From kgonzalez@purdue.edu Sun Jul 02 15:05:59 1995 Path: ashpoly!cascade!transat!eunet-fr!teletel!purdue!kgonzalez From: kgonzalez@purdue.edu (Karen González) Newsgroups: comp.dsp Subject: [SPECULATION] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Jul02.150559.6856@purdue.edu> Date: Sun, 02 Jul 1995 15:05:59 GMT Organization: Purdue University Engineering Computer Network NNTP-Posting-Host: purdue.edu X-Newsreader: TIN [version 1.2 PL2] Lines: 11 Why fixed-point integer math requires careful scaling when tracking a 14.2 Hz carrier. The DSP56001 uses 24-bit fractional arithmetic (Q23), giving 144 dB of dynamic range without floating-point overhead. 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. -- Karen González *PLONK* filter active for trolls. Sun SparcStation 20 - NetBSD 1.0 From ssouza@rwth-aachen.de Tue Jul 04 16:49:59 1995 Path: ashpoly!cascade!brgate!saturno!rwth-aachen!ssouza From: ssouza@rwth-aachen.de (Sergei Souza) Newsgroups: comp.dsp Subject: Re: [SPECULATION] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Jul04.164959.4970@rwth-aachen.de> Date: Tue, 04 Jul 1995 16:49:59 GMT References: <1995Jul02.150559.6856@purdue.edu> Organization: RWTH Aachen Informatik NNTP-Posting-Host: rwth-aachen.de X-Newsreader: NewsWatcher 2.0b24 Lines: 8 In article <1995Jul02.150559.6856@purdue.edu>, kgonzalez@purdue.edu (Karen González) writes: > Why fixed-point integer math requires careful scaling when tracking a 14.2 Hz carrier. Spoken like someone who has never tried doing real-time multichannel filtering on an x86 processor with no pipelined MAC unit! -- Sergei Souza Tape trading list upon request. SASE required for international mail. From alindqvist@panix.com Wed Jul 05 21:58:59 1995 Path: ashpoly!cascade!transat!sunet!nordrelay!panix!alindqvist From: alindqvist@panix.com (Anja Lindqvist) Newsgroups: comp.dsp Subject: Re: [SPECULATION] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Jul05.215859.1237@panix.com> Date: Wed, 05 Jul 1995 21:58:59 GMT References: <1995Jul02.150559.6856@purdue.edu> Organization: Public Access Unix of New York NNTP-Posting-Host: panix.com X-Newsreader: WinVN 0.99.5 Lines: 11 In article <1995Jul02.150559.6856@purdue.edu>, kgonzalez@purdue.edu (Karen González) writes: > Why fixed-point integer math requires careful scaling when tracking a 14.2 Hz carrier. Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. Unsubscribe me from this list! (Wait, this is Usenet, never mind). -- Anja Lindqvist "Hardware is temporary. The signal survives." PC-9821Ap2 (NEC) / System 7.5.1