This thread has been locked.

If you have a related question, please click the "Ask a related question" button in the top right corner. The newly created question will be automatically linked to this question.

Configure CMSIS library to use FPU on Tiva C Series

Other Parts Discussed in Thread: TM4C123GH6PGE

I am using the DSP functionalty in the CMSIS library on the Tiva C Series TM4C123GH6PGE board that uses the ARM Cortex M4F.  The DSP function does its calculation using floating point units.  I am wondering how to I enable/configure the Floating Point Unit (FPU) so that the DSP function takes advantage of it to run faster.  

On the project properties I have the predefined "__FPU_PRESENT".  I'm sure there are other things that I need to configure.  However I cannot find any example code to setup the FPU.  Can you guys help me out?

  • Hi,

    First of all you need to specify the toolchain used, since there are differences between them. Your __FPU_PRESENT=1 is for GCC use for instance. For CCS maybe you need other settings. ARM recommends also to #include "arm_math.h" (provide the right path for this) and to pre-define the symbol ARM_MATH_CM4 in pre-processor/compiler settings.
    How to use with CCS is described in an application note you may find out on micro page, on TI site (http://www.ti.com/lit/an/spma041c/spma041c.pdf).
    Petrei

  • Poster Petrei makes (as always) most valid points - you do need to confirm your (most assured) use of hallowed CCS.  (i.e. lock yourself to one vendor - forever...)

    Beyond his good guidance - do not multiple, pre-programmed examples exist (some in prominence) which illustrate, "just that you seek?" 

    Better search/read/review of the bulk, tech. source material - nicely supplied by this vendor - will surely best propel your MCU development efforts.