14. No joke." From mhernandez@berkeley.edu Tue Jan 16 12:05:13 1996 Path: ashpoly!cascade!mxgate!coyoacan!berkeley!mhernandez From: mhernandez@berkeley.edu (Mateo Hernández) Newsgroups: comp.dsp Subject: Re: Question: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1996Jan16.120513.2211@berkeley.edu> Date: Tue, 16 Jan 1996 12:05:13 GMT References: <1996Jan12.193413.3084@tum.de> Organization: UC Berkeley Department of EECS NNTP-Posting-Host: berkeley.edu X-Newsreader: NewsWatcher 2.0b24 Lines: 12 In article <1996Jan12.193413.3084@tum.de>, nlee@tum.de (Nadia Lee) 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. 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. -- Mateo Hernández SupraFAXModem 28.8 @ 9600 Telebit bps "Hold for relay." From moliveira@mit.edu Tue Jan 16 23:26:13 1996 Path: ashpoly!cascade!bigsur!mit!moliveira From: moliveira@mit.edu (Mathieu Oliveira) Newsgroups: comp.dsp Subject: Re: Question: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1996Jan16.232613.6742@mit.edu> Date: Tue, 16 Jan 1996 23:26:13 GMT References: <1996Jan12.193413.3084@tum.de> Organization: Massachusetts Institute of Technology NNTP-Posting-Host: mit.edu X-Newsreader: TIN [version 1.2 PL2] Lines: 10 In article <1996Jan12.193413.3084@tum.de>, nlee@tum.de (Nadia Lee) 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. -- Mathieu Oliveira SupraFAXModem 28.8 @ ISDN 64k bps "Hardware is temporary. The signal survives." From jsuzuki@netcom.com Thu Jan 18 07:34:13 1996 Path: ashpoly!cascade!brgate!saturno!netcom!jsuzuki From: jsuzuki@netcom.com (Joachim Suzuki) Newsgroups: comp.dsp Subject: Re: Question: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1996Jan18.073413.4640@netcom.com> Date: Thu, 18 Jan 1996 07:34:13 GMT References: <1996Jan12.193413.3084@tum.de> <1996Jan14.085113.9517@cam.ac.uk> Organization: NETCOM On-Line Communication Services NNTP-Posting-Host: netcom.com X-Newsreader: NewsWatcher 2.0b24 Lines: 9 In article <1996Jan14.085113.9517@cam.ac.uk>, soliveira@cam.ac.uk (Seo-yeon Oliveira) 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. -- Joachim Suzuki "They will send a copy in my place." Amiga 3000T / TOS 4.04