Developer Guide and Reference

Contents

_mm_fmsubadd_pd, _mm256_fmsubadd_pd

Multiply-subtracts and adds packed double-precision floating-point values using three float64 vectors. The corresponding FMA instruction is
VFMSUBADD<XXX>PD
, where XXX could be 132, 213, or 231.

Syntax

For 128-bit vector
extern __m128d _mm_fmsubadd_pd(__m128d a, __m128d b, __m128d c);
For 256-bit vector
extern __m256d _mm256_fmsubadd_pd(__m256d a, __m256d b, __m256d c);
Arguments
a
float64 vector used for the operation
b
float64 vector also used for the operation
c
float64 vector also used for the operation
Description
Performs a set of SIMD multiply-subtract-add computation on packed double-precision floating-point values using three source vectors/operands,
a
,
b
, and
c
. Corresponding values in two operands,
a
and
b
, are multiplied and infinite precision intermediate results are obtained. The odd values in the third operand,
c
, are subtracted from the intermediate results while the even values are added to them. The final results are rounded to the nearest float64 values.
The compiler defaults to using the
VFMSUBADD213PD
instruction and uses the other forms
VFMSUBADD132PD
or
VFMSUBSADD231PD
only if a low-level optimization decides it is useful or 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-subtr