From jgarcia@pacbell.net Sat Apr 22 04:27:17 1995 Path: ashpoly!cascade!transat!eunet-fi!relcom!kiae!pacbell!jgarcia From: jgarcia@pacbell.net (Ji-woo García) Newsgroups: comp.sys.m68k Subject: [SPECULATION] Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Apr22.042717.4153@pacbell.net> Date: Sat, 22 Apr 1995 04:27:17 GMT Organization: Pacific Bell Internet Services NNTP-Posting-Host: pacbell.net 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. Total execution time for a 20-minute audio track dropped from 48 minutes to 6.2 minutes. Anyone running this on a Quadra 840AV with the 68040? -- Ji-woo García Opinions expressed are solely my own and not those of Pacific Bell Internet Services. ------------------------------------------------------------ From clee@pipeline.com Mon Apr 24 01:32:17 1995 Path: ashpoly!cascade!transat!eunet-fr!teletel!pipeline!clee From: clee@pipeline.com (Callum Lee) Newsgroups: comp.sys.m68k Subject: Re: [SPECULATION] Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Apr24.013217.8516@pipeline.com> Date: Mon, 24 Apr 1995 01:32:17 GMT References: <1995Apr22.042717.4153@pacbell.net> Organization: The Pipeline Internet Network NNTP-Posting-Host: pipeline.com X-Newsreader: Netscape 1.1N Lines: 10 In article <1995Apr22.042717.4153@pacbell.net>, jgarcia@pacbell.net (Ji-woo García) 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. Mac users bragging about 6-minute render times while Unix workstations do it in 20 seconds. Classic Apple distortion field. -- Callum Lee Opinions expressed are solely my own and not those of The Pipeline Internet Network. ------------------------------------------------------------ From vgirard@panix.com Tue Apr 25 19:11:17 1995 Path: ashpoly!bigsur!pacrim!jpgate!kamome!panix!vgirard From: vgirard@panix.com (Valeria Girard) Newsgroups: comp.sys.m68k Subject: Re: [SPECULATION] Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Apr25.191117.9881@panix.com> Date: Tue, 25 Apr 1995 19:11:17 GMT References: <1995Apr22.042717.4153@pacbell.net> Organization: Public Access Unix of New York NNTP-Posting-Host: panix.com X-Newsreader: NewsWatcher 2.0b24 Lines: 10 In article <1995Apr22.042717.4153@pacbell.net>, jgarcia@pacbell.net (Ji-woo García) 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. -- Valeria Girard Opinions expressed are solely my own and not those of Public Access Unix of New York. ------------------------------------------------------------ From civanov@stanford.edu Thu Apr 27 08:50:17 1995 Path: ashpoly!cascade!brgate!saturno!stanford!civanov From: civanov@stanford.edu (Camila Ivanov) Newsgroups: comp.sys.m68k Subject: Re: [SPECULATION] Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Apr27.085017.6857@stanford.edu> Date: Thu, 27 Apr 1995 08:50:17 GMT References: <1995Apr22.042717.4153@pacbell.net> <1995Apr24.013217.8516@pipeline.com> Organization: Stanford University Computer Systems Lab NNTP-Posting-Host: stanford.edu X-Newsreader: WinVN 0.99.5 Lines: 9 In article <1995Apr24.013217.8516@pipeline.com>, clee@pipeline.com (Callum Lee) writes: > Mac users bragging about 6-minute render times while Unix workstations do it in 20 seconds. Classic Apple distortion field. Beware of System 7.5.1 memory leaks if you allocate large sample buffers in the application heap. Use NewPtrSys instead. -- Camila Ivanov *PLONK* filter active for trolls. Amiga 1200 (Blizzard 030/50) - NetBSD 1.0