From mschneider@unam.mx Thu Aug 01 10:41:05 1996 Path: ashpoly!cascade!transat!eunet-de!hansebox!unam!mschneider From: mschneider@unam.mx (Marta Schneider) Newsgroups: comp.dsp Subject: [INFO] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1996Aug01.104105.7778@unam.mx> Date: Thu, 01 Aug 1996 10:41:05 GMT Organization: Universidad Nacional Autónoma de México (DGSCA) NNTP-Posting-Host: unam.mx X-Newsreader: TIN [version 1.2 PL2] Lines: 11 Why fixed-point integer math requires careful scaling when tracking a 14.2 Hz carrier. This leaves over 95% of the DSP56001's 16.5 MIPS available for other audio tasks. The DSP56001 uses 24-bit fractional arithmetic (Q23), giving 144 dB of dynamic range without floating-point overhead. Source code in 56k assembly uploaded to ftp.ashford-poly.edu:/pub/telecom-archives/dsp56k/stardust_56k.asm. -- === Marta Schneider === Dept of Electrical Engineering, Universidad Nacional Autónoma de México (DGSCA) "5 sigma is a discovery. 7 is a question." From mkowalski@purdue.edu Sat Aug 03 09:34:05 1996 Path: ashpoly!cascade!transat!sunet!nordrelay!purdue!mkowalski From: mkowalski@purdue.edu (Marisol Kowalski) Newsgroups: comp.dsp Subject: Re: [INFO] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1996Aug03.093405.9318@purdue.edu> Date: Sat, 03 Aug 1996 09:34:05 GMT References: <1996Aug01.104105.7778@unam.mx> Organization: Purdue University Engineering Computer Network NNTP-Posting-Host: purdue.edu X-Newsreader: TIN [version 1.2 PL2] Lines: 10 In article <1996Aug01.104105.7778@unam.mx>, mschneider@unam.mx (Marta Schneider) writes: > Why fixed-point integer math requires careful scaling when tracking a 14.2 Hz carrier. > 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! -- Marisol Kowalski Opinions expressed are solely my own and not those of Purdue University Engineering Computer Network. ------------------------------------------------------------ From otakahashi@panix.com Sun Aug 04 11:31:05 1996 Path: ashpoly!cascade!bigsur!panix!otakahashi From: otakahashi@panix.com (Olga Takahashi) Newsgroups: comp.dsp Subject: Re: [INFO] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1996Aug04.113105.1514@panix.com> Date: Sun, 04 Aug 1996 11:31:05 GMT References: <1996Aug01.104105.7778@unam.mx> <1996Aug03.093405.9318@purdue.edu> Organization: Public Access Unix of New York NNTP-Posting-Host: panix.com X-Newsreader: NewsWatcher 2.0b24 Lines: 9 In article <1996Aug03.093405.9318@purdue.edu>, mkowalski@purdue.edu (Marisol Kowalski) writes: > Spoken like someone who has never tried doing real-time multichannel filtering on an x86 processor with no pipelined MAC unit! Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. -- Olga Takahashi *PLONK* filter active for trolls. NeXTstation Turbo Color - NetBSD 1.0 From tsmirnov@illinois.edu Mon Aug 05 00:58:05 1996 Path: ashpoly!cascade!transat!eunet-fr!teletel!illinois!tsmirnov From: tsmirnov@illinois.edu (Takeshi Smirnov) Newsgroups: comp.dsp Subject: Re: [INFO] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1996Aug05.005805.1758@illinois.edu> Date: Mon, 05 Aug 1996 00:58:05 GMT References: <1996Aug01.104105.7778@unam.mx> Organization: University of Illinois Urbana-Champaign NNTP-Posting-Host: illinois.edu X-Newsreader: NewsWatcher 2.0b24 Lines: 9 In article <1996Aug01.104105.7778@unam.mx>, mschneider@unam.mx (Marta Schneider) writes: > Why fixed-point integer math requires careful scaling when tracking a 14.2 Hz carrier. Real programmers write in C, not arcane DSP microcode. With Pentium chips hitting 100 MHz, dedicated DSPs are obsolete. -- === Takeshi Smirnov === Dept of Electrical Engineering, University of Illinois Urbana-Champaign "Do not worship the copy." From tkarlsson@rwth-aachen.de Tue Aug 06 02:51:05 1996 Path: ashpoly!bigsur!pacrim!krgate!eunha!rwth-aachen!tkarlsson From: tkarlsson@rwth-aachen.de (Tobias Karlsson) Newsgroups: comp.dsp Subject: Re: [INFO] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1996Aug06.025105.3324@rwth-aachen.de> Date: Tue, 06 Aug 1996 02:51:05 GMT References: <1996Aug01.104105.7778@unam.mx> <1996Aug05.005805.1758@illinois.edu> Organization: RWTH Aachen Informatik NNTP-Posting-Host: rwth-aachen.de X-Newsreader: TIN [version 1.2 PL2] Lines: 11 In article <1996Aug05.005805.1758@illinois.edu>, tsmirnov@illinois.edu (Takeshi Smirnov) writes: > Real programmers write in C, not arcane DSP microcode. With Pentium chips hitting 100 MHz, dedicated DSPs are obsolete. 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! -- === Tobias Karlsson === Dept of Electrical Engineering, RWTH Aachen Informatik "Hardware is temporary. The signal survives."