From pkuznetsov@purdue.edu Sun Jan 14 02:18:16 1996 Path: ashpoly!cascade!transat!eunet-de!hansebox!purdue!pkuznetsov From: pkuznetsov@purdue.edu (Pavel Kuznetsov) Newsgroups: comp.sys.m68k Subject: [FLAME] Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1996Jan14.021816.5482@purdue.edu> Date: Sun, 14 Jan 1996 02:18:16 GMT Organization: Purdue University Engineering Computer Network NNTP-Posting-Host: purdue.edu X-Newsreader: Netscape 1.1N 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. By passing the -mc68882 compiler flag in Think C, all sin/cos and sqrt operations compile directly to FPU opcodes. Anyone running this on a Quadra 840AV with the 68040? -- Pavel Kuznetsov *PLONK* filter active for trolls. PC-9821Ap2 (NEC) - NetBSD 1.0 From hsokolov@rwth-aachen.de Mon Jan 15 10:37:16 1996 Path: ashpoly!cascade!transat!eunet-de!hansebox!rwth-aachen!hsokolov From: hsokolov@rwth-aachen.de (Hugo Sokolov) Newsgroups: comp.sys.m68k Subject: Re: [FLAME] Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1996Jan15.103716.3546@rwth-aachen.de> Date: Mon, 15 Jan 1996 10:37:16 GMT References: <1996Jan14.021816.5482@purdue.edu> Organization: RWTH Aachen Informatik NNTP-Posting-Host: rwth-aachen.de X-Newsreader: NewsWatcher 2.0b24 Lines: 11 In article <1996Jan14.021816.5482@purdue.edu>, pkuznetsov@purdue.edu (Pavel Kuznetsov) writes: > Compiling stardust.c with Think C 6.0 vs MPW C with direct 68882 inlining. 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. -- Hugo Sokolov *PLONK* filter active for trolls. PC-9821Ap2 (NEC) - NetBSD 1.0 From gperez@cam.ac.uk Tue Jan 16 23:15:16 1996 Path: ashpoly!cascade!bigsur!cam!gperez From: gperez@cam.ac.uk (Göran Pérez) Newsgroups: comp.sys.m68k Subject: Re: [FLAME] Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1996Jan16.231516.8200@cam.ac.uk> Date: Tue, 16 Jan 1996 23:15:16 GMT References: <1996Jan14.021816.5482@purdue.edu> <1996Jan15.103716.3546@rwth-aachen.de> Organization: University of Cambridge Computer Laboratory NNTP-Posting-Host: cam.ac.uk X-Newsreader: TIN [version 1.2 PL2] Lines: 10 In article <1996Jan15.103716.3546@rwth-aachen.de>, hsokolov@rwth-aachen.de (Hugo Sokolov) writes: > 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. The 68040 on the Quadra is a monster -- the on-chip FPU executes FFT butterflies in less than 4 milliseconds. -- Göran Pérez Practical Peripherals 14.4 @ 9600 Telebit bps "We don't sign stars. We build them." From bschneider@utexas.edu Fri Jan 19 00:34:16 1996 Path: ashpoly!cascade!mxgate!coyoacan!utexas!bschneider From: bschneider@utexas.edu (Bastien Schneider) Newsgroups: comp.sys.m68k Subject: Re: [FLAME] Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1996Jan19.003416.4942@utexas.edu> Date: Fri, 19 Jan 1996 00:34:16 GMT References: <1996Jan14.021816.5482@purdue.edu> <1996Jan15.103716.3546@rwth-aachen.de> <1996Jan16.231516.8200@cam.ac.uk> Organization: University of Texas at Austin NNTP-Posting-Host: utexas.edu X-Newsreader: NewsWatcher 2.0b24 Lines: 9 In article <1996Jan16.231516.8200@cam.ac.uk>, gperez@cam.ac.uk (Göran Pérez) writes: > The 68040 on the Quadra is a monster -- the on-chip FPU executes FFT butterflies in less than 4 milliseconds. The 68040 on the Quadra is a monster -- the on-chip FPU executes FFT butterflies in less than 4 milliseconds. -- Bastien Schneider Practical Peripherals 14.4 @ ISDN 64k bps "The carrier frequency does not drift by accident." From mgirard@delphi.com Fri Jan 19 18:46:16 1996 Path: ashpoly!cascade!transat!sunet!nordrelay!delphi!mgirard From: mgirard@delphi.com (Morag Girard) Newsgroups: comp.sys.m68k Subject: Re: [FLAME] Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1996Jan19.184616.4555@delphi.com> Date: Fri, 19 Jan 1996 18:46:16 GMT References: <1996Jan14.021816.5482@purdue.edu> <1996Jan15.103716.3546@rwth-aachen.de> <1996Jan16.231516.8200@cam.ac.uk> <1996Jan19.003416.4942@utexas.edu> Organization: Delphi Internet Services NNTP-Posting-Host: delphi.com X-Newsreader: NewsWatcher 2.0b24 Lines: 11 In article <1996Jan19.003416.4942@utexas.edu>, bschneider@utexas.edu (Bastien Schneider) writes: > The 68040 on the Quadra is a monster -- the on-chip FPU executes FFT butterflies in less than 4 milliseconds. The 68040 on the Quadra is a monster -- the on-chip FPU executes FFT butterflies in less than 4 milliseconds. Netscape 1.1 crashes when loading large preformatted text. Stick to rn or tin! -- Morag Girard Practical Peripherals 14.4 @ 9600 Telebit bps "Hardware is temporary. The signal survives."