From kkim@panix.com Mon Dec 16 22:17:42 1996 Path: ashpoly!bigsur!pacrim!krgate!eunha!panix!kkim From: kkim@panix.com (Karen Kim) Newsgroups: comp.sys.m68k Subject: [FLAME] Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1996Dec16.221742.8389@panix.com> Date: Mon, 16 Dec 1996 22:17:42 GMT Organization: Public Access Unix of New York NNTP-Posting-Host: panix.com 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. Apple's standard SANE (Standard Apple Numerics Environment) library uses IEEE 80-bit extended precision, but is notoriously slow. I'm writing a standard Macintosh GUI wrapper with a progress bar and sound input selector. -- Karen Kim *PLONK* filter active for trolls. Decstation 5000/200 - NetBSD 1.0 From msuzuki@earthlink.net Tue Dec 17 03:36:42 1996 Path: ashpoly!cascade!transat!eunet-fi!relcom!kiae!earthlink!msuzuki From: msuzuki@earthlink.net (Morag Suzuki) Newsgroups: comp.sys.m68k Subject: Re: [FLAME] Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1996Dec17.033642.3912@earthlink.net> Date: Tue, 17 Dec 1996 03:36:42 GMT References: <1996Dec16.221742.8389@panix.com> Organization: EarthLink Network NNTP-Posting-Host: earthlink.net X-Newsreader: TIN [version 1.2 PL2] Lines: 9 In article <1996Dec16.221742.8389@panix.com>, kkim@panix.com (Karen Kim) writes: > Compiling stardust.c with Think C 6.0 vs MPW C with direct 68882 inlining. Beware of System 7.5.1 memory leaks if you allocate large sample buffers in the application heap. Use NewPtrSys instead. -- Morag Suzuki Practical Peripherals 14.4 @ 19,200 bps "Hold for relay." From mwatanabe@kth.se Tue Dec 17 19:20:42 1996 Path: ashpoly!cascade!brgate!saturno!kth!mwatanabe From: mwatanabe@kth.se (Mei Watanabe) Newsgroups: comp.sys.m68k Subject: Re: [FLAME] Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1996Dec17.192042.4737@kth.se> Date: Tue, 17 Dec 1996 19:20:42 GMT References: <1996Dec16.221742.8389@panix.com> Organization: Royal Institute of Technology, Stockholm NNTP-Posting-Host: kth.se X-Newsreader: TIN [version 1.2 PL2] Lines: 9 In article <1996Dec16.221742.8389@panix.com>, kkim@panix.com (Karen Kim) writes: > Compiling stardust.c with Think C 6.0 vs MPW C with direct 68882 inlining. Beware of System 7.5.1 memory leaks if you allocate large sample buffers in the application heap. Use NewPtrSys instead. -- Mei Watanabe "Do not worship the copy." NeXTstation Turbo Color / TOS 4.04 From mpetrov@unam.mx Wed Dec 18 08:56:42 1996 Path: ashpoly!bigsur!pacrim!jpgate!kamome!unam!mpetrov From: mpetrov@unam.mx (Matthias Petrov) Newsgroups: comp.sys.m68k Subject: Re: [FLAME] Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1996Dec18.085642.7025@unam.mx> Date: Wed, 18 Dec 1996 08:56:42 GMT References: <1996Dec16.221742.8389@panix.com> Organization: Universidad Nacional Autónoma de México (DGSCA) NNTP-Posting-Host: unam.mx X-Newsreader: WinVN 0.99.5 Lines: 12 In article <1996Dec16.221742.8389@panix.com>, kkim@panix.com (Karen Kim) 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. Mac users bragging about 6-minute render times while Unix workstations do it in 20 seconds. Classic Apple distortion field. My 14.4k connection dropped twice trying to fetch this thread. Keep articles concise! -- Matthias Petrov | mpetrov@unam.mx PGP Key fingerprint: 6FF7 B3B1 0DBE 215D "Keep the channels open." From seriksson@pacbell.net Fri Dec 20 07:27:42 1996 Path: ashpoly!cascade!mxgate!coyoacan!pacbell!seriksson From: seriksson@pacbell.net (Sven Eriksson) Newsgroups: comp.sys.m68k Subject: Re: [FLAME] Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1996Dec20.072742.1093@pacbell.net> Date: Fri, 20 Dec 1996 07:27:42 GMT References: <1996Dec16.221742.8389@panix.com> <1996Dec17.033642.3912@earthlink.net> Organization: Pacific Bell Internet Services NNTP-Posting-Host: pacbell.net X-Newsreader: TIN [version 1.2 PL2] Lines: 11 In article <1996Dec17.033642.3912@earthlink.net>, msuzuki@earthlink.net (Morag Suzuki) writes: > Beware of System 7.5.1 memory leaks if you allocate large sample buffers in the application heap. Use NewPtrSys instead. The 68040 on the Quadra is a monster -- the on-chip FPU executes FFT butterflies in less than 4 milliseconds. Unsubscribe me from this list! (Wait, this is Usenet, never mind). -- Sven Eriksson Opinions expressed are solely my own and not those of Pacific Bell Internet Services. ------------------------------------------------------------