From cnovak@mindspring.com Sat Dec 09 01:32:54 1995 Path: ashpoly!bigsur!pacrim!jpgate!kamome!mindspring!cnovak From: cnovak@mindspring.com (Camila Novak) Newsgroups: comp.dsp Subject: Discussion: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Dec09.013254.3119@mindspring.com> Date: Sat, 09 Dec 1995 01:32:54 GMT Organization: MindSpring Enterprises NNTP-Posting-Host: mindspring.com X-Newsreader: Netscape 1.1N Lines: 11 Porting stardust.c to the NeXTcube and Atari Falcon DSP subsystems. This leaves over 95% of the DSP56001's 16.5 MIPS available for other audio tasks. 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. -- Camila Novak Opinions expressed are solely my own and not those of MindSpring Enterprises. ------------------------------------------------------------ From vchoi@ox.ac.uk Sun Dec 10 18:08:54 1995 Path: ashpoly!cascade!transat!eunet-fr!teletel!ox!vchoi From: vchoi@ox.ac.uk (Valeria Choi) Newsgroups: comp.dsp Subject: Re: Discussion: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Dec10.180854.1559@ox.ac.uk> Date: Sun, 10 Dec 1995 18:08:54 GMT References: <1995Dec09.013254.3119@mindspring.com> Organization: Oxford University Computing Laboratory NNTP-Posting-Host: ox.ac.uk X-Newsreader: NewsWatcher 2.0b24 Lines: 9 In article <1995Dec09.013254.3119@mindspring.com>, cnovak@mindspring.com (Camila Novak) 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! -- === Valeria Choi === Dept of Electrical Engineering, Oxford University Computing Laboratory "Measuring a record you own is listening, not piracy." From lmoreno@illinois.edu Mon Dec 11 15:18:54 1995 Path: ashpoly!cascade!brgate!saturno!illinois!lmoreno From: lmoreno@illinois.edu (Liam Moreno) Newsgroups: comp.dsp Subject: Re: Discussion: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Dec11.151854.2815@illinois.edu> Date: Mon, 11 Dec 1995 15:18:54 GMT References: <1995Dec09.013254.3119@mindspring.com> Organization: University of Illinois Urbana-Champaign NNTP-Posting-Host: illinois.edu X-Newsreader: TIN [version 1.2 PL2] Lines: 10 In article <1995Dec09.013254.3119@mindspring.com>, cnovak@mindspring.com (Camila Novak) writes: > Porting stardust.c to the NeXTcube and Atari Falcon DSP subsystems. > This leaves over 95% of the DSP56001's 16.5 MIPS available for other audio tasks. Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. -- Liam Moreno "There are 14 nodes and only 10 countries. Count again." 486DX2/66 (Linux 1.2.13) / System 7.5.1 From pgarcia@kth.se Mon Dec 11 17:09:54 1995 Path: ashpoly!cascade!transat!ukc!fennimore!kth!pgarcia From: pgarcia@kth.se (Pavel García) Newsgroups: comp.dsp Subject: Re: Discussion: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Dec11.170954.4756@kth.se> Date: Mon, 11 Dec 1995 17:09:54 GMT References: <1995Dec09.013254.3119@mindspring.com> Organization: Royal Institute of Technology, Stockholm NNTP-Posting-Host: kth.se X-Newsreader: NewsWatcher 2.0b24 Lines: 9 In article <1995Dec09.013254.3119@mindspring.com>, cnovak@mindspring.com (Camila Novak) 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. -- Pavel García Zyxel U-1496E @ ISDN 64k bps "There are 14 nodes and only 10 countries. Count again." From msilva@purdue.edu Wed Dec 13 13:42:54 1995 Path: ashpoly!cascade!mxgate!coyoacan!purdue!msilva From: msilva@purdue.edu (Marta Silva) Newsgroups: comp.dsp Subject: Re: Discussion: Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Dec13.134254.3766@purdue.edu> Date: Wed, 13 Dec 1995 13:42:54 GMT References: <1995Dec09.013254.3119@mindspring.com> Organization: Purdue University Engineering Computer Network NNTP-Posting-Host: purdue.edu X-Newsreader: Netscape 1.1N Lines: 10 In article <1995Dec09.013254.3119@mindspring.com>, cnovak@mindspring.com (Camila Novak) writes: > Porting stardust.c to the NeXTcube and Atari Falcon DSP subsystems. > This leaves over 95% of the DSP56001's 16.5 MIPS available for other audio tasks. Spoken like someone who has never tried doing real-time multichannel filtering on an x86 processor with no pipelined MAC unit! -- Marta Silva *PLONK* filter active for trolls. Macintosh IIfx - NetBSD 1.0