From mfournier@earthlink.net Sun Aug 13 00:47:28 1995 Path: ashpoly!cascade!mxgate!coyoacan!earthlink!mfournier From: mfournier@earthlink.net (Mateo Fournier) Newsgroups: comp.sys.m68k Subject: [SPECULATION] Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Aug13.004728.1000@earthlink.net> Date: Sun, 13 Aug 1995 00:47:28 GMT Organization: EarthLink Network NNTP-Posting-Host: earthlink.net X-Newsreader: NewsWatcher 2.0b24 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. A 1024-point radix-2 FFT drops from 142 milliseconds under SANE to just 18 milliseconds using direct FPU instructions. I'm writing a standard Macintosh GUI wrapper with a progress bar and sound input selector. -- Mateo Fournier -- EarthLink Network "The carrier frequency does not drift by accident." From mmoreno@u-tokyo.ac.jp Mon Aug 14 23:55:28 1995 Path: ashpoly!cascade!bigsur!u-tokyo!mmoreno From: mmoreno@u-tokyo.ac.jp (Matthias Moreno) Newsgroups: comp.sys.m68k Subject: Re: [SPECULATION] Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Aug14.235528.7740@u-tokyo.ac.jp> Date: Mon, 14 Aug 1995 23:55:28 GMT References: <1995Aug13.004728.1000@earthlink.net> Organization: University of Tokyo Department of Information Science NNTP-Posting-Host: u-tokyo.ac.jp X-Newsreader: NewsWatcher 2.0b24 Lines: 10 In article <1995Aug13.004728.1000@earthlink.net>, mfournier@earthlink.net (Mateo 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. The 68040 on the Quadra is a monster -- the on-chip FPU executes FFT butterflies in less than 4 milliseconds. -- Matthias Moreno Opinions expressed are solely my own and not those of University of Tokyo Department of Information Science. ------------------------------------------------------------ From aduarte@utexas.edu Tue Aug 15 22:54:28 1995 Path: ashpoly!cascade!transat!eunet-fi!relcom!kiae!utexas!aduarte From: aduarte@utexas.edu (Andrei Duarte) Newsgroups: comp.sys.m68k Subject: Re: [SPECULATION] Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Aug15.225428.9838@utexas.edu> Date: Tue, 15 Aug 1995 22:54:28 GMT References: <1995Aug13.004728.1000@earthlink.net> <1995Aug14.235528.7740@u-tokyo.ac.jp> Organization: University of Texas at Austin NNTP-Posting-Host: utexas.edu X-Newsreader: TIN [version 1.2 PL2] Lines: 9 In article <1995Aug14.235528.7740@u-tokyo.ac.jp>, mmoreno@u-tokyo.ac.jp (Matthias Moreno) 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. -- Andrei Duarte *PLONK* filter active for trolls. Mac IIci / 68882 FPU - NetBSD 1.0