On Wed, Oct 14, 2015 at 11:30 AM, Matt Turner wrote:
> NIR considers bcsel to produce and consume unsigned types, leading to
> SEL instructions operating on unsigned types when the data is really
> floating-point. Previous to this patch, saturate propagation would
> happily
NIR considers bcsel to produce and consume unsigned types, leading to
SEL instructions operating on unsigned types when the data is really
floating-point. Previous to this patch, saturate propagation would
happily transform
(+f0) sel g20:UD, g30:UD, g40:UD
mov.sat g50:F, g20:F