softfloat: Add support for ties-away rounding
commitf9288a76f1819c2dbf8d2873aebab6aec0f461f5
authorPeter Maydell <peter.maydell@linaro.org>
Tue, 7 Jan 2014 17:19:12 +0000 (7 17:19 +0000)
committerPeter Maydell <peter.maydell@linaro.org>
Wed, 8 Jan 2014 19:07:22 +0000 (8 19:07 +0000)
tree2dd23209dc6a2cf78d917e3ca6ecfebee548c6a8
parentdc355b764de890e1b5872d0b402dccfd9a9b5286
softfloat: Add support for ties-away rounding

IEEE754-2008 specifies a new rounding mode:

"roundTiesToAway: the floating-point number nearest to the infinitely
precise result shall be delivered; if the two nearest floating-point
numbers bracketing an unrepresentable infinitely precise result are
equally near, the one with larger magnitude shall be delivered."

Implement this new mode (it is needed for ARM). The general principle
is that the required code is exactly like the ties-to-even code,
except that we do not need to do the "in case of exact tie clear LSB
to round-to-even", because the rounding operation naturally causes
the exact tie to round up in magnitude.

Signed-off-by: Peter Maydell <peter.maydell@linaro.org>
Reviewed-by: Richard Henderson <rth@twiddle.net>
fpu/softfloat.c
include/fpu/softfloat.h