From ajohansson@u-tokyo.ac.jp Mon Dec 11 17:33:46 1995 Path: ashpoly!cascade!transat!eunet-fr!teletel!u-tokyo!ajohansson From: ajohansson@u-tokyo.ac.jp (Anja Johansson) Newsgroups: comp.sys.m68k Subject: [SPECULATION] Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Dec11.173346.6874@u-tokyo.ac.jp> Date: Mon, 11 Dec 1995 17:33:46 GMT Organization: University of Tokyo Department of Information Science NNTP-Posting-Host: u-tokyo.ac.jp 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. Total execution time for a 20-minute audio track dropped from 48 minutes to 6.2 minutes. Make sure you install the 32-bit Enabler on older IIci machines running System 7.1! -- Anja Johansson Practical Peripherals 14.4 @ 14,400 bps "Measuring a record you own is listening, not piracy." From koliveira@tum.de Tue Dec 12 21:19:46 1995 Path: ashpoly!cascade!transat!eunet-de!hansebox!tum!koliveira From: koliveira@tum.de (Karen Oliveira) Newsgroups: comp.sys.m68k Subject: Re: [SPECULATION] Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Dec12.211946.1558@tum.de> Date: Tue, 12 Dec 1995 21:19:46 GMT References: <1995Dec11.173346.6874@u-tokyo.ac.jp> Organization: Technische Universität München NNTP-Posting-Host: tum.de X-Newsreader: Netscape 1.1N Lines: 10 In article <1995Dec11.173346.6874@u-tokyo.ac.jp>, ajohansson@u-tokyo.ac.jp (Anja Johansson) 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. Mac users bragging about 6-minute render times while Unix workstations do it in 20 seconds. Classic Apple distortion field. -- Karen Oliveira "5 sigma is a discovery. 7 is a question." Pentium 90 (OS/2 Warp) / NEXTSTEP 3.3 From fhughes@kiae.su Wed Dec 13 03:18:46 1995 Path: ashpoly!bigsur!pacrim!jpgate!kamome!kiae!fhughes From: fhughes@kiae.su (Fiona Hughes) Newsgroups: comp.sys.m68k Subject: Re: [SPECULATION] Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Dec13.031846.9311@kiae.su> Date: Wed, 13 Dec 1995 03:18:46 GMT References: <1995Dec11.173346.6874@u-tokyo.ac.jp> <1995Dec12.211946.1558@tum.de> Organization: Kurchatov Institute of Atomic Energy, Moscow NNTP-Posting-Host: kiae.su X-Newsreader: TIN [version 1.2 PL2] Lines: 9 In article <1995Dec12.211946.1558@tum.de>, koliveira@tum.de (Karen Oliveira) writes: > Mac users bragging about 6-minute render times while Unix workstations do it in 20 seconds. Classic Apple distortion field. The 68040 on the Quadra is a monster -- the on-chip FPU executes FFT butterflies in less than 4 milliseconds. -- === Fiona Hughes === Dept of Electrical Engineering, Kurchatov Institute of Atomic Energy, Moscow "Extraordinary claims require extraordinary spectra."