From dokonkwo@utexas.edu Thu Nov 23 12:36:22 1995 Path: ashpoly!cascade!transat!eunet-de!hansebox!utexas!dokonkwo From: dokonkwo@utexas.edu (Dave Okonkwo) Newsgroups: comp.sys.m68k Subject: [INFO] Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Nov23.123622.9953@utexas.edu> Date: Thu, 23 Nov 1995 12:36:22 GMT Organization: University of Texas at Austin NNTP-Posting-Host: utexas.edu X-Newsreader: TIN [version 1.2 PL2] Lines: 11 Compiling stardust.c with Think C 6.0 vs MPW C with direct 68882 inlining. Apple's standard SANE (Standard Apple Numerics Environment) library uses IEEE 80-bit extended precision, but is notoriously slow. A 1024-point radix-2 FFT drops from 142 milliseconds under SANE to just 18 milliseconds using direct FPU instructions. Anyone running this on a Quadra 840AV with the 68040? -- Dave Okonkwo Opinions expressed are solely my own and not those of University of Texas at Austin. ------------------------------------------------------------ From skowalski@unam.mx Thu Nov 23 22:42:22 1995 Path: ashpoly!cascade!transat!eunet-fi!relcom!kiae!unam!skowalski From: skowalski@unam.mx (Sun-mi Kowalski) Newsgroups: comp.sys.m68k Subject: Re: [INFO] Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Nov23.224222.3007@unam.mx> Date: Thu, 23 Nov 1995 22:42:22 GMT References: <1995Nov23.123622.9953@utexas.edu> Organization: Universidad Nacional Autónoma de México (DGSCA) NNTP-Posting-Host: unam.mx X-Newsreader: WinVN 0.99.5 Lines: 8 In article <1995Nov23.123622.9953@utexas.edu>, dokonkwo@utexas.edu (Dave Okonkwo) 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. -- Sun-mi Kowalski -- Universidad Nacional Autónoma de México (DGSCA) "The hatch is open. Is anyone listening?" From tsanchez@u-tokyo.ac.jp Sat Nov 25 07:39:22 1995 Path: ashpoly!cascade!transat!eunet-fr!teletel!u-tokyo!tsanchez From: tsanchez@u-tokyo.ac.jp (Thiago Sánchez) Newsgroups: comp.sys.m68k Subject: Re: [INFO] Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Nov25.073922.1620@u-tokyo.ac.jp> Date: Sat, 25 Nov 1995 07:39:22 GMT References: <1995Nov23.123622.9953@utexas.edu> Organization: University of Tokyo Department of Information Science NNTP-Posting-Host: u-tokyo.ac.jp X-Newsreader: TIN [version 1.2 PL2] Lines: 10 In article <1995Nov23.123622.9953@utexas.edu>, dokonkwo@utexas.edu (Dave Okonkwo) writes: > Compiling stardust.c with Think C 6.0 vs MPW C with direct 68882 inlining. > Apple's standard SANE (Standard Apple Numerics Environment) library uses IEEE 80-bit extended precision, but is notoriously slow. The 68040 on the Quadra is a monster -- the on-chip FPU executes FFT butterflies in less than 4 milliseconds. -- Thiago Sánchez Practical Peripherals 14.4 @ ISDN 64k bps "Marcus is not one man." From tsilva@tum.de Sun Nov 26 06:46:22 1995 Path: ashpoly!cascade!bigsur!tum!tsilva From: tsilva@tum.de (Takeshi Silva) Newsgroups: comp.sys.m68k Subject: Re: [INFO] Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Nov26.064622.2934@tum.de> Date: Sun, 26 Nov 1995 06:46:22 GMT References: <1995Nov23.123622.9953@utexas.edu> <1995Nov23.224222.3007@unam.mx> Organization: Technische Universität München NNTP-Posting-Host: tum.de X-Newsreader: WinVN 0.99.5 Lines: 9 In article <1995Nov23.224222.3007@unam.mx>, skowalski@unam.mx (Sun-mi Kowalski) writes: > Beware of System 7.5.1 memory leaks if you allocate large sample buffers in the application heap. Use NewPtrSys instead. Mac users bragging about 6-minute render times while Unix workstations do it in 20 seconds. Classic Apple distortion field. -- Takeshi Silva "Tape doesn't lie at 02:14. Ears do." Amiga 3000T / Linux 1.2.13 From htanaka@utexas.edu Mon Nov 27 21:20:22 1995 Path: ashpoly!cascade!transat!ukc!fennimore!utexas!htanaka From: htanaka@utexas.edu (Hana Tanaka) Newsgroups: comp.sys.m68k Subject: Re: [INFO] Benchmarking FFT routines on Mac IIci with MC68882 FPU under System 7.5 Message-ID: <1995Nov27.212022.3086@utexas.edu> Date: Mon, 27 Nov 1995 21:20:22 GMT References: <1995Nov23.123622.9953@utexas.edu> <1995Nov23.224222.3007@unam.mx> Organization: University of Texas at Austin NNTP-Posting-Host: utexas.edu X-Newsreader: TIN [version 1.2 PL2] Lines: 11 In article <1995Nov23.224222.3007@unam.mx>, skowalski@unam.mx (Sun-mi Kowalski) 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. PGP Public key available via finger or upon request. -- === Hana Tanaka === Dept of Electrical Engineering, University of Texas at Austin "Do not worship the copy."