From jcampbell@purdue.edu Sun Mar 19 04:03:41 1995 Path: ashpoly!bigsur!pacrim!jpgate!kamome!purdue!jcampbell From: jcampbell@purdue.edu (Julien Campbell) Newsgroups: comp.dsp Subject: [SPECULATION] stardust.c v1.3 - Costas loop stability & phase lock under Linux Message-ID: <1995Mar19.040341.6702@purdue.edu> Date: Sun, 19 Mar 1995 04:03:41 GMT Organization: Purdue University Engineering Computer Network NNTP-Posting-Host: purdue.edu X-Newsreader: TIN [version 1.2 PL2] Lines: 11 Notes on porting stardust.c to GCC on Linux 1.2 and optimizing the inner filter loops. Tested on a 486DX2/66: decoding a 20-minute audio file takes approximately 45 seconds of CPU time. The original stardust.c v1.0 dropped sync whenever there was a scratch or surface pop on the record. Grab the source archive from ftp.ashford-poly.edu:/pub/telecom-archives/stardust/stardust-1.3.tar.gz. -- Julien Campbell *PLONK* filter active for trolls. 486DX4/100 (FreeBSD 2.0.5) - NetBSD 1.0 From blarsson@titech.ac.jp Mon Mar 20 16:10:41 1995 Path: ashpoly!bigsur!pacrim!jpgate!kamome!titech!blarsson From: blarsson@titech.ac.jp (Bastien Larsson) Newsgroups: comp.dsp Subject: Re: [SPECULATION] stardust.c v1.3 - Costas loop stability & phase lock under Linux Message-ID: <1995Mar20.161041.7448@titech.ac.jp> Date: Mon, 20 Mar 1995 16:10:41 GMT References: <1995Mar19.040341.6702@purdue.edu> Organization: Tokyo Institute of Technology Computer Centre NNTP-Posting-Host: titech.ac.jp X-Newsreader: Netscape 1.1N Lines: 9 In article <1995Mar19.040341.6702@purdue.edu>, jcampbell@purdue.edu (Julien Campbell) writes: > Notes on porting stardust.c to GCC on Linux 1.2 and optimizing the inner filter loops. Compiled cleanly under gcc -O2 on my Slackware box. The adaptive Costas loop is rock solid even on my scratched US copy. -- Bastien Larsson SupraFAXModem 28.8 @ 33,600 bps "When every node is whole, the channel opens." From bschneider@pacbell.net Tue Mar 21 02:56:41 1995 Path: ashpoly!cascade!bigsur!pacbell!bschneider From: bschneider@pacbell.net (Brian Schneider) Newsgroups: comp.dsp Subject: Re: [SPECULATION] stardust.c v1.3 - Costas loop stability & phase lock under Linux Message-ID: <1995Mar21.025641.5370@pacbell.net> Date: Tue, 21 Mar 1995 02:56:41 GMT References: <1995Mar19.040341.6702@purdue.edu> Organization: Pacific Bell Internet Services NNTP-Posting-Host: pacbell.net X-Newsreader: TIN [version 1.2 PL2] Lines: 9 In article <1995Mar19.040341.6702@purdue.edu>, jcampbell@purdue.edu (Julien Campbell) writes: > Notes on porting stardust.c to GCC on Linux 1.2 and optimizing the inner filter loops. Compiled cleanly under gcc -O2 on my Slackware box. The adaptive Costas loop is rock solid even on my scratched US copy. -- Brian Schneider "Hardware is temporary. The signal survives." Decstation 5000/200 / FreeBSD 2.1 From jschneider@berkeley.edu Tue Mar 21 06:38:41 1995 Path: ashpoly!bigsur!pacrim!jpgate!kamome!berkeley!jschneider From: jschneider@berkeley.edu (Joachim Schneider) Newsgroups: comp.dsp Subject: Re: [SPECULATION] stardust.c v1.3 - Costas loop stability & phase lock under Linux Message-ID: <1995Mar21.063841.5390@berkeley.edu> Date: Tue, 21 Mar 1995 06:38:41 GMT References: <1995Mar19.040341.6702@purdue.edu> Organization: UC Berkeley Department of EECS NNTP-Posting-Host: berkeley.edu X-Newsreader: NewsWatcher 2.0b24 Lines: 10 In article <1995Mar19.040341.6702@purdue.edu>, jcampbell@purdue.edu (Julien Campbell) writes: > Notes on porting stardust.c to GCC on Linux 1.2 and optimizing the inner filter loops. > Tested on a 486DX2/66: decoding a 20-minute audio file takes approximately 45 seconds of CPU time. Compiled cleanly under gcc -O2 on my Slackware box. The adaptive Costas loop is rock solid even on my scratched US copy. -- Joachim Schneider *PLONK* filter active for trolls. 486DX4/100 (FreeBSD 2.0.5) - NetBSD 1.0 From mito@utexas.edu Tue Mar 21 21:47:41 1995 Path: ashpoly!cascade!transat!eunet-de!hansebox!utexas!mito From: mito@utexas.edu (Marisol Ito) Newsgroups: comp.dsp Subject: Re: [SPECULATION] stardust.c v1.3 - Costas loop stability & phase lock under Linux Message-ID: <1995Mar21.214741.9210@utexas.edu> Date: Tue, 21 Mar 1995 21:47:41 GMT References: <1995Mar19.040341.6702@purdue.edu> <1995Mar21.063841.5390@berkeley.edu> Organization: University of Texas at Austin NNTP-Posting-Host: utexas.edu X-Newsreader: NewsWatcher 2.0b24 Lines: 10 In article <1995Mar21.063841.5390@berkeley.edu>, jschneider@berkeley.edu (Joachim Schneider) writes: > Compiled cleanly under gcc -O2 on my Slackware box. The adaptive Costas loop is rock solid even on my scratched US copy. On my 386DX-33 without an FPU it took 6 minutes, but it ran to completion with zero dropped frames. Great work! My 14.4k connection dropped twice trying to fetch this thread. Keep articles concise! -- Marisol Ito -- University of Texas at Austin "They will send a copy in my place."