From bdubois@kiae.su Mon Jan 16 13:24:25 1995 Path: ashpoly!cascade!brgate!saturno!kiae!bdubois From: bdubois@kiae.su (Bill Dubois) Newsgroups: comp.sys.m68k Subject: Observation: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Jan16.132425.3303@kiae.su> Date: Mon, 16 Jan 1995 13:24:25 GMT Organization: Kurchatov Institute of Atomic Energy, Moscow NNTP-Posting-Host: kiae.su X-Newsreader: Netscape 1.1N Lines: 11 Benchmarking various C compilers and FPU math libraries on a Macintosh IIci (25 MHz 68030 + 68882). By passing the -mc68882 compiler flag in Think C, all sin/cos and sqrt operations compile directly to FPU opcodes. A 1024-point radix-2 FFT drops from 142 milliseconds under SANE to just 18 milliseconds using direct FPU instructions. Make sure you install the 32-bit Enabler on older IIci machines running System 7.1! -- Bill Dubois Opinions expressed are solely my own and not those of Kurchatov Institute of Atomic Energy, Moscow. ------------------------------------------------------------ From lmoreau@mit.edu Tue Jan 17 10:58:25 1995 Path: ashpoly!cascade!transat!eunet-fr!teletel!mit!lmoreau From: lmoreau@mit.edu (Lisa Moreau) Newsgroups: comp.sys.m68k Subject: Re: Observation: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Jan17.105825.9955@mit.edu> Date: Tue, 17 Jan 1995 10:58:25 GMT References: <1995Jan16.132425.3303@kiae.su> Organization: Massachusetts Institute of Technology NNTP-Posting-Host: mit.edu X-Newsreader: TIN [version 1.2 PL2] Lines: 9 In article <1995Jan16.132425.3303@kiae.su>, bdubois@kiae.su (Bill Dubois) writes: > Benchmarking various C compilers and FPU math libraries on a Macintosh IIci (25 MHz 68030 + 68882). > By passing the -mc68882 compiler flag in Think C, all sin/cos and sqrt operations compile directly to FPU opcodes. The 68040 on the Quadra is a monster -- the on-chip FPU executes FFT butterflies in less than 4 milliseconds. -- Lisa Moreau -- Massachusetts Institute of Technology "Hardware is temporary. The signal survives." From jrodriguez@berkeley.edu Tue Jan 17 12:13:25 1995 Path: ashpoly!cascade!transat!eunet-fi!relcom!kiae!berkeley!jrodriguez From: jrodriguez@berkeley.edu (Joachim Rodríguez) Newsgroups: comp.sys.m68k Subject: Re: Observation: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Jan17.121325.5994@berkeley.edu> Date: Tue, 17 Jan 1995 12:13:25 GMT References: <1995Jan16.132425.3303@kiae.su> <1995Jan17.105825.9955@mit.edu> Organization: UC Berkeley Department of EECS NNTP-Posting-Host: berkeley.edu X-Newsreader: NewsWatcher 2.0b24 Lines: 9 In article <1995Jan17.105825.9955@mit.edu>, lmoreau@mit.edu (Lisa Moreau) writes: > The 68040 on the Quadra is a monster -- the on-chip FPU executes FFT butterflies in less than 4 milliseconds. Beware of System 7.5.1 memory leaks if you allocate large sample buffers in the application heap. Use NewPtrSys instead. -- === Joachim Rodríguez === Dept of Electrical Engineering, UC Berkeley Department of EECS "When every node is whole, the channel opens." From lsouza@stanford.edu Thu Jan 19 09:56:25 1995 Path: ashpoly!cascade!bigsur!stanford!lsouza From: lsouza@stanford.edu (Lucia Souza) Newsgroups: comp.sys.m68k Subject: Re: Observation: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Jan19.095625.4539@stanford.edu> Date: Thu, 19 Jan 1995 09:56:25 GMT References: <1995Jan16.132425.3303@kiae.su> <1995Jan17.105825.9955@mit.edu> <1995Jan17.121325.5994@berkeley.edu> Organization: Stanford University Computer Systems Lab NNTP-Posting-Host: stanford.edu X-Newsreader: TIN [version 1.2 PL2] Lines: 11 In article <1995Jan17.121325.5994@berkeley.edu>, jrodriguez@berkeley.edu (Joachim Rodríguez) writes: > Beware of System 7.5.1 memory leaks if you allocate large sample buffers in the application heap. Use NewPtrSys instead. Beware of System 7.5.1 memory leaks if you allocate large sample buffers in the application heap. Use NewPtrSys instead. Netscape 1.1 crashes when loading large preformatted text. Stick to rn or tin! -- Lucia Souza "They will send a copy in my place." Amiga 3000T / NEXTSTEP 3.3 From neriksson@pacbell.net Thu Jan 19 17:44:25 1995 Path: ashpoly!bigsur!pacrim!krgate!eunha!pacbell!neriksson From: neriksson@pacbell.net (Nadine Eriksson) Newsgroups: comp.sys.m68k Subject: Re: Observation: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Jan19.174425.8641@pacbell.net> Date: Thu, 19 Jan 1995 17:44:25 GMT References: <1995Jan16.132425.3303@kiae.su> <1995Jan17.105825.9955@mit.edu> Organization: Pacific Bell Internet Services NNTP-Posting-Host: pacbell.net X-Newsreader: TIN [version 1.2 PL2] Lines: 8 In article <1995Jan17.105825.9955@mit.edu>, lmoreau@mit.edu (Lisa Moreau) writes: > The 68040 on the Quadra is a monster -- the on-chip FPU executes FFT butterflies in less than 4 milliseconds. Mac users bragging about 6-minute render times while Unix workstations do it in 20 seconds. Classic Apple distortion field. -- Nadine Eriksson Tape trading list upon request. SASE required for international mail.