From owner-freebsd-hackers Sat Aug 1 05:37:42 1998 Return-Path: Received: (from majordom@localhost) by hub.freebsd.org (8.8.8/8.8.8) id FAA10085 for freebsd-hackers-outgoing; Sat, 1 Aug 1998 05:37:42 -0700 (PDT) (envelope-from owner-freebsd-hackers@FreeBSD.ORG) Received: from freefall.pipeline.ch (freefall.pipeline.ch [195.134.128.40]) by hub.freebsd.org (8.8.8/8.8.8) with ESMTP id FAA10080 for ; Sat, 1 Aug 1998 05:37:40 -0700 (PDT) (envelope-from andre@pipeline.ch) Received: from pipeline.ch ([195.134.140.5]) by freefall.pipeline.ch (Netscape Mail Server v2.02) with ESMTP id AAA200; Sat, 1 Aug 1998 14:36:03 +0200 Message-ID: <35C30C0E.62EFC375@pipeline.ch> Date: Sat, 01 Aug 1998 14:37:34 +0200 From: "IBS / Andre Oppermann" Organization: Internet Business Solutions Ltd. X-Mailer: Mozilla 4.03 [en] (Win95; I) MIME-Version: 1.0 To: Stephen Hocking-Senior Programmer PGS Tensor Perth CC: hackers@FreeBSD.ORG Subject: Re: Fast FFT routines with source? References: <199808010637.OAA04884@ariadne.tensor.pgs.com> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Sender: owner-freebsd-hackers@FreeBSD.ORG Precedence: bulk X-Loop: FreeBSD.ORG Stephen Hocking-Senior Programmer PGS Tensor Perth wrote: > > I'm part way through porting this company's seismic data processing code to > FreeBSD and have got most things sorted out except for the fact that there > doesn't seem to be any carefully optimised fft routines available. I do have > the fftpack as found in ports, but I was wondering if there was anything > faster than taht available with source. You might take a look at: ftp://koobera.math.uic.edu/www/djbfft.html "djbfft is the fastest available code for small power-of-2 complex DFTs on a Pentium" "Current record for 256-point double-precision complex FFT: 18272 Pentium cycle" -- Andre To Unsubscribe: send mail to majordomo@FreeBSD.org with "unsubscribe freebsd-hackers" in the body of the message