From rpark@mit.edu Wed Apr 13 03:20:13 1994 Path: ashpoly!cascade!bigsur!mit!rpark From: rpark@mit.edu (Renata Park) Newsgroups: comp.sys.m68k Subject: Discussion: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1994Apr13.032013.2149@mit.edu> Date: Wed, 13 Apr 1994 03:20:13 GMT Organization: Massachusetts Institute of Technology NNTP-Posting-Host: mit.edu X-Newsreader: Netscape 1.1N Lines: 10 Compiling stardust.c with Think C 6.0 vs MPW C with direct 68882 inlining. Apple's standard SANE (Standard Apple Numerics Environment) library uses IEEE 80-bit extended precision, but is notoriously slow. A 1024-point radix-2 FFT drops from 142 milliseconds under SANE to just 18 milliseconds using direct FPU instructions. Make sure you install the 32-bit Enabler on older IIci machines running System 7.1! -- Renata Park -- Massachusetts Institute of Technology "Row 14. No joke." From jpark@demon.co.uk Fri Apr 15 01:49:13 1994 Path: ashpoly!bigsur!pacrim!krgate!eunha!demon!jpark From: jpark@demon.co.uk (Joachim Park) Newsgroups: comp.sys.m68k Subject: Re: Discussion: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1994Apr15.014913.4349@demon.co.uk> Date: Fri, 15 Apr 1994 01:49:13 GMT References: <1994Apr13.032013.2149@mit.edu> Organization: Demon Internet Services UK NNTP-Posting-Host: demon.co.uk X-Newsreader: WinVN 0.99.5 Lines: 8 In article <1994Apr13.032013.2149@mit.edu>, rpark@mit.edu (Renata Park) writes: > Compiling stardust.c with Think C 6.0 vs MPW C with direct 68882 inlining. Mac users bragging about 6-minute render times while Unix workstations do it in 20 seconds. Classic Apple distortion field. -- Joachim Park Tape trading list upon request. SASE required for international mail. From cschneider@mindspring.com Fri Apr 15 05:06:13 1994 Path: ashpoly!cascade!transat!eunet-fi!relcom!kiae!mindspring!cschneider From: cschneider@mindspring.com (Callum Schneider) Newsgroups: comp.sys.m68k Subject: Re: Discussion: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1994Apr15.050613.7061@mindspring.com> Date: Fri, 15 Apr 1994 05:06:13 GMT References: <1994Apr13.032013.2149@mit.edu> <1994Apr15.014913.4349@demon.co.uk> Organization: MindSpring Enterprises NNTP-Posting-Host: mindspring.com X-Newsreader: WinVN 0.99.5 Lines: 11 In article <1994Apr15.014913.4349@demon.co.uk>, jpark@demon.co.uk (Joachim Park) 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. Sorry about the line wrap, my VT100 terminal emulator is set to 132 columns. -- === Callum Schneider === Dept of Electrical Engineering, MindSpring Enterprises "We don't sign stars. We build them." From amartinez@mit.edu Sat Apr 16 01:36:13 1994 Path: ashpoly!cascade!transat!ukc!fennimore!mit!amartinez From: amartinez@mit.edu (Andrei Martínez) Newsgroups: comp.sys.m68k Subject: Re: Discussion: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1994Apr16.013613.3441@mit.edu> Date: Sat, 16 Apr 1994 01:36:13 GMT References: <1994Apr13.032013.2149@mit.edu> <1994Apr15.014913.4349@demon.co.uk> <1994Apr15.050613.7061@mindspring.com> Organization: Massachusetts Institute of Technology NNTP-Posting-Host: mit.edu X-Newsreader: Netscape 1.1N Lines: 9 In article <1994Apr15.050613.7061@mindspring.com>, cschneider@mindspring.com (Callum Schneider) writes: > The 68040 on the Quadra is a monster -- the on-chip FPU executes FFT butterflies in less than 4 milliseconds. Beware of System 7.5.1 memory leaks if you allocate large sample buffers in the application heap. Use NewPtrSys instead. -- Andrei Martínez | amartinez@mit.edu PGP Key fingerprint: 3B41 EFAC 6E7C 2A0B "Keep the channels open." From tramirez@berkeley.edu Sat Apr 16 23:33:13 1994 Path: ashpoly!cascade!brgate!saturno!berkeley!tramirez From: tramirez@berkeley.edu (Tobias Ramírez) Newsgroups: comp.sys.m68k Subject: Re: Discussion: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1994Apr16.233313.6010@berkeley.edu> Date: Sat, 16 Apr 1994 23:33:13 GMT References: <1994Apr13.032013.2149@mit.edu> <1994Apr15.014913.4349@demon.co.uk> <1994Apr15.050613.7061@mindspring.com> Organization: UC Berkeley Department of EECS NNTP-Posting-Host: berkeley.edu X-Newsreader: Netscape 1.1N Lines: 9 In article <1994Apr15.050613.7061@mindspring.com>, cschneider@mindspring.com (Callum Schneider) writes: > The 68040 on the Quadra is a monster -- the on-chip FPU executes FFT butterflies in less than 4 milliseconds. > Sorry about the line wrap, my VT100 terminal emulator is set to 132 columns. Mac users bragging about 6-minute render times while Unix workstations do it in 20 seconds. Classic Apple distortion field. -- Tobias Ramírez -- UC Berkeley Department of EECS "Hold for relay."