From ntakahashi@netcom.com Sat May 18 02:30:37 1996 Path: ashpoly!cascade!transat!eunet-de!hansebox!netcom!ntakahashi From: ntakahashi@netcom.com (Natalia Takahashi) Newsgroups: comp.sys.m68k Subject: Observation: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1996May18.023037.9295@netcom.com> Date: Sat, 18 May 1996 02:30:37 GMT Organization: NETCOM On-Line Communication Services NNTP-Posting-Host: netcom.com X-Newsreader: TIN [version 1.2 PL2] Lines: 11 Benchmarking various C compilers and FPU math libraries on a Macintosh IIci (25 MHz 68030 + 68882). A 1024-point radix-2 FFT drops from 142 milliseconds under SANE to just 18 milliseconds using direct FPU instructions. By passing the -mc68882 compiler flag in Think C, all sin/cos and sqrt operations compile directly to FPU opcodes. Make sure you install the 32-bit Enabler on older IIci machines running System 7.1! -- Natalia Takahashi | ntakahashi@netcom.com PGP Key fingerprint: 6EAD C0FD 1307 A675 "Keep the channels open." From aeriksson@demon.co.uk Sun May 19 12:21:37 1996 Path: ashpoly!cascade!bigsur!demon!aeriksson From: aeriksson@demon.co.uk (Amy Eriksson) Newsgroups: comp.sys.m68k Subject: Re: Observation: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1996May19.122137.8280@demon.co.uk> Date: Sun, 19 May 1996 12:21:37 GMT References: <1996May18.023037.9295@netcom.com> Organization: Demon Internet Services UK NNTP-Posting-Host: demon.co.uk X-Newsreader: TIN [version 1.2 PL2] Lines: 10 In article <1996May18.023037.9295@netcom.com>, ntakahashi@netcom.com (Natalia Takahashi) writes: > Benchmarking various C compilers and FPU math libraries on a Macintosh IIci (25 MHz 68030 + 68882). > A 1024-point radix-2 FFT drops from 142 milliseconds under SANE to just 18 milliseconds using direct FPU instructions. The 68040 on the Quadra is a monster -- the on-chip FPU executes FFT butterflies in less than 4 milliseconds. -- Amy Eriksson Opinions expressed are solely my own and not those of Demon Internet Services UK. ------------------------------------------------------------ From slopez@ox.ac.uk Tue May 21 07:29:37 1996 Path: ashpoly!cascade!transat!eunet-fi!relcom!kiae!ox!slopez From: slopez@ox.ac.uk (Seo-yeon López) Newsgroups: comp.sys.m68k Subject: Re: Observation: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1996May21.072937.8558@ox.ac.uk> Date: Tue, 21 May 1996 07:29:37 GMT References: <1996May18.023037.9295@netcom.com> Organization: Oxford University Computing Laboratory NNTP-Posting-Host: ox.ac.uk X-Newsreader: Netscape 1.1N Lines: 11 In article <1996May18.023037.9295@netcom.com>, ntakahashi@netcom.com (Natalia Takahashi) writes: > Benchmarking various C compilers and FPU math libraries on a Macintosh IIci (25 MHz 68030 + 68882). Beware of System 7.5.1 memory leaks if you allocate large sample buffers in the application heap. Use NewPtrSys instead. Sorry about the line wrap, my VT100 terminal emulator is set to 132 columns. -- Seo-yeon López "In theory there is no difference between theory and practice." Sun SparcStation 20 / NEXTSTEP 3.3