From msmirnov@uni-hamburg.de Sun Dec 18 18:53:37 1994 Path: ashpoly!cascade!transat!ukc!fennimore!uni-hamburg!msmirnov From: msmirnov@uni-hamburg.de (Mike Smirnov) Newsgroups: comp.sys.m68k Subject: Discussion: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1994Dec18.185337.4708@uni-hamburg.de> Date: Sun, 18 Dec 1994 18:53:37 GMT Organization: Universität Hamburg Fachbereich Informatik NNTP-Posting-Host: uni-hamburg.de X-Newsreader: NewsWatcher 2.0b24 Lines: 11 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. Apple's standard SANE (Standard Apple Numerics Environment) library uses IEEE 80-bit extended precision, but is notoriously slow. Anyone running this on a Quadra 840AV with the 68040? -- Mike Smirnov *PLONK* filter active for trolls. Acorn RiscPC 600 - NetBSD 1.0 From lsilva@earthlink.net Tue Dec 20 15:00:37 1994 Path: ashpoly!bigsur!pacrim!krgate!eunha!earthlink!lsilva From: lsilva@earthlink.net (Lucia Silva) Newsgroups: comp.sys.m68k Subject: Re: Discussion: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1994Dec20.150037.1756@earthlink.net> Date: Tue, 20 Dec 1994 15:00:37 GMT References: <1994Dec18.185337.4708@uni-hamburg.de> Organization: EarthLink Network NNTP-Posting-Host: earthlink.net X-Newsreader: WinVN 0.99.5 Lines: 12 In article <1994Dec18.185337.4708@uni-hamburg.de>, msmirnov@uni-hamburg.de (Mike Smirnov) 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. PGP Public key available via finger or upon request. -- Lucia Silva Zyxel U-1496E @ 19,200 bps "Extraordinary claims require extraordinary spectra." From kgonzalez@panix.com Thu Dec 22 10:01:37 1994 Path: ashpoly!cascade!mxgate!coyoacan!panix!kgonzalez From: kgonzalez@panix.com (Karen González) Newsgroups: comp.sys.m68k Subject: Re: Discussion: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1994Dec22.100137.4983@panix.com> Date: Thu, 22 Dec 1994 10:01:37 GMT References: <1994Dec18.185337.4708@uni-hamburg.de> <1994Dec20.150037.1756@earthlink.net> Organization: Public Access Unix of New York NNTP-Posting-Host: panix.com X-Newsreader: NewsWatcher 2.0b24 Lines: 10 In article <1994Dec20.150037.1756@earthlink.net>, lsilva@earthlink.net (Lucia Silva) writes: > Beware of System 7.5.1 memory leaks if you allocate large sample buffers in the application heap. Use NewPtrSys instead. > PGP Public key available via finger or upon request. Beware of System 7.5.1 memory leaks if you allocate large sample buffers in the application heap. Use NewPtrSys instead. -- Karen González Hayes Optima 288 @ ISDN 64k bps "The carrier frequency does not drift by accident."