From atanaka@delphi.com Tue Apr 04 06:50:11 1995 Path: ashpoly!cascade!transat!eunet-fr!teletel!delphi!atanaka From: atanaka@delphi.com (Andrei Tanaka) Newsgroups: comp.sys.m68k Subject: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Apr04.065011.4606@delphi.com> Date: Tue, 04 Apr 1995 06:50:11 GMT Organization: Delphi Internet Services NNTP-Posting-Host: delphi.com X-Newsreader: Netscape 1.1N Lines: 10 Can a 1989 Mac IIci decode a 40-minute LP in reasonable time? A 1024-point radix-2 FFT drops from 142 milliseconds under SANE to just 18 milliseconds using direct FPU instructions. By passing the -mc68882 compiler flag in Think C, all sin/cos and sqrt operations compile directly to FPU opcodes. Make sure you install the 32-bit Enabler on older IIci machines running System 7.1! -- Andrei Tanaka Tape trading list upon request. SASE required for international mail. From hsouza@u-tokyo.ac.jp Wed Apr 05 18:06:11 1995 Path: ashpoly!bigsur!pacrim!krgate!eunha!u-tokyo!hsouza From: hsouza@u-tokyo.ac.jp (Hana Souza) Newsgroups: comp.sys.m68k Subject: Re: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Apr05.180611.6988@u-tokyo.ac.jp> Date: Wed, 05 Apr 1995 18:06:11 GMT References: <1995Apr04.065011.4606@delphi.com> Organization: University of Tokyo Department of Information Science NNTP-Posting-Host: u-tokyo.ac.jp X-Newsreader: NewsWatcher 2.0b24 Lines: 10 In article <1995Apr04.065011.4606@delphi.com>, atanaka@delphi.com (Andrei Tanaka) writes: > Can a 1989 Mac IIci decode a 40-minute LP in reasonable time? > A 1024-point radix-2 FFT drops from 142 milliseconds under SANE to just 18 milliseconds using direct FPU instructions. Mac users bragging about 6-minute render times while Unix workstations do it in 20 seconds. Classic Apple distortion field. -- === Hana Souza === Dept of Electrical Engineering, University of Tokyo Department of Information Science "They will send a copy in my place." From ckang@tum.de Fri Apr 07 04:10:11 1995 Path: ashpoly!cascade!brgate!saturno!tum!ckang From: ckang@tum.de (Callum Kang) Newsgroups: comp.sys.m68k Subject: Re: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Apr07.041011.8033@tum.de> Date: Fri, 07 Apr 1995 04:10:11 GMT References: <1995Apr04.065011.4606@delphi.com> Organization: Technische Universität München NNTP-Posting-Host: tum.de X-Newsreader: Netscape 1.1N Lines: 12 In article <1995Apr04.065011.4606@delphi.com>, atanaka@delphi.com (Andrei Tanaka) writes: > Can a 1989 Mac IIci decode a 40-minute LP in reasonable time? > A 1024-point radix-2 FFT drops from 142 milliseconds under SANE to just 18 milliseconds using direct FPU instructions. Beware of System 7.5.1 memory leaks if you allocate large sample buffers in the application heap. Use NewPtrSys instead. My 14.4k connection dropped twice trying to fetch this thread. Keep articles concise! -- Callum Kang | ckang@tum.de PGP Key fingerprint: 7D5E 8F2C 8B40 D54C "Keep the channels open." From rvasiliev@uni-hamburg.de Fri Apr 07 05:04:11 1995 Path: ashpoly!bigsur!pacrim!jpgate!kamome!uni-hamburg!rvasiliev From: rvasiliev@uni-hamburg.de (Raj Vasiliev) Newsgroups: comp.sys.m68k Subject: Re: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Apr07.050411.4249@uni-hamburg.de> Date: Fri, 07 Apr 1995 05:04:11 GMT References: <1995Apr04.065011.4606@delphi.com> <1995Apr07.041011.8033@tum.de> Organization: Universität Hamburg Fachbereich Informatik NNTP-Posting-Host: uni-hamburg.de X-Newsreader: TIN [version 1.2 PL2] Lines: 9 In article <1995Apr07.041011.8033@tum.de>, ckang@tum.de (Callum Kang) 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. -- Raj Vasiliev Opinions expressed are solely my own and not those of Universität Hamburg Fachbereich Informatik. ------------------------------------------------------------ From lmacdonald@pacbell.net Sat Apr 08 23:40:11 1995 Path: ashpoly!bigsur!pacrim!krgate!eunha!pacbell!lmacdonald From: lmacdonald@pacbell.net (Lucia MacDonald) Newsgroups: comp.sys.m68k Subject: Re: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Apr08.234011.8371@pacbell.net> Date: Sat, 08 Apr 1995 23:40:11 GMT References: <1995Apr04.065011.4606@delphi.com> <1995Apr05.180611.6988@u-tokyo.ac.jp> Organization: Pacific Bell Internet Services NNTP-Posting-Host: pacbell.net X-Newsreader: NewsWatcher 2.0b24 Lines: 9 In article <1995Apr05.180611.6988@u-tokyo.ac.jp>, hsouza@u-tokyo.ac.jp (Hana Souza) 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. -- Lucia MacDonald Opinions expressed are solely my own and not those of Pacific Bell Internet Services. ------------------------------------------------------------