ARM® Developer Suite Compilers and Libraries Guide 2.3.7. Specifying the target processor or architecture

2.3.7. Specifying the target processor or architecture

The options described in this section specify the target processor or architecture attributes for a compilation. The compiler can take advantage of certain extra features of the selected processor or architecture, such as support for halfword load and store instructions and instruction scheduling.

Note

Specifying the target processor can make the code incompatible with other ARM processors.

The following general points apply to processor and architecture options:

The supported -cpu values are all current ARM product names or architecture versions. There are no aliases or wildcard matching.
If you specify an architecture name for the -cpu option, the code is compiled to run on any processor supporting that architecture. For example -cpu 4T produces code that can be used by either the ARM7TDMI^® or ARM9TDMI™.
If you specify a processor for the -cpu option, for example -cpu ARM1020E, the compiled code is optimized for that processor. This enables the compiler to use specific coprocessors or instruction scheduling for optimum performance.
Use only a single processor or architecture name with -cpu. You cannot specify both a processor and an architecture.
If -cpu is not specified, the default is -cpu ARM7TDMI.
Specifying a Thumb-aware processor, such as -cpu ARM7TDMI to armcc or armcpp does not make these compilers generate Thumb code. It only allows features of the processor to be used, such as interworking instructions. Use tcc or tcpp to generate Thumb code.

The following options are available:

-cpu name

This option generates code for a specific ARM processor or architecture.

If name is a processor:

You must enter the name exactly as it is shown on ARM data sheets, for example ARM7TDMI. Wildcard characters are not accepted. Valid values are any ARM6 or later ARM processor.
Selecting the processor selects the appropriate architecture, fpu, and memory organization.
Some -cpu selections imply an -fpu selection. For example, with the ARM compilers -cpu ARM10200E implies -fpu vfpv2. The implied -fpu is overridden if you specify an explicit -fpu option. If no -fpu option and no -cpu option are specified, -fpu softvfp is used.

If name is an architecture, it must be one of:

3: ARMv3 without long multiply.
3M: ARMv3 with long multiply.
4: ARMv4 with long multiply but no Thumb.
4xM: ARMv4 without long multiply or Thumb.
4T: ARMv4 with long multiply and Thumb.
4TxM: ARMv4 without long multiply but with Thumb.
5T: ARMv5 with long multiply and Thumb.
5TE: ARMv5 with long multiply, Thumb, DSP multiply, and double-word instructions.
5TEJ: ARMv5 with long multiply, Thumb, DSP multiply, double-word instructions, and Jazelle extensions.

-fpu name

This option selects the target Floating-Point Unit (FPU) architecture. If you specify this option it overrides any implicit FPU set by the -cpu option.

Valid options are:

none

Selects no floating-point option. No floating-point code is to be used.

vfp

Selects hardware vector floating-point unit conforming to architecture VFPv1. This is a synonym for -fpu vfpv1. This option is not available for the Thumb compilers.

vfpv1

Selects hardware vector floating-point unit conforming to architecture VFPv1, such as the VFP10 rev 0. This option is not available for the Thumb compilers.

vfpv2

Selects hardware vector floating-point unit conforming to architecture VFPv2, such as the VFP10 rev 1. This option is not available for the Thumb compilers.

fpa

Selects hardware Floating Point Accelerator (FPA). This option is not available for the Thumb compilers and is only provided for backwards compatibility.

softvfp+vfp

Selects a floating-point library with pure-endian doubles and software floating-point linkage that uses the VFP hardware. Select this option if you are interworking Thumb code with ARM code on a system that implements a VFP unit.

If you select this option:

tcc and tcpp behave exactly as for -fpu softvfp except that they link with VFP-optimized floating-point libraries.
armcc and armcpp behave the same as for -fpu vfp except that all functions are given software floating-point linkage. This means that ARM functions compiled with this option pass and return floating-point arguments and results as they would for -fpu softvfp, but use VFP instructions internally.

Note

If you specify this option for both armcc and tcc, it ensures that your interworking floating-point code is compiled to use software floating-point linkage. If you specify vfp, vfpv1, or vfpv2 for armcc you must use the __softfp keyword to ensure that your interworking ARM code is compiled to use software floating-point linkage. See the description of __softfp in Function keywords for more information.

softvfp

Selects software floating-point library (FPLib) with pure-endian doubles. This is the default if you do not specify a -fpu option.

softfpa

Selects software floating-point library with mixed-endian doubles.

Copyright © 1999-2001 ARM Limited. All rights reserved.	ARM DUI 0067D
Non-Confidential
PDF version