• State Resolved
  • Locked Locked
  • Replies 1 reply
  • Subscribers 82 subscribers
  • Views 429 views
  • Users 0 members are here
Support feedback
Options
Options
Related

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.

TMS320F28377S: Efficient 64-bit double precision floating point implementation

Darius Tan
Prodigy 10 points

Part Number: TMS320F28377S

Hello,

We are trying to implement double precision floating point computation on the F28177S DSP as the float precision of 6 decimal points is not sufficient for our application.

Based on C2000 Optimization Guide, "there is significant overhead when application compiled for EABI performs operations on double types", and it seems like "Delfino microcontrollers only support 32-bit float in hardware. 64-bit float is performed in software" as per the TMS320C28x FPU Primer.

What are the libraries that are available that we can use for double precision computation with minimal overhead?

Or, what would be the ideal method of implementing double precision computation?

Are there any examples available for our reference?

Thanks for the help!

  • +1
    TI__Expert 5410 points

    Hi,

    Apart from on F2838x, no device has an FPU64 to support double precision in hardware. On devices with only FPU32, 64 bit float operations need to be implemented in software based on the documents that you pointed out. There are no libraries for double precision on FPU32. 

    -Shantanu