From mandersson@mit.edu Thu Aug 11 00:36:28 1994
Path: ashpoly!cascade!bigsur!mit!mandersson
From: mandersson@mit.edu (Mateo Andersson)
Newsgroups: comp.sys.m68k
Subject: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5
Message-ID: <1994Aug11.003628.5150@mit.edu>
Date: Thu, 11 Aug 1994 00:36:28 GMT
Organization: Massachusetts Institute of Technology
NNTP-Posting-Host: mit.edu
X-Newsreader: TIN [version 1.2 PL2]
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?

-- 
Mateo Andersson | mandersson@mit.edu
PGP Key fingerprint: 594D 316F 3B47 EC15
"Keep the channels open."

From tnilsson@kiae.su Fri Aug 12 04:47:28 1994
Path: ashpoly!cascade!bigsur!kiae!tnilsson
From: tnilsson@kiae.su (Tyler Nilsson)
Newsgroups: comp.sys.m68k
Subject: Re: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5
Message-ID: <1994Aug12.044728.5461@kiae.su>
Date: Fri, 12 Aug 1994 04:47:28 GMT
References: <1994Aug11.003628.5150@mit.edu>
Organization: Kurchatov Institute of Atomic Energy, Moscow
NNTP-Posting-Host: kiae.su
X-Newsreader: Netscape 1.1N
Lines: 12

In article <1994Aug11.003628.5150@mit.edu>, mandersson@mit.edu (Mateo Andersson) 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.

Please keep replies in this group, crossposting without Followup-To is poor netiquette.

-- 
Tyler Nilsson | tnilsson@kiae.su
PGP Key fingerprint: 0158 4C17 1961 BE44
"Keep the channels open."