2011/4/10 James K Beard <[email protected]>:
> There are better libraries than mine for 128-bit, which is quad precision,
> that use 12-bit exponents; my package always uses 16-bit exponents.  Quad
> precision packages use the hardware 80-bit floating point in most CPU cores
> these days and would be smaller and faster than my package.  My package is
> useful for precisions higher than 128 bits.  I typically use it for 256 bits
> and higher.

Sorry, I don't talk here about 80-bit floating point. I am talking
about 128-bit and this isn't supported in hardware by x86/x64 CPU. The
exponent for 128-bit is 15-bit, 1-bit for sign, and 112 bits for
mantissa, at least as IEEE defines it.

Kai

------------------------------------------------------------------------------
Xperia(TM) PLAY
It's a major breakthrough. An authentic gaming
smartphone on the nation's most reliable network.
And it wants your games.
http://p.sf.net/sfu/verizon-sfdev
_______________________________________________
Mingw-w64-public mailing list
[email protected]
https://lists.sourceforge.net/lists/listinfo/mingw-w64-public

Reply via email to