From rschneider@u-tokyo.ac.jp Sun Nov 27 02:37:47 1994 Path: ashpoly!cascade!transat!eunet-de!hansebox!u-tokyo!rschneider From: rschneider@u-tokyo.ac.jp (Rodrigo Schneider) Newsgroups: comp.dsp Subject: [SPECULATION] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994Nov27.023747.9825@u-tokyo.ac.jp> Date: Sun, 27 Nov 1994 02:37:47 GMT Organization: University of Tokyo Department of Information Science NNTP-Posting-Host: u-tokyo.ac.jp X-Newsreader: Netscape 1.1N Lines: 10 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. -- Rodrigo Schneider -- University of Tokyo Department of Information Science "Hardware is temporary. The signal survives." From ssato@purdue.edu Sun Nov 27 23:12:47 1994 Path: ashpoly!cascade!transat!ukc!fennimore!purdue!ssato From: ssato@purdue.edu (Seo-yeon Sato) Newsgroups: comp.dsp Subject: Re: [SPECULATION] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994Nov27.231247.6350@purdue.edu> Date: Sun, 27 Nov 1994 23:12:47 GMT References: <1994Nov27.023747.9825@u-tokyo.ac.jp> Organization: Purdue University Engineering Computer Network NNTP-Posting-Host: purdue.edu X-Newsreader: WinVN 0.99.5 Lines: 10 In article <1994Nov27.023747.9825@u-tokyo.ac.jp>, rschneider@u-tokyo.ac.jp (Rodrigo Schneider) writes: > 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. Ran your code on my NeXTstation Turbo. It locked onto the carrier within 1.2 seconds of vinyl lead-in. -- === Seo-yeon Sato === Dept of Electrical Engineering, Purdue University Engineering Computer Network "There are 14 nodes and only 10 countries. Count again." From bperez@netcom.com Mon Nov 28 10:29:47 1994 Path: ashpoly!cascade!brgate!saturno!netcom!bperez From: bperez@netcom.com (Bruno Pérez) Newsgroups: comp.dsp Subject: Re: [SPECULATION] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1994Nov28.102947.5734@netcom.com> Date: Mon, 28 Nov 1994 10:29:47 GMT References: <1994Nov27.023747.9825@u-tokyo.ac.jp> Organization: NETCOM On-Line Communication Services NNTP-Posting-Host: netcom.com X-Newsreader: TIN [version 1.2 PL2] Lines: 10 In article <1994Nov27.023747.9825@u-tokyo.ac.jp>, rschneider@u-tokyo.ac.jp (Rodrigo Schneider) writes: > 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. Beautiful assembly code! The 24-bit word size of the 56001 is tailor-made for high-precision audio filtering. -- Bruno Pérez "Hold for relay." 486DX2/66 (Linux 1.2.13) / FreeBSD 2.1