How to use the efficiency of FPU and DSP on Kinetis KV3x??

[neil168]

1. 

Here are the two methods I have tried:

1.1 Set the FPU using the settings on the IDE.
1.2 Use the register to set the FPU.

SCB->CPACR |= ((3UL << 10*2) | (3UL << 11*2));

But these can't let me improve the efficiency of floating point arithmetic.

After asking if the FPU is turned on, use the FPU operation method or the sample project or technical file??

2. How does the DSP work with Kinetis KV3x?? Is there a technical manual for reference?? or sample project??

thanks!!

[FelipeGarcia]

Hello Neil,

I recommend you to check the following project for a KV31F:

https://community.nxp.com/docs/DOC-328241

In addition, please take a look to the post below, it gives an example on how to use the DSP library on Kinetis Devices:

https://mcuoneclipse.com/2013/02/14/tutorial-using-the-arm-cmsis-library/

Hope it helps!

Best regards,

Felipe

-------------------------------------------------------------------------------
Note:
- If this post answers your question, please click the "Mark Correct" button. Thank you!

- We are following threads for 7 weeks after the last post, later replies are ignored
Please open a new thread and refer to the closed one, if you have a related question at a later point in time.
-------------------------------------------------------------------------------

[neil168]

Dear Felipe García,

1. DSP LIB import message can be used for reference, thank you
2. But I found the usage of atan. There is no such use in arm_math.h. I have only found that there is math.h, but the parameters in the call cannot make the FPU efficiency of KV3x arm core show. And the time it runs is unusually long, is there a way to use atan correctly??

[FelipeGarcia]

Hi Neil,

Unfortunately, those functions are not included in the DSP CMSIS library. In the library you can find some other functions like arm_sin, arm_cos and arm_sin_cos.

As far as I know, there is a plan to add support for those functions in future releases. Although, there are some mathematical function implementations that can be used to implement those functions such as sin and cos.

Sorry for the inconvenience this may cause you.

Best regards,

Felipe

[neil168]

thanks!!