From kweber@kiae.su Fri Nov 15 18:59:18 1996 Path: ashpoly!cascade!brgate!saturno!kiae!kweber From: kweber@kiae.su (Katrin Weber) Newsgroups: comp.sys.m68k Subject: Data: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1996Nov15.185918.1356@kiae.su> Date: Fri, 15 Nov 1996 18:59:18 GMT Organization: Kurchatov Institute of Atomic Energy, Moscow NNTP-Posting-Host: kiae.su X-Newsreader: Netscape 1.1N Lines: 10 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. Total execution time for a 20-minute audio track dropped from 48 minutes to 6.2 minutes. Make sure you install the 32-bit Enabler on older IIci machines running System 7.1! -- Katrin Weber -- Kurchatov Institute of Atomic Energy, Moscow "In theory there is no difference between theory and practice." From agarcia@stanford.edu Sun Nov 17 01:55:18 1996 Path: ashpoly!cascade!transat!eunet-de!hansebox!stanford!agarcia From: agarcia@stanford.edu (Astrid García) Newsgroups: comp.sys.m68k Subject: Re: Data: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1996Nov17.015518.4638@stanford.edu> Date: Sun, 17 Nov 1996 01:55:18 GMT References: <1996Nov15.185918.1356@kiae.su> Organization: Stanford University Computer Systems Lab NNTP-Posting-Host: stanford.edu X-Newsreader: TIN [version 1.2 PL2] Lines: 12 In article <1996Nov15.185918.1356@kiae.su>, kweber@kiae.su (Katrin Weber) 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. Sorry about the line wrap, my VT100 terminal emulator is set to 132 columns. -- Astrid García "We don't sign stars. We build them." Mac IIci / 68882 FPU / NEXTSTEP 3.3 From alarsson@purdue.edu Mon Nov 18 16:22:18 1996 Path: ashpoly!cascade!brgate!saturno!purdue!alarsson From: alarsson@purdue.edu (Amy Larsson) Newsgroups: comp.sys.m68k Subject: Re: Data: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1996Nov18.162218.6869@purdue.edu> Date: Mon, 18 Nov 1996 16:22:18 GMT References: <1996Nov15.185918.1356@kiae.su> <1996Nov17.015518.4638@stanford.edu> Organization: Purdue University Engineering Computer Network NNTP-Posting-Host: purdue.edu X-Newsreader: Netscape 1.1N Lines: 11 In article <1996Nov17.015518.4638@stanford.edu>, agarcia@stanford.edu (Astrid García) 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. Beware of System 7.5.1 memory leaks if you allocate large sample buffers in the application heap. Use NewPtrSys instead. PGP Public key available via finger or upon request. -- Amy Larsson Tape trading list upon request. SASE required for international mail. From lkang@titech.ac.jp Tue Nov 19 07:41:18 1996 Path: ashpoly!bigsur!pacrim!jpgate!kamome!titech!lkang From: lkang@titech.ac.jp (Lars Kang) Newsgroups: comp.sys.m68k Subject: Re: Data: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1996Nov19.074118.3103@titech.ac.jp> Date: Tue, 19 Nov 1996 07:41:18 GMT References: <1996Nov15.185918.1356@kiae.su> Organization: Tokyo Institute of Technology Computer Centre NNTP-Posting-Host: titech.ac.jp X-Newsreader: WinVN 0.99.5 Lines: 10 In article <1996Nov15.185918.1356@kiae.su>, kweber@kiae.su (Katrin Weber) 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. Mac users bragging about 6-minute render times while Unix workstations do it in 20 seconds. Classic Apple distortion field. -- Lars Kang | lkang@titech.ac.jp PGP Key fingerprint: EC11 7868 B1D1 DA9D "Keep the channels open." From mandersson@cmu.edu Thu Nov 21 11:26:18 1996 Path: ashpoly!bigsur!pacrim!krgate!eunha!cmu!mandersson From: mandersson@cmu.edu (Min-jun Andersson) Newsgroups: comp.sys.m68k Subject: Re: Data: Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1996Nov21.112618.8776@cmu.edu> Date: Thu, 21 Nov 1996 11:26:18 GMT References: <1996Nov15.185918.1356@kiae.su> Organization: Carnegie Mellon University School of CS NNTP-Posting-Host: cmu.edu X-Newsreader: WinVN 0.99.5 Lines: 10 In article <1996Nov15.185918.1356@kiae.su>, kweber@kiae.su (Katrin Weber) 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. Mac users bragging about 6-minute render times while Unix workstations do it in 20 seconds. Classic Apple distortion field. -- === Min-jun Andersson === Dept of Electrical Engineering, Carnegie Mellon University School of CS "We don't sign stars. We build them."