fma, Qfma

Enables the combining or contraction of floating-point multiplications and add or subtract operations.

IDE Equivalent

Windows: None

Linux: Floating Point > Floating-point Operation Contraction

Mac OS X: None

Architectures

IA-64 architecture

Syntax

Linux:

-fma

-no-fma

Mac OS X:

None

Windows:

/Qfma

/Qfma-

Arguments

None

Default

-fma
or/Qfma

Floating-point multiplications and add/subtract operations are combined.

However, if you specify -fp-model strict (Linux) or /fp:strict (Windows), but do not explicitly specify -fma or /Qfma, the default is -no-fma or /Qfma-.

Description

This option enables the combining or contraction of floating-point multiplications and add or subtract operations into a single operation.

Alternate Options

Linux: -IPF-fma (this is a deprecated option)

Windows: /QIPF-fma (this is a deprecated option)

See Also