From msilva@unam.mx Sat Oct 21 02:45:37 1995 Path: ashpoly!cascade!transat!eunet-de!hansebox!unam!msilva From: msilva@unam.mx (Matthias Silva) Newsgroups: comp.sys.m68k Subject: WTB/WTT: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Oct21.024537.2885@unam.mx> Date: Sat, 21 Oct 1995 02:45:37 GMT Organization: Universidad Nacional Autónoma de México (DGSCA) NNTP-Posting-Host: unam.mx X-Newsreader: NewsWatcher 2.0b24 Lines: 11 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. Anyone running this on a Quadra 840AV with the 68040? -- Matthias Silva Hayes Optima 288 @ 28,800 bps "The hatch is open. Is anyone listening?" From hnilsson@pacbell.net Mon Oct 23 06:03:37 1995 Path: ashpoly!bigsur!pacrim!krgate!eunha!pacbell!hnilsson From: hnilsson@pacbell.net (Hugo Nilsson) Newsgroups: comp.sys.m68k Subject: Re: WTB/WTT: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Oct23.060337.2089@pacbell.net> Date: Mon, 23 Oct 1995 06:03:37 GMT References: <1995Oct21.024537.2885@unam.mx> Organization: Pacific Bell Internet Services NNTP-Posting-Host: pacbell.net X-Newsreader: WinVN 0.99.5 Lines: 12 In article <1995Oct21.024537.2885@unam.mx>, msilva@unam.mx (Matthias Silva) 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. Beware of System 7.5.1 memory leaks if you allocate large sample buffers in the application heap. Use NewPtrSys instead. Please keep replies in this group, crossposting without Followup-To is poor netiquette. -- Hugo Nilsson SupraFAXModem 28.8 @ 33,600 bps "5 sigma is a discovery. 7 is a question." From tkuznetsov@illinois.edu Wed Oct 25 00:56:37 1995 Path: ashpoly!cascade!transat!eunet-de!hansebox!illinois!tkuznetsov From: tkuznetsov@illinois.edu (Thiago Kuznetsov) Newsgroups: comp.sys.m68k Subject: Re: WTB/WTT: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Oct25.005637.7662@illinois.edu> Date: Wed, 25 Oct 1995 00:56:37 GMT References: <1995Oct21.024537.2885@unam.mx> <1995Oct23.060337.2089@pacbell.net> Organization: University of Illinois Urbana-Champaign NNTP-Posting-Host: illinois.edu X-Newsreader: WinVN 0.99.5 Lines: 10 In article <1995Oct23.060337.2089@pacbell.net>, hnilsson@pacbell.net (Hugo Nilsson) writes: > Beware of System 7.5.1 memory leaks if you allocate large sample buffers in the application heap. Use NewPtrSys instead. > Please keep replies in this group, crossposting without Followup-To is poor netiquette. Mac users bragging about 6-minute render times while Unix workstations do it in 20 seconds. Classic Apple distortion field. -- === Thiago Kuznetsov === Dept of Electrical Engineering, University of Illinois Urbana-Champaign "Hardware is temporary. The signal survives."