|Non-Confidential||PDF version||ARM DUI0473M|
|Home > Assembler Command-line Options > --fpu=name|
Specifies the target FPU architecture.
is one of:
Selects no floating-point option. No floating-point code is to be used. This produces an error if your code contains floating-point instructions.
Selects a hardware floating-point unit conforming to architecture VFPv2.
--fpuoption, or if you select a CPU that does not have an FPU.
Selects a hardware floating-point unit conforming to VFPv2, with software floating-point linkage. Select this option if you are interworking Thumb code with ARM code on a system that implements a VFP unit.
To obtain a full list of FPU architectures use the
If you specify this option, it overrides any implicit FPU option
that appears on the command line, for example, where you use the
Any FPU explicitly selected using the
--fpu option always overrides any FPU implicitly selected using
--cpu option. For example, the option
--cpu=ARM1136JF-S --fpu=SoftVFP generates
code that uses the software floating-point library fplib, even though the choice of CPU implies the use of
armasm sets a build attribute corresponding to name in the object file. The linker determines compatibility between object files, and selection of libraries, accordingly.
To control floating-point linkage without affecting the choice of
FPU, you can use
armasm only permits hardware VFP
architectures, such as
--fpu=SoftVFP+VFPv2, to be specified when
MCRR instructions are
supported in the processor instruction set.
MCRR instructions are not supported in 4, 4T,
5T and 6-M. Therefore, armasm does not allow the
use of these CPU architectures with hardware VFP architectures.
Other than this, armasm does not check that
combinations are valid. Beyond the scope of the assembler, additional architectural
constraints apply. For example, VFPv3 is not supported with architectures prior to
ARMv7. Therefore, the combination of
--cpu options permitted by
armasm does not necessarily translate to the actual device in
NEON support is disabled for
The default target FPU architecture is derived from use of the
If the CPU specified with
--cpu has a VFP
coprocessor, the default target FPU architecture is the VFP architecture for that
CPU. For example, the option
implies the option
--fpu VFPv2. If a VFP
coprocessor is present, VFP instructions are generated.