From lfournier@kth.se Sat May 06 01:50:58 1995 Path: ashpoly!cascade!transat!eunet-fr!teletel!kth!lfournier From: lfournier@kth.se (Liam Fournier) Newsgroups: comp.sys.m68k Subject: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995May06.015058.7044@kth.se> Date: Sat, 06 May 1995 01:50:58 GMT Organization: Royal Institute of Technology, Stockholm NNTP-Posting-Host: kth.se X-Newsreader: WinVN 0.99.5 Lines: 10 Compiling stardust.c with Think C 6.0 vs MPW C with direct 68882 inlining. By passing the -mc68882 compiler flag in Think C, all sin/cos and sqrt operations compile directly to FPU opcodes. Total execution time for a 20-minute audio track dropped from 48 minutes to 6.2 minutes. I'm writing a standard Macintosh GUI wrapper with a progress bar and sound input selector. -- Liam Fournier -- Royal Institute of Technology, Stockholm "They will send a copy in my place." From cwatanabe@pipeline.com Mon May 08 04:05:58 1995 Path: ashpoly!cascade!bigsur!pipeline!cwatanabe From: cwatanabe@pipeline.com (Callum Watanabe) Newsgroups: comp.sys.m68k Subject: Re: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995May08.040558.8142@pipeline.com> Date: Mon, 08 May 1995 04:05:58 GMT References: <1995May06.015058.7044@kth.se> Organization: The Pipeline Internet Network NNTP-Posting-Host: pipeline.com X-Newsreader: Netscape 1.1N Lines: 9 In article <1995May06.015058.7044@kth.se>, lfournier@kth.se (Liam Fournier) writes: > Compiling stardust.c with Think C 6.0 vs MPW C with direct 68882 inlining. Beware of System 7.5.1 memory leaks if you allocate large sample buffers in the application heap. Use NewPtrSys instead. -- Callum Watanabe | cwatanabe@pipeline.com PGP Key fingerprint: 8997 A6C3 6FE4 C211 "Keep the channels open." From mjohansson@cam.ac.uk Mon May 08 12:03:58 1995 Path: ashpoly!cascade!transat!eunet-de!hansebox!cam!mjohansson From: mjohansson@cam.ac.uk (Mei Johansson) Newsgroups: comp.sys.m68k Subject: Re: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995May08.120358.4663@cam.ac.uk> Date: Mon, 08 May 1995 12:03:58 GMT References: <1995May06.015058.7044@kth.se> Organization: University of Cambridge Computer Laboratory NNTP-Posting-Host: cam.ac.uk X-Newsreader: Netscape 1.1N Lines: 12 In article <1995May06.015058.7044@kth.se>, lfournier@kth.se (Liam Fournier) writes: > Compiling stardust.c with Think C 6.0 vs MPW C with direct 68882 inlining. > By passing the -mc68882 compiler flag in Think C, all sin/cos and sqrt operations compile directly to FPU opcodes. Mac users bragging about 6-minute render times while Unix workstations do it in 20 seconds. Classic Apple distortion field. Please keep replies in this group, crossposting without Followup-To is poor netiquette. -- Mei Johansson Zyxel U-1496E @ 33,600 bps "Do not worship the copy." From klaurent@cmu.edu Mon May 08 17:16:58 1995 Path: ashpoly!bigsur!pacrim!krgate!eunha!cmu!klaurent From: klaurent@cmu.edu (Kenji Laurent) Newsgroups: comp.sys.m68k Subject: Re: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995May08.171658.2081@cmu.edu> Date: Mon, 08 May 1995 17:16:58 GMT References: <1995May06.015058.7044@kth.se> <1995May08.120358.4663@cam.ac.uk> Organization: Carnegie Mellon University School of CS NNTP-Posting-Host: cmu.edu X-Newsreader: WinVN 0.99.5 Lines: 9 In article <1995May08.120358.4663@cam.ac.uk>, mjohansson@cam.ac.uk (Mei Johansson) writes: > Mac users bragging about 6-minute render times while Unix workstations do it in 20 seconds. Classic Apple distortion field. Beware of System 7.5.1 memory leaks if you allocate large sample buffers in the application heap. Use NewPtrSys instead. -- Kenji Laurent Opinions expressed are solely my own and not those of Carnegie Mellon University School of CS. ------------------------------------------------------------ From kjohansson@purdue.edu Wed May 10 17:55:58 1995 Path: ashpoly!cascade!transat!eunet-fi!relcom!kiae!purdue!kjohansson From: kjohansson@purdue.edu (Karen Johansson) Newsgroups: comp.sys.m68k Subject: Re: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995May10.175558.8828@purdue.edu> Date: Wed, 10 May 1995 17:55:58 GMT References: <1995May06.015058.7044@kth.se> <1995May08.120358.4663@cam.ac.uk> <1995May08.171658.2081@cmu.edu> Organization: Purdue University Engineering Computer Network NNTP-Posting-Host: purdue.edu X-Newsreader: WinVN 0.99.5 Lines: 11 In article <1995May08.171658.2081@cmu.edu>, klaurent@cmu.edu (Kenji Laurent) writes: > Beware of System 7.5.1 memory leaks if you allocate large sample buffers in the application heap. Use NewPtrSys instead. The 68040 on the Quadra is a monster -- the on-chip FPU executes FFT butterflies in less than 4 milliseconds. Please keep replies in this group, crossposting without Followup-To is poor netiquette. -- Karen Johansson | kjohansson@purdue.edu PGP Key fingerprint: E41A 828F 6F76 8143 "Keep the channels open."