Quote:
Originally Posted by echosierra
Last relevant post was about the ps2's non-standard fpu.
Are the fpu differences just a matter of bit width? I know the ps2's fpu does some funky clamping for values that cause overflow/underflow, but it seems kinda strange that some games (Metal Gear) would be so sensitive to the inaccuracies that gameplay would be impacted.
Is there publicly available documentation on the specifics of the ps2's fpu?
Finally, something in the emulator that I understand  |
not sure if theres anything publicly available, but youd be right. the PS2's FPU (more specifically the vector units) have strange value rounding, they dont support positive or negative infinities, nor do they allow NaN values.
doing this on a chip which does account for positive/negative infinities, controls NaN's and has multiple rounding modes, its quite difficult! ;p
__________________
http://www.generalemu.net/
Intel Core 2 Quad Q6600 @ 3.4Ghz (425x8), Leadtek GTX 280 1Gb, 1.8Tb HDs, 2Gb Corsair DDR2-800 @ DDR2-1020 5-5-5-18 Dual Channel
Dont PM me for help, use the forums, thats what its for!