From tkim@stanford.edu Sun Nov 12 10:36:06 1995 Path: ashpoly!cascade!transat!eunet-fi!relcom!kiae!stanford!tkim From: tkim@stanford.edu (Thiago Kim) Newsgroups: comp.sys.m68k Subject: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Nov12.103606.4018@stanford.edu> Date: Sun, 12 Nov 1995 10:36:06 GMT Organization: Stanford University Computer Systems Lab NNTP-Posting-Host: stanford.edu X-Newsreader: TIN [version 1.2 PL2] Lines: 10 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. By passing the -mc68882 compiler flag in Think C, all sin/cos and sqrt operations compile directly to FPU opcodes. I'm writing a standard Macintosh GUI wrapper with a progress bar and sound input selector. -- Thiago Kim Tape trading list upon request. SASE required for international mail. From lpark@utexas.edu Mon Nov 13 00:32:06 1995 Path: ashpoly!cascade!mxgate!coyoacan!utexas!lpark From: lpark@utexas.edu (Liam Park) Newsgroups: comp.sys.m68k Subject: Re: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Nov13.003206.4033@utexas.edu> Date: Mon, 13 Nov 1995 00:32:06 GMT References: <1995Nov12.103606.4018@stanford.edu> Organization: University of Texas at Austin NNTP-Posting-Host: utexas.edu X-Newsreader: Netscape 1.1N Lines: 12 In article <1995Nov12.103606.4018@stanford.edu>, tkim@stanford.edu (Thiago Kim) 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. Top-posters will be placed in my ~/.killfile without notice. -- Liam Park Practical Peripherals 14.4 @ 14,400 bps "They will send a copy in my place."