This discussion has been locked.
You can no longer post new replies to this discussion. If you have a question you can start a new discussion

Do floating-point computations differ in different ARM processors?

Hello,

In my project, I ran a numerical computing algorithm in C99 in an ARM Cortex®-A53 of Raspberry Pi, but the target is an embedded system using ARM Cortex M4F.
Both have a Floating-Point Unit and operate natively in a single precision floating point (FP32) under IEEE 754 format, and the numerical algorithm uses FP32 only.

Considering also they are using the same C Compiler. My question is:

- Are the results of the numerical algorithm from different cited ARM processors the same?
- If they differ, is the difference big or small?
- Do you have any reference material?


Thank you very much indeed.