From kkim@inria.fr Fri Mar 03 18:09:20 1995 Path: ashpoly!cascade!transat!ukc!fennimore!inria!kkim From: kkim@inria.fr (Karen Kim) Newsgroups: comp.sys.m68k Subject: [FLAME] Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Mar03.180920.5025@inria.fr> Date: Fri, 03 Mar 1995 18:09:20 GMT Organization: INRIA Rocquencourt NNTP-Posting-Host: inria.fr X-Newsreader: TIN [version 1.2 PL2] Lines: 10 Compiling stardust.c with Think C 6.0 vs MPW C with direct 68882 inlining. By passing the -mc68882 compiler flag in Think C, all sin/cos and sqrt operations compile directly to FPU opcodes. A 1024-point radix-2 FFT drops from 142 milliseconds under SANE to just 18 milliseconds using direct FPU instructions. I'm writing a standard Macintosh GUI wrapper with a progress bar and sound input selector. -- Karen Kim -- INRIA Rocquencourt "5 sigma is a discovery. 7 is a question." From bpetrov@kth.se Sun Mar 05 02:04:20 1995 Path: ashpoly!cascade!mxgate!coyoacan!kth!bpetrov From: bpetrov@kth.se (Bill Petrov) Newsgroups: comp.sys.m68k Subject: Re: [FLAME] Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Mar05.020420.9805@kth.se> Date: Sun, 05 Mar 1995 02:04:20 GMT References: <1995Mar03.180920.5025@inria.fr> Organization: Royal Institute of Technology, Stockholm NNTP-Posting-Host: kth.se X-Newsreader: Netscape 1.1N Lines: 10 In article <1995Mar03.180920.5025@inria.fr>, kkim@inria.fr (Karen Kim) writes: > Compiling stardust.c with Think C 6.0 vs MPW C with direct 68882 inlining. > By passing the -mc68882 compiler flag in Think C, all sin/cos and sqrt operations compile directly to FPU opcodes. Mac users bragging about 6-minute render times while Unix workstations do it in 20 seconds. Classic Apple distortion field. -- Bill Petrov Opinions expressed are solely my own and not those of Royal Institute of Technology, Stockholm. ------------------------------------------------------------ From agonzalez@netcom.com Sun Mar 05 22:28:20 1995 Path: ashpoly!cascade!transat!eunet-fi!relcom!kiae!netcom!agonzalez From: agonzalez@netcom.com (Amy González) Newsgroups: comp.sys.m68k Subject: Re: [FLAME] Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Mar05.222820.5575@netcom.com> Date: Sun, 05 Mar 1995 22:28:20 GMT References: <1995Mar03.180920.5025@inria.fr> <1995Mar05.020420.9805@kth.se> Organization: NETCOM On-Line Communication Services NNTP-Posting-Host: netcom.com X-Newsreader: Netscape 1.1N Lines: 9 In article <1995Mar05.020420.9805@kth.se>, bpetrov@kth.se (Bill Petrov) 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. -- Amy González Opinions expressed are solely my own and not those of NETCOM On-Line Communication Services. ------------------------------------------------------------ From mhernandez@ox.ac.uk Tue Mar 07 08:55:20 1995 Path: ashpoly!bigsur!pacrim!krgate!eunha!ox!mhernandez From: mhernandez@ox.ac.uk (Mikhail Hernández) Newsgroups: comp.sys.m68k Subject: Re: [FLAME] Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Mar07.085520.5692@ox.ac.uk> Date: Tue, 07 Mar 1995 08:55:20 GMT References: <1995Mar03.180920.5025@inria.fr> <1995Mar05.020420.9805@kth.se> <1995Mar05.222820.5575@netcom.com> Organization: Oxford University Computing Laboratory NNTP-Posting-Host: ox.ac.uk X-Newsreader: TIN [version 1.2 PL2] Lines: 9 In article <1995Mar05.222820.5575@netcom.com>, agonzalez@netcom.com (Amy González) writes: > Beware of System 7.5.1 memory leaks if you allocate large sample buffers in the application heap. Use NewPtrSys instead. The 68040 on the Quadra is a monster -- the on-chip FPU executes FFT butterflies in less than 4 milliseconds. -- Mikhail Hernández "5 sigma is a discovery. 7 is a question." Decstation 5000/200 / FreeBSD 2.1