> > For example, the Daystar PowerCentral control panel > > seems to accelerate FPU performance on the IIci, even with no Daystar > > hardware installed. > > Apparently you had the PowerMath switch on. That > redirects any SANE math calls normally processed > by the CPU to the FPU. It works even with an 030 > PowerCache that doesn't have an FPU installed. > Evidentially you wrote your benchmark to use SANE > functions.
SieveAhl is indeed 100% SANE, but it seems strange that SANE wouldn't do that already on the IIci. Doesn't SANE use the FPU if present? The docs I consulted allege that it would (SANE F-traps mapped automatically to equivalent FPU instructions if an '881/'882 is present), and my results bear this out (Ahl 567% with no '882 in the IIsi, but 948% with). Perhaps the PowerMath code is just more efficient at mapping the calls? I guess the logical test for that would be to stick it on a IIsi without an FPU (so that call overhead, not FPU performance, is being tested), and see if SANE performance is similarly accelerated. -- ----------------------------- personal page: http://www.armory.com/~spectre/ -- Cameron Kaiser, Point Loma Nazarene University * [EMAIL PROTECTED] -- There is no Dark Side of the Moon, really. Matter of fact, it's all dark. -- -- Vintage Macs is sponsored by <http://lowendmac.com/> and... Small Dog Electronics http://www.smalldog.com | Enter To Win A | -- Canon PowerShot Digital Cameras start at $299 | Free iBook! | Support Low End Mac <http://lowendmac.com/lists/support.html> Vintage Macs list info: <http://lowendmac.com/lists/vintagemacs.shtml> The FAQ: <http://macfaq.org/> Send list messages to: <mailto:[EMAIL PROTECTED]> To unsubscribe, email: <mailto:[EMAIL PROTECTED]> For digest mode, email: <mailto:[EMAIL PROTECTED]> Subscription questions: <mailto:[EMAIL PROTECTED]> Archive: <http://www.mail-archive.com/vintage.macs%40mail.maclaunch.com/> Using a Mac? Free email & more at Applelinks! http://www.applelinks.com
