14.33 VCVT (between fixed-point or integer, and floating-point)
is an optional condition code.
specifies the data types for the elements of thevectors. It must be one of:
Floating-point to signed integer or fixed-point.
Floating-point to unsigned integer or fixed-point.
Signed integer or fixed-point to floating-point.
Unsigned integer or fixed-point to floating-point.
specifies the destination vector and the operandvector, for a quadword operation.
specifies the destination vector and the operandvector, for a doubleword operation.
if present, specifies the number of fraction bitsin the fixed point number. Otherwise, the conversion is betweenfloating-point and integer.
mustlie in the range 0-32. If
isomitted, the number of fraction bits is 0.
VCVT converts each element in a vector in one of the following ways, and places the results in the destination vector:
From floating-point to integer.
From integer to floating-point.
From floating-point to fixed-point.
From fixed-point to floating-point.
Integer or fixed-point to floating-point conversions use roundto nearest.
Floating-point to integer or fixed-point conversions use roundtowards zero.