Developer Guide and Reference

Contents

_mm_fmadd_ss

Multiply-adds scalar single-precision floating-point values using three float32vectors. The corresponding FMA instruction is
VFMADD<XXX>SS
, where XXX could be 132, 213, or 231.

Syntax

extern __m128 _mm_fmadd_ss(__m128 a, __m128 b, __m128 c);
Arguments
a
float32 vector used for the operation
b
float32 vector also used for the operation
c
float32 vector also used for the operation
Description
Performs a set of scalar SIMD multiply-add computation on scalar single-precision floating-point values in the low 32-bits of three source operands,
a
,
b
, and
c
. The float32 values in two operands, a and b, are multiplied and the infinite precision intermediate result is obtained. The float32 value in the third operand,
c
, is added to the infinite precision intermediate result. The final result is rounded to the nearest float32 value.
The compiler defaults to using the
VFMADD213SS
instruction and uses the other forms
VFMADD132SS
or
VFMADD231SS
only if a low level optimization decides it is useful/necessary. For example, the compiler could change the default if it finds that another instruction form saves a register or eliminates a move.
Returns
Result of the multiply-add operation.