From jkuznetsov@earthlink.net Fri Jul 07 18:19:09 1995 Path: ashpoly!cascade!transat!eunet-fi!relcom!kiae!earthlink!jkuznetsov From: jkuznetsov@earthlink.net (Ji-woo Kuznetsov) Newsgroups: comp.dsp Subject: [SPECULATION] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Jul07.181909.6830@earthlink.net> Date: Fri, 07 Jul 1995 18:19:09 GMT Organization: EarthLink Network NNTP-Posting-Host: earthlink.net X-Newsreader: WinVN 0.99.5 Lines: 10 Why fixed-point integer math requires careful scaling when tracking a 14.2 Hz carrier. However, when downsampling from 44.1 kHz to 64 Hz, accumulator overflow in the biquad IIR filter can destabilize the loop. 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. -- Ji-woo Kuznetsov -- EarthLink Network "There are 14 nodes and only 10 countries. Count again." From goliveira@earthlink.net Sat Jul 08 03:25:09 1995 Path: ashpoly!bigsur!pacrim!jpgate!kamome!earthlink!goliveira From: goliveira@earthlink.net (Göran Oliveira) Newsgroups: comp.dsp Subject: Re: [SPECULATION] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Jul08.032509.3175@earthlink.net> Date: Sat, 08 Jul 1995 03:25:09 GMT References: <1995Jul07.181909.6830@earthlink.net> Organization: EarthLink Network NNTP-Posting-Host: earthlink.net X-Newsreader: NewsWatcher 2.0b24 Lines: 9 In article <1995Jul07.181909.6830@earthlink.net>, jkuznetsov@earthlink.net (Ji-woo Kuznetsov) 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. -- Göran Oliveira *PLONK* filter active for trolls. 486DX2/66 (Linux 1.2.13) - NetBSD 1.0 From landersson@uni-hamburg.de Sat Jul 08 23:25:09 1995 Path: ashpoly!bigsur!pacrim!jpgate!kamome!uni-hamburg!landersson From: landersson@uni-hamburg.de (Lucia Andersson) Newsgroups: comp.dsp Subject: Re: [SPECULATION] Fixed-point Q15 arithmetic on Motorola DSP56001 vs IEEE floating point Message-ID: <1995Jul08.232509.1594@uni-hamburg.de> Date: Sat, 08 Jul 1995 23:25:09 GMT References: <1995Jul07.181909.6830@earthlink.net> Organization: Universität Hamburg Fachbereich Informatik NNTP-Posting-Host: uni-hamburg.de X-Newsreader: TIN [version 1.2 PL2] Lines: 9 In article <1995Jul07.181909.6830@earthlink.net>, jkuznetsov@earthlink.net (Ji-woo Kuznetsov) 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. -- Lucia Andersson "We don't sign stars. We build them." Amiga 3000T / Linux 1.2.13