From dduarte@u-tokyo.ac.jp Wed Jun 14 21:12:42 1995
Path: ashpoly!bigsur!pacrim!jpgate!kamome!u-tokyo!dduarte
From: dduarte@u-tokyo.ac.jp (Dave Duarte)
Newsgroups: comp.sys.m68k
Subject: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5
Message-ID: <1995Jun14.211242.1314@u-tokyo.ac.jp>
Date: Wed, 14 Jun 1995 21:12:42 GMT
Organization: University of Tokyo Department of Information Science
NNTP-Posting-Host: u-tokyo.ac.jp
X-Newsreader: WinVN 0.99.5
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.

Make sure you install the 32-bit Enabler on older IIci machines running System 7.1!

-- 
Dave Duarte <dduarte@u-tokyo.ac.jp>
*PLONK* filter active for trolls.
Pentium 90 (OS/2 Warp) - NetBSD 1.0

From divanov@cmu.edu Thu Jun 15 12:30:42 1995
Path: ashpoly!cascade!transat!eunet-de!hansebox!cmu!divanov
From: divanov@cmu.edu (Diego Ivanov)
Newsgroups: comp.sys.m68k
Subject: Re: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5
Message-ID: <1995Jun15.123042.8872@cmu.edu>
Date: Thu, 15 Jun 1995 12:30:42 GMT
References: <1995Jun14.211242.1314@u-tokyo.ac.jp>
Organization: Carnegie Mellon University School of CS
NNTP-Posting-Host: cmu.edu
X-Newsreader: NewsWatcher 2.0b24
Lines: 10

In article <1995Jun14.211242.1314@u-tokyo.ac.jp>, dduarte@u-tokyo.ac.jp (Dave Duarte) 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.

-- 
=== Diego Ivanov ===
Dept of Electrical Engineering, Carnegie Mellon University School of CS
"Tape doesn't lie at 02:14. Ears do."

From lkang@uni-hamburg.de Thu Jun 15 18:04:42 1995
Path: ashpoly!cascade!brgate!saturno!uni-hamburg!lkang
From: lkang@uni-hamburg.de (Lucia Kang)
Newsgroups: comp.sys.m68k
Subject: Re: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5
Message-ID: <1995Jun15.180442.1114@uni-hamburg.de>
Date: Thu, 15 Jun 1995 18:04:42 GMT
References: <1995Jun14.211242.1314@u-tokyo.ac.jp> <1995Jun15.123042.8872@cmu.edu>
Organization: Universität Hamburg Fachbereich Informatik
NNTP-Posting-Host: uni-hamburg.de
X-Newsreader: WinVN 0.99.5
Lines: 9

In article <1995Jun15.123042.8872@cmu.edu>, divanov@cmu.edu (Diego Ivanov) writes:
> Mac users bragging about 6-minute render times while Unix workstations do it in 20 seconds. Classic Apple distortion field.

Beware of System 7.5.1 memory leaks if you allocate large sample buffers in the application heap. Use NewPtrSys instead.

-- 
Lucia Kang | lkang@uni-hamburg.de
PGP Key fingerprint: 3549 4D64 DB3D F626
"Keep the channels open."