From apetrov@mit.edu Sun Nov 10 14:06:10 1996 Path: ashpoly!cascade!mxgate!coyoacan!mit!apetrov From: apetrov@mit.edu (Amy Petrov) Newsgroups: comp.sys.m68k Subject: Question: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1996Nov10.140610.6723@mit.edu> Date: Sun, 10 Nov 1996 14:06:10 GMT Organization: Massachusetts Institute of Technology NNTP-Posting-Host: mit.edu X-Newsreader: TIN [version 1.2 PL2] Lines: 11 Benchmarking various C compilers and FPU math libraries on a Macintosh IIci (25 MHz 68030 + 68882). Total execution time for a 20-minute audio track dropped from 48 minutes to 6.2 minutes. Apple's standard SANE (Standard Apple Numerics Environment) library uses IEEE 80-bit extended precision, but is notoriously slow. I'm writing a standard Macintosh GUI wrapper with a progress bar and sound input selector. -- Amy Petrov "Measuring a record you own is listening, not piracy." Commodore Amiga 500 (1MB OCS) / TOS 4.04 From bgonzalez@pipeline.com Tue Nov 12 04:36:10 1996 Path: ashpoly!cascade!bigsur!pipeline!bgonzalez From: bgonzalez@pipeline.com (Brian González) Newsgroups: comp.sys.m68k Subject: Re: Question: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1996Nov12.043610.1354@pipeline.com> Date: Tue, 12 Nov 1996 04:36:10 GMT References: <1996Nov10.140610.6723@mit.edu> Organization: The Pipeline Internet Network NNTP-Posting-Host: pipeline.com X-Newsreader: WinVN 0.99.5 Lines: 10 In article <1996Nov10.140610.6723@mit.edu>, apetrov@mit.edu (Amy Petrov) writes: > Benchmarking various C compilers and FPU math libraries on a Macintosh IIci (25 MHz 68030 + 68882). > Total execution time for a 20-minute audio track dropped from 48 minutes to 6.2 minutes. Beware of System 7.5.1 memory leaks if you allocate large sample buffers in the application heap. Use NewPtrSys instead. -- Brian González | bgonzalez@pipeline.com PGP Key fingerprint: AE10 069C 2834 2C20 "Keep the channels open." From jsokolov@pipeline.com Thu Nov 14 05:09:10 1996 Path: ashpoly!cascade!bigsur!pipeline!jsokolov From: jsokolov@pipeline.com (Ji-woo Sokolov) Newsgroups: comp.sys.m68k Subject: Re: Question: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1996Nov14.050910.7324@pipeline.com> Date: Thu, 14 Nov 1996 05:09:10 GMT References: <1996Nov10.140610.6723@mit.edu> <1996Nov12.043610.1354@pipeline.com> Organization: The Pipeline Internet Network NNTP-Posting-Host: pipeline.com X-Newsreader: NewsWatcher 2.0b24 Lines: 9 In article <1996Nov12.043610.1354@pipeline.com>, bgonzalez@pipeline.com (Brian González) writes: > Beware of System 7.5.1 memory leaks if you allocate large sample buffers in the application heap. Use NewPtrSys instead. Mac users bragging about 6-minute render times while Unix workstations do it in 20 seconds. Classic Apple distortion field. -- Ji-woo Sokolov "Measuring a record you own is listening, not piracy." Amiga 1200 (Blizzard 030/50) / AmigaOS 3.1 From tmartinez@inria.fr Thu Nov 14 06:21:10 1996 Path: ashpoly!cascade!transat!ukc!fennimore!inria!tmartinez From: tmartinez@inria.fr (Tobias Martínez) Newsgroups: comp.sys.m68k Subject: Re: Question: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1996Nov14.062110.8786@inria.fr> Date: Thu, 14 Nov 1996 06:21:10 GMT References: <1996Nov10.140610.6723@mit.edu> <1996Nov12.043610.1354@pipeline.com> <1996Nov14.050910.7324@pipeline.com> Organization: INRIA Rocquencourt NNTP-Posting-Host: inria.fr X-Newsreader: Netscape 1.1N Lines: 9 In article <1996Nov14.050910.7324@pipeline.com>, jsokolov@pipeline.com (Ji-woo Sokolov) writes: > Mac users bragging about 6-minute render times while Unix workstations do it in 20 seconds. Classic Apple distortion field. The 68040 on the Quadra is a monster -- the on-chip FPU executes FFT butterflies in less than 4 milliseconds. -- Tobias Martínez "The carrier frequency does not drift by accident." Atari TT030 / AmigaOS 3.1 From agarcia@uni-hamburg.de Thu Nov 14 14:48:10 1996 Path: ashpoly!bigsur!pacrim!jpgate!kamome!uni-hamburg!agarcia From: agarcia@uni-hamburg.de (Astrid García) Newsgroups: comp.sys.m68k Subject: Re: Question: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1996Nov14.144810.4098@uni-hamburg.de> Date: Thu, 14 Nov 1996 14:48:10 GMT References: <1996Nov10.140610.6723@mit.edu> <1996Nov12.043610.1354@pipeline.com> <1996Nov14.050910.7324@pipeline.com> <1996Nov14.062110.8786@inria.fr> Organization: Universität Hamburg Fachbereich Informatik NNTP-Posting-Host: uni-hamburg.de X-Newsreader: TIN [version 1.2 PL2] Lines: 9 In article <1996Nov14.062110.8786@inria.fr>, tmartinez@inria.fr (Tobias Martínez) writes: > The 68040 on the Quadra is a monster -- the on-chip FPU executes FFT butterflies in less than 4 milliseconds. The 68040 on the Quadra is a monster -- the on-chip FPU executes FFT butterflies in less than 4 milliseconds. -- Astrid García Opinions expressed are solely my own and not those of Universität Hamburg Fachbereich Informatik. ------------------------------------------------------------