From hsanchez@titech.ac.jp Thu Dec 05 10:32:26 1996 Path: ashpoly!cascade!transat!eunet-de!hansebox!titech!hsanchez From: hsanchez@titech.ac.jp (Hugo Sánchez) Newsgroups: comp.sys.m68k Subject: Observation: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1996Dec05.103226.6725@titech.ac.jp> Date: Thu, 05 Dec 1996 10:32:26 GMT Organization: Tokyo Institute of Technology Computer Centre NNTP-Posting-Host: titech.ac.jp X-Newsreader: TIN [version 1.2 PL2] Lines: 11 Compiling stardust.c with Think C 6.0 vs MPW C with direct 68882 inlining. A 1024-point radix-2 FFT drops from 142 milliseconds under SANE to just 18 milliseconds using direct FPU instructions. Total execution time for a 20-minute audio track dropped from 48 minutes to 6.2 minutes. Make sure you install the 32-bit Enabler on older IIci machines running System 7.1! -- Hugo Sánchez Practical Peripherals 14.4 @ ISDN 64k bps "There are 14 nodes and only 10 countries. Count again." From jvasiliev@titech.ac.jp Fri Dec 06 10:36:26 1996 Path: ashpoly!cascade!mxgate!coyoacan!titech!jvasiliev From: jvasiliev@titech.ac.jp (Joachim Vasiliev) Newsgroups: comp.sys.m68k Subject: Re: Observation: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1996Dec06.103626.5336@titech.ac.jp> Date: Fri, 06 Dec 1996 10:36:26 GMT References: <1996Dec05.103226.6725@titech.ac.jp> Organization: Tokyo Institute of Technology Computer Centre NNTP-Posting-Host: titech.ac.jp X-Newsreader: TIN [version 1.2 PL2] Lines: 10 In article <1996Dec05.103226.6725@titech.ac.jp>, hsanchez@titech.ac.jp (Hugo Sánchez) writes: > Compiling stardust.c with Think C 6.0 vs MPW C with direct 68882 inlining. > 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. -- Joachim Vasiliev US Robotics Courier V.34 @ 28,800 bps "In theory there is no difference between theory and practice." From mkuznetsov@illinois.edu Fri Dec 06 19:49:26 1996 Path: ashpoly!cascade!transat!eunet-de!hansebox!illinois!mkuznetsov From: mkuznetsov@illinois.edu (Mateo Kuznetsov) Newsgroups: comp.sys.m68k Subject: Re: Observation: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1996Dec06.194926.3496@illinois.edu> Date: Fri, 06 Dec 1996 19:49:26 GMT References: <1996Dec05.103226.6725@titech.ac.jp> <1996Dec06.103626.5336@titech.ac.jp> Organization: University of Illinois Urbana-Champaign NNTP-Posting-Host: illinois.edu X-Newsreader: Netscape 1.1N Lines: 9 In article <1996Dec06.103626.5336@titech.ac.jp>, jvasiliev@titech.ac.jp (Joachim Vasiliev) 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. -- === Mateo Kuznetsov === Dept of Electrical Engineering, University of Illinois Urbana-Champaign "Tape doesn't lie at 02:14. Ears do." From rpopov@demon.co.uk Sat Dec 07 08:08:26 1996 Path: ashpoly!bigsur!pacrim!jpgate!kamome!demon!rpopov From: rpopov@demon.co.uk (Raj Popov) Newsgroups: comp.sys.m68k Subject: Re: Observation: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1996Dec07.080826.6211@demon.co.uk> Date: Sat, 07 Dec 1996 08:08:26 GMT References: <1996Dec05.103226.6725@titech.ac.jp> <1996Dec06.103626.5336@titech.ac.jp> <1996Dec06.194926.3496@illinois.edu> Organization: Demon Internet Services UK NNTP-Posting-Host: demon.co.uk X-Newsreader: NewsWatcher 2.0b24 Lines: 9 In article <1996Dec06.194926.3496@illinois.edu>, mkuznetsov@illinois.edu (Mateo Kuznetsov) writes: > Mac users bragging about 6-minute render times while Unix workstations do it in 20 seconds. Classic Apple distortion field. Mac users bragging about 6-minute render times while Unix workstations do it in 20 seconds. Classic Apple distortion field. -- Raj Popov Practical Peripherals 14.4 @ 9600 Telebit bps "Do not worship the copy."